kreuzcrawl 0.1.0.pre.rc.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/ext/kreuzcrawl_rb/Cargo.lock +3162 -0
- data/ext/kreuzcrawl_rb/Cargo.toml +15 -0
- data/ext/kreuzcrawl_rb/extconf.rb +10 -0
- data/ext/kreuzcrawl_rb/src/kreuzcrawl/version.rb +6 -0
- data/ext/kreuzcrawl_rb/src/kreuzcrawl.rb +9 -0
- data/ext/kreuzcrawl_rb/src/lib.rs +4835 -0
- data/lib/kreuzcrawl.rb +3 -0
- data/lib/kreuzcrawl_rb.bundle +0 -0
- metadata +63 -0
|
@@ -0,0 +1,4835 @@
|
|
|
1
|
+
// This file is auto-generated by alef. DO NOT EDIT.
|
|
2
|
+
// Re-generate with: alef generate
|
|
3
|
+
#![allow(dead_code)]
|
|
4
|
+
|
|
5
|
+
use magnus::{Error, IntoValueFromNative, Ruby, function, method, prelude::*, try_convert::TryConvertOwned};
|
|
6
|
+
use std::collections::HashMap;
|
|
7
|
+
use std::sync::Arc;
|
|
8
|
+
|
|
9
|
+
fn json_to_ruby(handle: &Ruby, val: serde_json::Value) -> magnus::Value {
|
|
10
|
+
use magnus::IntoValue;
|
|
11
|
+
match val {
|
|
12
|
+
serde_json::Value::Null => handle.qnil().into_value_with(handle),
|
|
13
|
+
serde_json::Value::Bool(b) => b.into_value_with(handle),
|
|
14
|
+
serde_json::Value::Number(n) => {
|
|
15
|
+
if let Some(i) = n.as_i64() {
|
|
16
|
+
i.into_value_with(handle)
|
|
17
|
+
} else if let Some(f) = n.as_f64() {
|
|
18
|
+
f.into_value_with(handle)
|
|
19
|
+
} else {
|
|
20
|
+
handle.qnil().into_value_with(handle)
|
|
21
|
+
}
|
|
22
|
+
}
|
|
23
|
+
serde_json::Value::String(s) => s.into_value_with(handle),
|
|
24
|
+
serde_json::Value::Array(arr) => {
|
|
25
|
+
let ruby_arr = handle.ary_new_capa(arr.len());
|
|
26
|
+
for item in arr {
|
|
27
|
+
let _ = ruby_arr.push(json_to_ruby(handle, item));
|
|
28
|
+
}
|
|
29
|
+
ruby_arr.into_value_with(handle)
|
|
30
|
+
}
|
|
31
|
+
serde_json::Value::Object(map) => {
|
|
32
|
+
let hash = handle.hash_new();
|
|
33
|
+
for (k, v) in map {
|
|
34
|
+
let key = handle.to_symbol(&k);
|
|
35
|
+
let val = json_to_ruby(handle, v);
|
|
36
|
+
let _ = hash.aset(key, val);
|
|
37
|
+
}
|
|
38
|
+
hash.into_value_with(handle)
|
|
39
|
+
}
|
|
40
|
+
}
|
|
41
|
+
}
|
|
42
|
+
|
|
43
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
44
|
+
#[magnus::wrap(class = "Kreuzcrawl::ExtractionMeta")]
|
|
45
|
+
#[serde(default)]
|
|
46
|
+
pub struct ExtractionMeta {
|
|
47
|
+
pub cost: Option<f64>,
|
|
48
|
+
pub prompt_tokens: Option<u64>,
|
|
49
|
+
pub completion_tokens: Option<u64>,
|
|
50
|
+
pub model: Option<String>,
|
|
51
|
+
pub chunks_processed: usize,
|
|
52
|
+
}
|
|
53
|
+
|
|
54
|
+
unsafe impl IntoValueFromNative for ExtractionMeta {}
|
|
55
|
+
|
|
56
|
+
impl magnus::TryConvert for ExtractionMeta {
|
|
57
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
58
|
+
let r: &ExtractionMeta = magnus::TryConvert::try_convert(val)?;
|
|
59
|
+
Ok(r.clone())
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
unsafe impl TryConvertOwned for ExtractionMeta {}
|
|
63
|
+
|
|
64
|
+
impl Default for ExtractionMeta {
|
|
65
|
+
fn default() -> Self {
|
|
66
|
+
Self {
|
|
67
|
+
cost: Default::default(),
|
|
68
|
+
prompt_tokens: Default::default(),
|
|
69
|
+
completion_tokens: Default::default(),
|
|
70
|
+
model: Default::default(),
|
|
71
|
+
chunks_processed: Default::default(),
|
|
72
|
+
}
|
|
73
|
+
}
|
|
74
|
+
}
|
|
75
|
+
|
|
76
|
+
impl ExtractionMeta {
|
|
77
|
+
fn new(
|
|
78
|
+
cost: Option<f64>,
|
|
79
|
+
prompt_tokens: Option<u64>,
|
|
80
|
+
completion_tokens: Option<u64>,
|
|
81
|
+
model: Option<String>,
|
|
82
|
+
chunks_processed: Option<usize>,
|
|
83
|
+
) -> Self {
|
|
84
|
+
Self {
|
|
85
|
+
cost,
|
|
86
|
+
prompt_tokens,
|
|
87
|
+
completion_tokens,
|
|
88
|
+
model,
|
|
89
|
+
chunks_processed: chunks_processed.unwrap_or_default(),
|
|
90
|
+
}
|
|
91
|
+
}
|
|
92
|
+
|
|
93
|
+
fn cost(&self) -> Option<f64> {
|
|
94
|
+
self.cost
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
fn prompt_tokens(&self) -> Option<u64> {
|
|
98
|
+
self.prompt_tokens
|
|
99
|
+
}
|
|
100
|
+
|
|
101
|
+
fn completion_tokens(&self) -> Option<u64> {
|
|
102
|
+
self.completion_tokens
|
|
103
|
+
}
|
|
104
|
+
|
|
105
|
+
fn model(&self) -> Option<String> {
|
|
106
|
+
self.model.clone()
|
|
107
|
+
}
|
|
108
|
+
|
|
109
|
+
fn chunks_processed(&self) -> usize {
|
|
110
|
+
self.chunks_processed
|
|
111
|
+
}
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
115
|
+
#[magnus::wrap(class = "Kreuzcrawl::ProxyConfig")]
|
|
116
|
+
#[serde(default)]
|
|
117
|
+
pub struct ProxyConfig {
|
|
118
|
+
pub url: String,
|
|
119
|
+
pub username: Option<String>,
|
|
120
|
+
pub password: Option<String>,
|
|
121
|
+
}
|
|
122
|
+
|
|
123
|
+
unsafe impl IntoValueFromNative for ProxyConfig {}
|
|
124
|
+
|
|
125
|
+
impl magnus::TryConvert for ProxyConfig {
|
|
126
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
127
|
+
let r: &ProxyConfig = magnus::TryConvert::try_convert(val)?;
|
|
128
|
+
Ok(r.clone())
|
|
129
|
+
}
|
|
130
|
+
}
|
|
131
|
+
unsafe impl TryConvertOwned for ProxyConfig {}
|
|
132
|
+
|
|
133
|
+
impl Default for ProxyConfig {
|
|
134
|
+
fn default() -> Self {
|
|
135
|
+
Self {
|
|
136
|
+
url: Default::default(),
|
|
137
|
+
username: Default::default(),
|
|
138
|
+
password: Default::default(),
|
|
139
|
+
}
|
|
140
|
+
}
|
|
141
|
+
}
|
|
142
|
+
|
|
143
|
+
impl ProxyConfig {
|
|
144
|
+
fn new(url: Option<String>, username: Option<String>, password: Option<String>) -> Self {
|
|
145
|
+
Self {
|
|
146
|
+
url: url.unwrap_or_default(),
|
|
147
|
+
username,
|
|
148
|
+
password,
|
|
149
|
+
}
|
|
150
|
+
}
|
|
151
|
+
|
|
152
|
+
fn url(&self) -> String {
|
|
153
|
+
self.url.clone()
|
|
154
|
+
}
|
|
155
|
+
|
|
156
|
+
fn username(&self) -> Option<String> {
|
|
157
|
+
self.username.clone()
|
|
158
|
+
}
|
|
159
|
+
|
|
160
|
+
fn password(&self) -> Option<String> {
|
|
161
|
+
self.password.clone()
|
|
162
|
+
}
|
|
163
|
+
}
|
|
164
|
+
|
|
165
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
|
166
|
+
#[magnus::wrap(class = "Kreuzcrawl::BrowserConfig")]
|
|
167
|
+
#[serde(default)]
|
|
168
|
+
pub struct BrowserConfig {
|
|
169
|
+
pub mode: BrowserMode,
|
|
170
|
+
pub endpoint: Option<String>,
|
|
171
|
+
pub timeout: u64,
|
|
172
|
+
pub wait: BrowserWait,
|
|
173
|
+
pub wait_selector: Option<String>,
|
|
174
|
+
pub extra_wait: Option<u64>,
|
|
175
|
+
}
|
|
176
|
+
|
|
177
|
+
unsafe impl IntoValueFromNative for BrowserConfig {}
|
|
178
|
+
|
|
179
|
+
impl magnus::TryConvert for BrowserConfig {
|
|
180
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
181
|
+
let r: &BrowserConfig = magnus::TryConvert::try_convert(val)?;
|
|
182
|
+
Ok(r.clone())
|
|
183
|
+
}
|
|
184
|
+
}
|
|
185
|
+
unsafe impl TryConvertOwned for BrowserConfig {}
|
|
186
|
+
|
|
187
|
+
impl BrowserConfig {
|
|
188
|
+
fn new(
|
|
189
|
+
mode: Option<BrowserMode>,
|
|
190
|
+
endpoint: Option<String>,
|
|
191
|
+
timeout: Option<u64>,
|
|
192
|
+
wait: Option<BrowserWait>,
|
|
193
|
+
wait_selector: Option<String>,
|
|
194
|
+
extra_wait: Option<u64>,
|
|
195
|
+
) -> Self {
|
|
196
|
+
Self {
|
|
197
|
+
mode: mode.unwrap_or(BrowserMode::Auto),
|
|
198
|
+
endpoint,
|
|
199
|
+
timeout: timeout.unwrap_or(30000),
|
|
200
|
+
wait: wait.unwrap_or_default(),
|
|
201
|
+
wait_selector,
|
|
202
|
+
extra_wait,
|
|
203
|
+
}
|
|
204
|
+
}
|
|
205
|
+
|
|
206
|
+
fn mode(&self) -> BrowserMode {
|
|
207
|
+
self.mode.clone()
|
|
208
|
+
}
|
|
209
|
+
|
|
210
|
+
fn endpoint(&self) -> Option<String> {
|
|
211
|
+
self.endpoint.clone()
|
|
212
|
+
}
|
|
213
|
+
|
|
214
|
+
fn timeout(&self) -> u64 {
|
|
215
|
+
self.timeout.clone()
|
|
216
|
+
}
|
|
217
|
+
|
|
218
|
+
fn wait(&self) -> BrowserWait {
|
|
219
|
+
self.wait.clone()
|
|
220
|
+
}
|
|
221
|
+
|
|
222
|
+
fn wait_selector(&self) -> Option<String> {
|
|
223
|
+
self.wait_selector.clone()
|
|
224
|
+
}
|
|
225
|
+
|
|
226
|
+
fn extra_wait(&self) -> Option<u64> {
|
|
227
|
+
self.extra_wait.clone()
|
|
228
|
+
}
|
|
229
|
+
}
|
|
230
|
+
|
|
231
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
|
232
|
+
#[magnus::wrap(class = "Kreuzcrawl::CrawlConfig")]
|
|
233
|
+
#[serde(default)]
|
|
234
|
+
pub struct CrawlConfig {
|
|
235
|
+
pub max_depth: Option<usize>,
|
|
236
|
+
pub max_pages: Option<usize>,
|
|
237
|
+
pub max_concurrent: Option<usize>,
|
|
238
|
+
pub respect_robots_txt: bool,
|
|
239
|
+
pub user_agent: Option<String>,
|
|
240
|
+
pub stay_on_domain: bool,
|
|
241
|
+
pub allow_subdomains: bool,
|
|
242
|
+
pub include_paths: Vec<String>,
|
|
243
|
+
pub exclude_paths: Vec<String>,
|
|
244
|
+
pub custom_headers: HashMap<String, String>,
|
|
245
|
+
pub request_timeout: u64,
|
|
246
|
+
pub max_redirects: usize,
|
|
247
|
+
pub retry_count: usize,
|
|
248
|
+
pub retry_codes: Vec<u16>,
|
|
249
|
+
pub cookies_enabled: bool,
|
|
250
|
+
pub auth: Option<AuthConfig>,
|
|
251
|
+
pub max_body_size: Option<usize>,
|
|
252
|
+
pub main_content_only: bool,
|
|
253
|
+
pub remove_tags: Vec<String>,
|
|
254
|
+
pub map_limit: Option<usize>,
|
|
255
|
+
pub map_search: Option<String>,
|
|
256
|
+
pub download_assets: bool,
|
|
257
|
+
pub asset_types: Vec<AssetCategory>,
|
|
258
|
+
pub max_asset_size: Option<usize>,
|
|
259
|
+
pub browser: BrowserConfig,
|
|
260
|
+
pub proxy: Option<ProxyConfig>,
|
|
261
|
+
pub user_agents: Vec<String>,
|
|
262
|
+
pub capture_screenshot: bool,
|
|
263
|
+
pub download_documents: bool,
|
|
264
|
+
pub document_max_size: Option<usize>,
|
|
265
|
+
pub document_mime_types: Vec<String>,
|
|
266
|
+
pub warc_output: Option<String>,
|
|
267
|
+
pub browser_profile: Option<String>,
|
|
268
|
+
pub save_browser_profile: bool,
|
|
269
|
+
}
|
|
270
|
+
|
|
271
|
+
unsafe impl IntoValueFromNative for CrawlConfig {}
|
|
272
|
+
|
|
273
|
+
impl magnus::TryConvert for CrawlConfig {
|
|
274
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
275
|
+
let r: &CrawlConfig = magnus::TryConvert::try_convert(val)?;
|
|
276
|
+
Ok(r.clone())
|
|
277
|
+
}
|
|
278
|
+
}
|
|
279
|
+
unsafe impl TryConvertOwned for CrawlConfig {}
|
|
280
|
+
|
|
281
|
+
impl CrawlConfig {
|
|
282
|
+
fn new(kwargs: magnus::RHash) -> Result<Self, magnus::Error> {
|
|
283
|
+
let ruby = unsafe { magnus::Ruby::get_unchecked() };
|
|
284
|
+
Ok(Self {
|
|
285
|
+
max_depth: kwargs
|
|
286
|
+
.get(ruby.to_symbol("max_depth"))
|
|
287
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
288
|
+
max_pages: kwargs
|
|
289
|
+
.get(ruby.to_symbol("max_pages"))
|
|
290
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
291
|
+
max_concurrent: kwargs
|
|
292
|
+
.get(ruby.to_symbol("max_concurrent"))
|
|
293
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
294
|
+
respect_robots_txt: kwargs
|
|
295
|
+
.get(ruby.to_symbol("respect_robots_txt"))
|
|
296
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
297
|
+
.unwrap_or(false),
|
|
298
|
+
user_agent: kwargs
|
|
299
|
+
.get(ruby.to_symbol("user_agent"))
|
|
300
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
301
|
+
stay_on_domain: kwargs
|
|
302
|
+
.get(ruby.to_symbol("stay_on_domain"))
|
|
303
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
304
|
+
.unwrap_or(false),
|
|
305
|
+
allow_subdomains: kwargs
|
|
306
|
+
.get(ruby.to_symbol("allow_subdomains"))
|
|
307
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
308
|
+
.unwrap_or(false),
|
|
309
|
+
include_paths: kwargs
|
|
310
|
+
.get(ruby.to_symbol("include_paths"))
|
|
311
|
+
.and_then(|v| <Vec<String>>::try_convert(v).ok())
|
|
312
|
+
.unwrap_or_default(),
|
|
313
|
+
exclude_paths: kwargs
|
|
314
|
+
.get(ruby.to_symbol("exclude_paths"))
|
|
315
|
+
.and_then(|v| <Vec<String>>::try_convert(v).ok())
|
|
316
|
+
.unwrap_or_default(),
|
|
317
|
+
custom_headers: kwargs
|
|
318
|
+
.get(ruby.to_symbol("custom_headers"))
|
|
319
|
+
.and_then(|v| <HashMap<String, String>>::try_convert(v).ok())
|
|
320
|
+
.unwrap_or_default(),
|
|
321
|
+
request_timeout: kwargs
|
|
322
|
+
.get(ruby.to_symbol("request_timeout"))
|
|
323
|
+
.and_then(|v| u64::try_convert(v).ok())
|
|
324
|
+
.unwrap_or(30000),
|
|
325
|
+
max_redirects: kwargs
|
|
326
|
+
.get(ruby.to_symbol("max_redirects"))
|
|
327
|
+
.and_then(|v| usize::try_convert(v).ok())
|
|
328
|
+
.unwrap_or(10),
|
|
329
|
+
retry_count: kwargs
|
|
330
|
+
.get(ruby.to_symbol("retry_count"))
|
|
331
|
+
.and_then(|v| usize::try_convert(v).ok())
|
|
332
|
+
.unwrap_or(0),
|
|
333
|
+
retry_codes: kwargs
|
|
334
|
+
.get(ruby.to_symbol("retry_codes"))
|
|
335
|
+
.and_then(|v| <Vec<u16>>::try_convert(v).ok())
|
|
336
|
+
.unwrap_or_default(),
|
|
337
|
+
cookies_enabled: kwargs
|
|
338
|
+
.get(ruby.to_symbol("cookies_enabled"))
|
|
339
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
340
|
+
.unwrap_or(false),
|
|
341
|
+
auth: kwargs
|
|
342
|
+
.get(ruby.to_symbol("auth"))
|
|
343
|
+
.and_then(|v| AuthConfig::try_convert(v).ok()),
|
|
344
|
+
max_body_size: kwargs
|
|
345
|
+
.get(ruby.to_symbol("max_body_size"))
|
|
346
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
347
|
+
main_content_only: kwargs
|
|
348
|
+
.get(ruby.to_symbol("main_content_only"))
|
|
349
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
350
|
+
.unwrap_or(false),
|
|
351
|
+
remove_tags: kwargs
|
|
352
|
+
.get(ruby.to_symbol("remove_tags"))
|
|
353
|
+
.and_then(|v| <Vec<String>>::try_convert(v).ok())
|
|
354
|
+
.unwrap_or_default(),
|
|
355
|
+
map_limit: kwargs
|
|
356
|
+
.get(ruby.to_symbol("map_limit"))
|
|
357
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
358
|
+
map_search: kwargs
|
|
359
|
+
.get(ruby.to_symbol("map_search"))
|
|
360
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
361
|
+
download_assets: kwargs
|
|
362
|
+
.get(ruby.to_symbol("download_assets"))
|
|
363
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
364
|
+
.unwrap_or(false),
|
|
365
|
+
asset_types: kwargs
|
|
366
|
+
.get(ruby.to_symbol("asset_types"))
|
|
367
|
+
.and_then(|v| <Vec<AssetCategory>>::try_convert(v).ok())
|
|
368
|
+
.unwrap_or_default(),
|
|
369
|
+
max_asset_size: kwargs
|
|
370
|
+
.get(ruby.to_symbol("max_asset_size"))
|
|
371
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
372
|
+
browser: kwargs
|
|
373
|
+
.get(ruby.to_symbol("browser"))
|
|
374
|
+
.and_then(|v| BrowserConfig::try_convert(v).ok())
|
|
375
|
+
.unwrap_or_default(),
|
|
376
|
+
proxy: kwargs
|
|
377
|
+
.get(ruby.to_symbol("proxy"))
|
|
378
|
+
.and_then(|v| ProxyConfig::try_convert(v).ok()),
|
|
379
|
+
user_agents: kwargs
|
|
380
|
+
.get(ruby.to_symbol("user_agents"))
|
|
381
|
+
.and_then(|v| <Vec<String>>::try_convert(v).ok())
|
|
382
|
+
.unwrap_or_default(),
|
|
383
|
+
capture_screenshot: kwargs
|
|
384
|
+
.get(ruby.to_symbol("capture_screenshot"))
|
|
385
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
386
|
+
.unwrap_or(false),
|
|
387
|
+
download_documents: kwargs
|
|
388
|
+
.get(ruby.to_symbol("download_documents"))
|
|
389
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
390
|
+
.unwrap_or(true),
|
|
391
|
+
document_max_size: kwargs
|
|
392
|
+
.get(ruby.to_symbol("document_max_size"))
|
|
393
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
394
|
+
document_mime_types: kwargs
|
|
395
|
+
.get(ruby.to_symbol("document_mime_types"))
|
|
396
|
+
.and_then(|v| <Vec<String>>::try_convert(v).ok())
|
|
397
|
+
.unwrap_or_default(),
|
|
398
|
+
warc_output: kwargs
|
|
399
|
+
.get(ruby.to_symbol("warc_output"))
|
|
400
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
401
|
+
browser_profile: kwargs
|
|
402
|
+
.get(ruby.to_symbol("browser_profile"))
|
|
403
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
404
|
+
save_browser_profile: kwargs
|
|
405
|
+
.get(ruby.to_symbol("save_browser_profile"))
|
|
406
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
407
|
+
.unwrap_or(false),
|
|
408
|
+
})
|
|
409
|
+
}
|
|
410
|
+
|
|
411
|
+
fn max_depth(&self) -> Option<usize> {
|
|
412
|
+
self.max_depth
|
|
413
|
+
}
|
|
414
|
+
|
|
415
|
+
fn max_pages(&self) -> Option<usize> {
|
|
416
|
+
self.max_pages
|
|
417
|
+
}
|
|
418
|
+
|
|
419
|
+
fn max_concurrent(&self) -> Option<usize> {
|
|
420
|
+
self.max_concurrent
|
|
421
|
+
}
|
|
422
|
+
|
|
423
|
+
fn respect_robots_txt(&self) -> bool {
|
|
424
|
+
self.respect_robots_txt
|
|
425
|
+
}
|
|
426
|
+
|
|
427
|
+
fn user_agent(&self) -> Option<String> {
|
|
428
|
+
self.user_agent.clone()
|
|
429
|
+
}
|
|
430
|
+
|
|
431
|
+
fn stay_on_domain(&self) -> bool {
|
|
432
|
+
self.stay_on_domain
|
|
433
|
+
}
|
|
434
|
+
|
|
435
|
+
fn allow_subdomains(&self) -> bool {
|
|
436
|
+
self.allow_subdomains
|
|
437
|
+
}
|
|
438
|
+
|
|
439
|
+
fn include_paths(&self) -> Vec<String> {
|
|
440
|
+
self.include_paths.clone()
|
|
441
|
+
}
|
|
442
|
+
|
|
443
|
+
fn exclude_paths(&self) -> Vec<String> {
|
|
444
|
+
self.exclude_paths.clone()
|
|
445
|
+
}
|
|
446
|
+
|
|
447
|
+
fn custom_headers(&self) -> HashMap<String, String> {
|
|
448
|
+
self.custom_headers.clone()
|
|
449
|
+
}
|
|
450
|
+
|
|
451
|
+
fn request_timeout(&self) -> u64 {
|
|
452
|
+
self.request_timeout.clone()
|
|
453
|
+
}
|
|
454
|
+
|
|
455
|
+
fn max_redirects(&self) -> usize {
|
|
456
|
+
self.max_redirects
|
|
457
|
+
}
|
|
458
|
+
|
|
459
|
+
fn retry_count(&self) -> usize {
|
|
460
|
+
self.retry_count
|
|
461
|
+
}
|
|
462
|
+
|
|
463
|
+
fn retry_codes(&self) -> Vec<u16> {
|
|
464
|
+
self.retry_codes.clone()
|
|
465
|
+
}
|
|
466
|
+
|
|
467
|
+
fn cookies_enabled(&self) -> bool {
|
|
468
|
+
self.cookies_enabled
|
|
469
|
+
}
|
|
470
|
+
|
|
471
|
+
fn auth(&self) -> Option<AuthConfig> {
|
|
472
|
+
self.auth.clone()
|
|
473
|
+
}
|
|
474
|
+
|
|
475
|
+
fn max_body_size(&self) -> Option<usize> {
|
|
476
|
+
self.max_body_size
|
|
477
|
+
}
|
|
478
|
+
|
|
479
|
+
fn main_content_only(&self) -> bool {
|
|
480
|
+
self.main_content_only
|
|
481
|
+
}
|
|
482
|
+
|
|
483
|
+
fn remove_tags(&self) -> Vec<String> {
|
|
484
|
+
self.remove_tags.clone()
|
|
485
|
+
}
|
|
486
|
+
|
|
487
|
+
fn map_limit(&self) -> Option<usize> {
|
|
488
|
+
self.map_limit
|
|
489
|
+
}
|
|
490
|
+
|
|
491
|
+
fn map_search(&self) -> Option<String> {
|
|
492
|
+
self.map_search.clone()
|
|
493
|
+
}
|
|
494
|
+
|
|
495
|
+
fn download_assets(&self) -> bool {
|
|
496
|
+
self.download_assets
|
|
497
|
+
}
|
|
498
|
+
|
|
499
|
+
fn asset_types(&self) -> Vec<AssetCategory> {
|
|
500
|
+
self.asset_types.clone()
|
|
501
|
+
}
|
|
502
|
+
|
|
503
|
+
fn max_asset_size(&self) -> Option<usize> {
|
|
504
|
+
self.max_asset_size
|
|
505
|
+
}
|
|
506
|
+
|
|
507
|
+
fn browser(&self) -> BrowserConfig {
|
|
508
|
+
self.browser.clone()
|
|
509
|
+
}
|
|
510
|
+
|
|
511
|
+
fn proxy(&self) -> Option<ProxyConfig> {
|
|
512
|
+
self.proxy.clone()
|
|
513
|
+
}
|
|
514
|
+
|
|
515
|
+
fn user_agents(&self) -> Vec<String> {
|
|
516
|
+
self.user_agents.clone()
|
|
517
|
+
}
|
|
518
|
+
|
|
519
|
+
fn capture_screenshot(&self) -> bool {
|
|
520
|
+
self.capture_screenshot
|
|
521
|
+
}
|
|
522
|
+
|
|
523
|
+
fn download_documents(&self) -> bool {
|
|
524
|
+
self.download_documents
|
|
525
|
+
}
|
|
526
|
+
|
|
527
|
+
fn document_max_size(&self) -> Option<usize> {
|
|
528
|
+
self.document_max_size
|
|
529
|
+
}
|
|
530
|
+
|
|
531
|
+
fn document_mime_types(&self) -> Vec<String> {
|
|
532
|
+
self.document_mime_types.clone()
|
|
533
|
+
}
|
|
534
|
+
|
|
535
|
+
fn warc_output(&self) -> Option<String> {
|
|
536
|
+
self.warc_output.clone()
|
|
537
|
+
}
|
|
538
|
+
|
|
539
|
+
fn browser_profile(&self) -> Option<String> {
|
|
540
|
+
self.browser_profile.clone()
|
|
541
|
+
}
|
|
542
|
+
|
|
543
|
+
fn save_browser_profile(&self) -> bool {
|
|
544
|
+
self.save_browser_profile
|
|
545
|
+
}
|
|
546
|
+
}
|
|
547
|
+
|
|
548
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
549
|
+
#[magnus::wrap(class = "Kreuzcrawl::DownloadedDocument")]
|
|
550
|
+
#[serde(default)]
|
|
551
|
+
pub struct DownloadedDocument {
|
|
552
|
+
pub url: String,
|
|
553
|
+
pub mime_type: String,
|
|
554
|
+
pub content: Vec<u8>,
|
|
555
|
+
pub size: usize,
|
|
556
|
+
pub filename: Option<String>,
|
|
557
|
+
pub content_hash: String,
|
|
558
|
+
pub headers: HashMap<String, String>,
|
|
559
|
+
}
|
|
560
|
+
|
|
561
|
+
unsafe impl IntoValueFromNative for DownloadedDocument {}
|
|
562
|
+
|
|
563
|
+
impl magnus::TryConvert for DownloadedDocument {
|
|
564
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
565
|
+
let r: &DownloadedDocument = magnus::TryConvert::try_convert(val)?;
|
|
566
|
+
Ok(r.clone())
|
|
567
|
+
}
|
|
568
|
+
}
|
|
569
|
+
unsafe impl TryConvertOwned for DownloadedDocument {}
|
|
570
|
+
|
|
571
|
+
impl Default for DownloadedDocument {
|
|
572
|
+
fn default() -> Self {
|
|
573
|
+
Self {
|
|
574
|
+
url: Default::default(),
|
|
575
|
+
mime_type: Default::default(),
|
|
576
|
+
content: Default::default(),
|
|
577
|
+
size: Default::default(),
|
|
578
|
+
filename: Default::default(),
|
|
579
|
+
content_hash: Default::default(),
|
|
580
|
+
headers: Default::default(),
|
|
581
|
+
}
|
|
582
|
+
}
|
|
583
|
+
}
|
|
584
|
+
|
|
585
|
+
impl DownloadedDocument {
|
|
586
|
+
fn new(
|
|
587
|
+
url: Option<String>,
|
|
588
|
+
mime_type: Option<String>,
|
|
589
|
+
content: Option<Vec<u8>>,
|
|
590
|
+
size: Option<usize>,
|
|
591
|
+
filename: Option<String>,
|
|
592
|
+
content_hash: Option<String>,
|
|
593
|
+
headers: Option<HashMap<String, String>>,
|
|
594
|
+
) -> Self {
|
|
595
|
+
Self {
|
|
596
|
+
url: url.unwrap_or_default(),
|
|
597
|
+
mime_type: mime_type.unwrap_or_default(),
|
|
598
|
+
content: content.unwrap_or_default(),
|
|
599
|
+
size: size.unwrap_or_default(),
|
|
600
|
+
filename,
|
|
601
|
+
content_hash: content_hash.unwrap_or_default(),
|
|
602
|
+
headers: headers.unwrap_or_default(),
|
|
603
|
+
}
|
|
604
|
+
}
|
|
605
|
+
|
|
606
|
+
fn url(&self) -> String {
|
|
607
|
+
self.url.clone()
|
|
608
|
+
}
|
|
609
|
+
|
|
610
|
+
fn mime_type(&self) -> String {
|
|
611
|
+
self.mime_type.clone()
|
|
612
|
+
}
|
|
613
|
+
|
|
614
|
+
fn content(&self) -> Vec<u8> {
|
|
615
|
+
self.content.clone()
|
|
616
|
+
}
|
|
617
|
+
|
|
618
|
+
fn size(&self) -> usize {
|
|
619
|
+
self.size
|
|
620
|
+
}
|
|
621
|
+
|
|
622
|
+
fn filename(&self) -> Option<String> {
|
|
623
|
+
self.filename.clone()
|
|
624
|
+
}
|
|
625
|
+
|
|
626
|
+
fn content_hash(&self) -> String {
|
|
627
|
+
self.content_hash.clone()
|
|
628
|
+
}
|
|
629
|
+
|
|
630
|
+
fn headers(&self) -> HashMap<String, String> {
|
|
631
|
+
self.headers.clone()
|
|
632
|
+
}
|
|
633
|
+
}
|
|
634
|
+
|
|
635
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
636
|
+
#[magnus::wrap(class = "Kreuzcrawl::InteractionResult")]
|
|
637
|
+
#[serde(default)]
|
|
638
|
+
pub struct InteractionResult {
|
|
639
|
+
pub action_results: Vec<ActionResult>,
|
|
640
|
+
pub final_html: String,
|
|
641
|
+
pub final_url: String,
|
|
642
|
+
pub screenshot: Option<Vec<u8>>,
|
|
643
|
+
}
|
|
644
|
+
|
|
645
|
+
unsafe impl IntoValueFromNative for InteractionResult {}
|
|
646
|
+
|
|
647
|
+
impl magnus::TryConvert for InteractionResult {
|
|
648
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
649
|
+
let r: &InteractionResult = magnus::TryConvert::try_convert(val)?;
|
|
650
|
+
Ok(r.clone())
|
|
651
|
+
}
|
|
652
|
+
}
|
|
653
|
+
unsafe impl TryConvertOwned for InteractionResult {}
|
|
654
|
+
|
|
655
|
+
impl Default for InteractionResult {
|
|
656
|
+
fn default() -> Self {
|
|
657
|
+
Self {
|
|
658
|
+
action_results: Default::default(),
|
|
659
|
+
final_html: Default::default(),
|
|
660
|
+
final_url: Default::default(),
|
|
661
|
+
screenshot: Default::default(),
|
|
662
|
+
}
|
|
663
|
+
}
|
|
664
|
+
}
|
|
665
|
+
|
|
666
|
+
impl InteractionResult {
|
|
667
|
+
fn new(
|
|
668
|
+
action_results: Option<Vec<ActionResult>>,
|
|
669
|
+
final_html: Option<String>,
|
|
670
|
+
final_url: Option<String>,
|
|
671
|
+
screenshot: Option<Vec<u8>>,
|
|
672
|
+
) -> Self {
|
|
673
|
+
Self {
|
|
674
|
+
action_results: action_results.unwrap_or_default(),
|
|
675
|
+
final_html: final_html.unwrap_or_default(),
|
|
676
|
+
final_url: final_url.unwrap_or_default(),
|
|
677
|
+
screenshot,
|
|
678
|
+
}
|
|
679
|
+
}
|
|
680
|
+
|
|
681
|
+
fn action_results(&self) -> Vec<ActionResult> {
|
|
682
|
+
self.action_results.clone()
|
|
683
|
+
}
|
|
684
|
+
|
|
685
|
+
fn final_html(&self) -> String {
|
|
686
|
+
self.final_html.clone()
|
|
687
|
+
}
|
|
688
|
+
|
|
689
|
+
fn final_url(&self) -> String {
|
|
690
|
+
self.final_url.clone()
|
|
691
|
+
}
|
|
692
|
+
|
|
693
|
+
fn screenshot(&self) -> Option<Vec<u8>> {
|
|
694
|
+
self.screenshot.clone()
|
|
695
|
+
}
|
|
696
|
+
}
|
|
697
|
+
|
|
698
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
699
|
+
#[magnus::wrap(class = "Kreuzcrawl::ActionResult")]
|
|
700
|
+
#[serde(default)]
|
|
701
|
+
pub struct ActionResult {
|
|
702
|
+
pub action_index: usize,
|
|
703
|
+
pub action_type: String,
|
|
704
|
+
pub success: bool,
|
|
705
|
+
pub data: Option<String>,
|
|
706
|
+
pub error: Option<String>,
|
|
707
|
+
}
|
|
708
|
+
|
|
709
|
+
unsafe impl IntoValueFromNative for ActionResult {}
|
|
710
|
+
|
|
711
|
+
impl magnus::TryConvert for ActionResult {
|
|
712
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
713
|
+
let r: &ActionResult = magnus::TryConvert::try_convert(val)?;
|
|
714
|
+
Ok(r.clone())
|
|
715
|
+
}
|
|
716
|
+
}
|
|
717
|
+
unsafe impl TryConvertOwned for ActionResult {}
|
|
718
|
+
|
|
719
|
+
impl Default for ActionResult {
|
|
720
|
+
fn default() -> Self {
|
|
721
|
+
Self {
|
|
722
|
+
action_index: Default::default(),
|
|
723
|
+
action_type: Default::default(),
|
|
724
|
+
success: Default::default(),
|
|
725
|
+
data: Default::default(),
|
|
726
|
+
error: Default::default(),
|
|
727
|
+
}
|
|
728
|
+
}
|
|
729
|
+
}
|
|
730
|
+
|
|
731
|
+
impl ActionResult {
|
|
732
|
+
fn new(
|
|
733
|
+
action_index: Option<usize>,
|
|
734
|
+
action_type: Option<String>,
|
|
735
|
+
success: Option<bool>,
|
|
736
|
+
data: Option<String>,
|
|
737
|
+
error: Option<String>,
|
|
738
|
+
) -> Self {
|
|
739
|
+
Self {
|
|
740
|
+
action_index: action_index.unwrap_or_default(),
|
|
741
|
+
action_type: action_type.unwrap_or_default(),
|
|
742
|
+
success: success.unwrap_or_default(),
|
|
743
|
+
data,
|
|
744
|
+
error,
|
|
745
|
+
}
|
|
746
|
+
}
|
|
747
|
+
|
|
748
|
+
fn action_index(&self) -> usize {
|
|
749
|
+
self.action_index
|
|
750
|
+
}
|
|
751
|
+
|
|
752
|
+
fn action_type(&self) -> String {
|
|
753
|
+
self.action_type.clone()
|
|
754
|
+
}
|
|
755
|
+
|
|
756
|
+
fn success(&self) -> bool {
|
|
757
|
+
self.success
|
|
758
|
+
}
|
|
759
|
+
|
|
760
|
+
fn data(&self) -> Option<String> {
|
|
761
|
+
self.data.clone()
|
|
762
|
+
}
|
|
763
|
+
|
|
764
|
+
fn error(&self) -> Option<String> {
|
|
765
|
+
self.error.clone()
|
|
766
|
+
}
|
|
767
|
+
}
|
|
768
|
+
|
|
769
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
770
|
+
#[magnus::wrap(class = "Kreuzcrawl::ScrapeResult")]
|
|
771
|
+
#[serde(default)]
|
|
772
|
+
pub struct ScrapeResult {
|
|
773
|
+
pub status_code: u16,
|
|
774
|
+
pub content_type: String,
|
|
775
|
+
pub html: String,
|
|
776
|
+
pub body_size: usize,
|
|
777
|
+
pub metadata: PageMetadata,
|
|
778
|
+
pub links: Vec<LinkInfo>,
|
|
779
|
+
pub images: Vec<ImageInfo>,
|
|
780
|
+
pub feeds: Vec<FeedInfo>,
|
|
781
|
+
pub json_ld: Vec<JsonLdEntry>,
|
|
782
|
+
pub is_allowed: bool,
|
|
783
|
+
pub crawl_delay: Option<u64>,
|
|
784
|
+
pub noindex_detected: bool,
|
|
785
|
+
pub nofollow_detected: bool,
|
|
786
|
+
pub x_robots_tag: Option<String>,
|
|
787
|
+
pub is_pdf: bool,
|
|
788
|
+
pub was_skipped: bool,
|
|
789
|
+
pub detected_charset: Option<String>,
|
|
790
|
+
pub main_content_only: bool,
|
|
791
|
+
pub auth_header_sent: bool,
|
|
792
|
+
pub response_meta: Option<ResponseMeta>,
|
|
793
|
+
pub assets: Vec<DownloadedAsset>,
|
|
794
|
+
pub js_render_hint: bool,
|
|
795
|
+
pub browser_used: bool,
|
|
796
|
+
pub markdown: Option<MarkdownResult>,
|
|
797
|
+
pub extracted_data: Option<String>,
|
|
798
|
+
pub extraction_meta: Option<ExtractionMeta>,
|
|
799
|
+
pub screenshot: Option<Vec<u8>>,
|
|
800
|
+
pub downloaded_document: Option<DownloadedDocument>,
|
|
801
|
+
}
|
|
802
|
+
|
|
803
|
+
unsafe impl IntoValueFromNative for ScrapeResult {}
|
|
804
|
+
|
|
805
|
+
impl magnus::TryConvert for ScrapeResult {
|
|
806
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
807
|
+
let r: &ScrapeResult = magnus::TryConvert::try_convert(val)?;
|
|
808
|
+
Ok(r.clone())
|
|
809
|
+
}
|
|
810
|
+
}
|
|
811
|
+
unsafe impl TryConvertOwned for ScrapeResult {}
|
|
812
|
+
|
|
813
|
+
impl Default for ScrapeResult {
|
|
814
|
+
fn default() -> Self {
|
|
815
|
+
Self {
|
|
816
|
+
status_code: Default::default(),
|
|
817
|
+
content_type: Default::default(),
|
|
818
|
+
html: Default::default(),
|
|
819
|
+
body_size: Default::default(),
|
|
820
|
+
metadata: Default::default(),
|
|
821
|
+
links: Default::default(),
|
|
822
|
+
images: Default::default(),
|
|
823
|
+
feeds: Default::default(),
|
|
824
|
+
json_ld: Default::default(),
|
|
825
|
+
is_allowed: Default::default(),
|
|
826
|
+
crawl_delay: Default::default(),
|
|
827
|
+
noindex_detected: Default::default(),
|
|
828
|
+
nofollow_detected: Default::default(),
|
|
829
|
+
x_robots_tag: Default::default(),
|
|
830
|
+
is_pdf: Default::default(),
|
|
831
|
+
was_skipped: Default::default(),
|
|
832
|
+
detected_charset: Default::default(),
|
|
833
|
+
main_content_only: Default::default(),
|
|
834
|
+
auth_header_sent: Default::default(),
|
|
835
|
+
response_meta: Default::default(),
|
|
836
|
+
assets: Default::default(),
|
|
837
|
+
js_render_hint: Default::default(),
|
|
838
|
+
browser_used: Default::default(),
|
|
839
|
+
markdown: Default::default(),
|
|
840
|
+
extracted_data: Default::default(),
|
|
841
|
+
extraction_meta: Default::default(),
|
|
842
|
+
screenshot: Default::default(),
|
|
843
|
+
downloaded_document: Default::default(),
|
|
844
|
+
}
|
|
845
|
+
}
|
|
846
|
+
}
|
|
847
|
+
|
|
848
|
+
impl ScrapeResult {
|
|
849
|
+
fn new(kwargs: magnus::RHash) -> Result<Self, magnus::Error> {
|
|
850
|
+
let ruby = unsafe { magnus::Ruby::get_unchecked() };
|
|
851
|
+
Ok(Self {
|
|
852
|
+
status_code: kwargs
|
|
853
|
+
.get(ruby.to_symbol("status_code"))
|
|
854
|
+
.and_then(|v| u16::try_convert(v).ok())
|
|
855
|
+
.unwrap_or_default(),
|
|
856
|
+
content_type: kwargs
|
|
857
|
+
.get(ruby.to_symbol("content_type"))
|
|
858
|
+
.and_then(|v| String::try_convert(v).ok())
|
|
859
|
+
.unwrap_or_default(),
|
|
860
|
+
html: kwargs
|
|
861
|
+
.get(ruby.to_symbol("html"))
|
|
862
|
+
.and_then(|v| String::try_convert(v).ok())
|
|
863
|
+
.unwrap_or_default(),
|
|
864
|
+
body_size: kwargs
|
|
865
|
+
.get(ruby.to_symbol("body_size"))
|
|
866
|
+
.and_then(|v| usize::try_convert(v).ok())
|
|
867
|
+
.unwrap_or_default(),
|
|
868
|
+
metadata: kwargs
|
|
869
|
+
.get(ruby.to_symbol("metadata"))
|
|
870
|
+
.and_then(|v| PageMetadata::try_convert(v).ok())
|
|
871
|
+
.unwrap_or_default(),
|
|
872
|
+
links: kwargs
|
|
873
|
+
.get(ruby.to_symbol("links"))
|
|
874
|
+
.and_then(|v| <Vec<LinkInfo>>::try_convert(v).ok())
|
|
875
|
+
.unwrap_or_default(),
|
|
876
|
+
images: kwargs
|
|
877
|
+
.get(ruby.to_symbol("images"))
|
|
878
|
+
.and_then(|v| <Vec<ImageInfo>>::try_convert(v).ok())
|
|
879
|
+
.unwrap_or_default(),
|
|
880
|
+
feeds: kwargs
|
|
881
|
+
.get(ruby.to_symbol("feeds"))
|
|
882
|
+
.and_then(|v| <Vec<FeedInfo>>::try_convert(v).ok())
|
|
883
|
+
.unwrap_or_default(),
|
|
884
|
+
json_ld: kwargs
|
|
885
|
+
.get(ruby.to_symbol("json_ld"))
|
|
886
|
+
.and_then(|v| <Vec<JsonLdEntry>>::try_convert(v).ok())
|
|
887
|
+
.unwrap_or_default(),
|
|
888
|
+
is_allowed: kwargs
|
|
889
|
+
.get(ruby.to_symbol("is_allowed"))
|
|
890
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
891
|
+
.unwrap_or_default(),
|
|
892
|
+
crawl_delay: kwargs
|
|
893
|
+
.get(ruby.to_symbol("crawl_delay"))
|
|
894
|
+
.and_then(|v| u64::try_convert(v).ok()),
|
|
895
|
+
noindex_detected: kwargs
|
|
896
|
+
.get(ruby.to_symbol("noindex_detected"))
|
|
897
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
898
|
+
.unwrap_or_default(),
|
|
899
|
+
nofollow_detected: kwargs
|
|
900
|
+
.get(ruby.to_symbol("nofollow_detected"))
|
|
901
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
902
|
+
.unwrap_or_default(),
|
|
903
|
+
x_robots_tag: kwargs
|
|
904
|
+
.get(ruby.to_symbol("x_robots_tag"))
|
|
905
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
906
|
+
is_pdf: kwargs
|
|
907
|
+
.get(ruby.to_symbol("is_pdf"))
|
|
908
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
909
|
+
.unwrap_or_default(),
|
|
910
|
+
was_skipped: kwargs
|
|
911
|
+
.get(ruby.to_symbol("was_skipped"))
|
|
912
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
913
|
+
.unwrap_or_default(),
|
|
914
|
+
detected_charset: kwargs
|
|
915
|
+
.get(ruby.to_symbol("detected_charset"))
|
|
916
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
917
|
+
main_content_only: kwargs
|
|
918
|
+
.get(ruby.to_symbol("main_content_only"))
|
|
919
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
920
|
+
.unwrap_or_default(),
|
|
921
|
+
auth_header_sent: kwargs
|
|
922
|
+
.get(ruby.to_symbol("auth_header_sent"))
|
|
923
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
924
|
+
.unwrap_or_default(),
|
|
925
|
+
response_meta: kwargs
|
|
926
|
+
.get(ruby.to_symbol("response_meta"))
|
|
927
|
+
.and_then(|v| ResponseMeta::try_convert(v).ok()),
|
|
928
|
+
assets: kwargs
|
|
929
|
+
.get(ruby.to_symbol("assets"))
|
|
930
|
+
.and_then(|v| <Vec<DownloadedAsset>>::try_convert(v).ok())
|
|
931
|
+
.unwrap_or_default(),
|
|
932
|
+
js_render_hint: kwargs
|
|
933
|
+
.get(ruby.to_symbol("js_render_hint"))
|
|
934
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
935
|
+
.unwrap_or_default(),
|
|
936
|
+
browser_used: kwargs
|
|
937
|
+
.get(ruby.to_symbol("browser_used"))
|
|
938
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
939
|
+
.unwrap_or_default(),
|
|
940
|
+
markdown: kwargs
|
|
941
|
+
.get(ruby.to_symbol("markdown"))
|
|
942
|
+
.and_then(|v| MarkdownResult::try_convert(v).ok()),
|
|
943
|
+
extracted_data: kwargs
|
|
944
|
+
.get(ruby.to_symbol("extracted_data"))
|
|
945
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
946
|
+
extraction_meta: kwargs
|
|
947
|
+
.get(ruby.to_symbol("extraction_meta"))
|
|
948
|
+
.and_then(|v| ExtractionMeta::try_convert(v).ok()),
|
|
949
|
+
screenshot: kwargs
|
|
950
|
+
.get(ruby.to_symbol("screenshot"))
|
|
951
|
+
.and_then(|v| <Vec<u8>>::try_convert(v).ok()),
|
|
952
|
+
downloaded_document: kwargs
|
|
953
|
+
.get(ruby.to_symbol("downloaded_document"))
|
|
954
|
+
.and_then(|v| DownloadedDocument::try_convert(v).ok()),
|
|
955
|
+
})
|
|
956
|
+
}
|
|
957
|
+
|
|
958
|
+
fn status_code(&self) -> u16 {
|
|
959
|
+
self.status_code
|
|
960
|
+
}
|
|
961
|
+
|
|
962
|
+
fn content_type(&self) -> String {
|
|
963
|
+
self.content_type.clone()
|
|
964
|
+
}
|
|
965
|
+
|
|
966
|
+
fn html(&self) -> String {
|
|
967
|
+
self.html.clone()
|
|
968
|
+
}
|
|
969
|
+
|
|
970
|
+
fn body_size(&self) -> usize {
|
|
971
|
+
self.body_size
|
|
972
|
+
}
|
|
973
|
+
|
|
974
|
+
fn metadata(&self) -> PageMetadata {
|
|
975
|
+
self.metadata.clone()
|
|
976
|
+
}
|
|
977
|
+
|
|
978
|
+
fn links(&self) -> Vec<LinkInfo> {
|
|
979
|
+
self.links.clone()
|
|
980
|
+
}
|
|
981
|
+
|
|
982
|
+
fn images(&self) -> Vec<ImageInfo> {
|
|
983
|
+
self.images.clone()
|
|
984
|
+
}
|
|
985
|
+
|
|
986
|
+
fn feeds(&self) -> Vec<FeedInfo> {
|
|
987
|
+
self.feeds.clone()
|
|
988
|
+
}
|
|
989
|
+
|
|
990
|
+
fn json_ld(&self) -> Vec<JsonLdEntry> {
|
|
991
|
+
self.json_ld.clone()
|
|
992
|
+
}
|
|
993
|
+
|
|
994
|
+
fn is_allowed(&self) -> bool {
|
|
995
|
+
self.is_allowed
|
|
996
|
+
}
|
|
997
|
+
|
|
998
|
+
fn crawl_delay(&self) -> Option<u64> {
|
|
999
|
+
self.crawl_delay
|
|
1000
|
+
}
|
|
1001
|
+
|
|
1002
|
+
fn noindex_detected(&self) -> bool {
|
|
1003
|
+
self.noindex_detected
|
|
1004
|
+
}
|
|
1005
|
+
|
|
1006
|
+
fn nofollow_detected(&self) -> bool {
|
|
1007
|
+
self.nofollow_detected
|
|
1008
|
+
}
|
|
1009
|
+
|
|
1010
|
+
fn x_robots_tag(&self) -> Option<String> {
|
|
1011
|
+
self.x_robots_tag.clone()
|
|
1012
|
+
}
|
|
1013
|
+
|
|
1014
|
+
fn is_pdf(&self) -> bool {
|
|
1015
|
+
self.is_pdf
|
|
1016
|
+
}
|
|
1017
|
+
|
|
1018
|
+
fn was_skipped(&self) -> bool {
|
|
1019
|
+
self.was_skipped
|
|
1020
|
+
}
|
|
1021
|
+
|
|
1022
|
+
fn detected_charset(&self) -> Option<String> {
|
|
1023
|
+
self.detected_charset.clone()
|
|
1024
|
+
}
|
|
1025
|
+
|
|
1026
|
+
fn main_content_only(&self) -> bool {
|
|
1027
|
+
self.main_content_only
|
|
1028
|
+
}
|
|
1029
|
+
|
|
1030
|
+
fn auth_header_sent(&self) -> bool {
|
|
1031
|
+
self.auth_header_sent
|
|
1032
|
+
}
|
|
1033
|
+
|
|
1034
|
+
fn response_meta(&self) -> Option<ResponseMeta> {
|
|
1035
|
+
self.response_meta.clone()
|
|
1036
|
+
}
|
|
1037
|
+
|
|
1038
|
+
fn assets(&self) -> Vec<DownloadedAsset> {
|
|
1039
|
+
self.assets.clone()
|
|
1040
|
+
}
|
|
1041
|
+
|
|
1042
|
+
fn js_render_hint(&self) -> bool {
|
|
1043
|
+
self.js_render_hint
|
|
1044
|
+
}
|
|
1045
|
+
|
|
1046
|
+
fn browser_used(&self) -> bool {
|
|
1047
|
+
self.browser_used
|
|
1048
|
+
}
|
|
1049
|
+
|
|
1050
|
+
fn markdown(&self) -> Option<MarkdownResult> {
|
|
1051
|
+
self.markdown.clone()
|
|
1052
|
+
}
|
|
1053
|
+
|
|
1054
|
+
fn extracted_data(&self) -> Option<String> {
|
|
1055
|
+
self.extracted_data.clone()
|
|
1056
|
+
}
|
|
1057
|
+
|
|
1058
|
+
fn extraction_meta(&self) -> Option<ExtractionMeta> {
|
|
1059
|
+
self.extraction_meta.clone()
|
|
1060
|
+
}
|
|
1061
|
+
|
|
1062
|
+
fn screenshot(&self) -> Option<Vec<u8>> {
|
|
1063
|
+
self.screenshot.clone()
|
|
1064
|
+
}
|
|
1065
|
+
|
|
1066
|
+
fn downloaded_document(&self) -> Option<DownloadedDocument> {
|
|
1067
|
+
self.downloaded_document.clone()
|
|
1068
|
+
}
|
|
1069
|
+
}
|
|
1070
|
+
|
|
1071
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1072
|
+
#[magnus::wrap(class = "Kreuzcrawl::CrawlPageResult")]
|
|
1073
|
+
#[serde(default)]
|
|
1074
|
+
pub struct CrawlPageResult {
|
|
1075
|
+
pub url: String,
|
|
1076
|
+
pub normalized_url: String,
|
|
1077
|
+
pub status_code: u16,
|
|
1078
|
+
pub content_type: String,
|
|
1079
|
+
pub html: String,
|
|
1080
|
+
pub body_size: usize,
|
|
1081
|
+
pub metadata: PageMetadata,
|
|
1082
|
+
pub links: Vec<LinkInfo>,
|
|
1083
|
+
pub images: Vec<ImageInfo>,
|
|
1084
|
+
pub feeds: Vec<FeedInfo>,
|
|
1085
|
+
pub json_ld: Vec<JsonLdEntry>,
|
|
1086
|
+
pub depth: usize,
|
|
1087
|
+
pub stayed_on_domain: bool,
|
|
1088
|
+
pub was_skipped: bool,
|
|
1089
|
+
pub is_pdf: bool,
|
|
1090
|
+
pub detected_charset: Option<String>,
|
|
1091
|
+
pub markdown: Option<MarkdownResult>,
|
|
1092
|
+
pub extracted_data: Option<String>,
|
|
1093
|
+
pub extraction_meta: Option<ExtractionMeta>,
|
|
1094
|
+
pub downloaded_document: Option<DownloadedDocument>,
|
|
1095
|
+
}
|
|
1096
|
+
|
|
1097
|
+
unsafe impl IntoValueFromNative for CrawlPageResult {}
|
|
1098
|
+
|
|
1099
|
+
impl magnus::TryConvert for CrawlPageResult {
|
|
1100
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1101
|
+
let r: &CrawlPageResult = magnus::TryConvert::try_convert(val)?;
|
|
1102
|
+
Ok(r.clone())
|
|
1103
|
+
}
|
|
1104
|
+
}
|
|
1105
|
+
unsafe impl TryConvertOwned for CrawlPageResult {}
|
|
1106
|
+
|
|
1107
|
+
impl Default for CrawlPageResult {
|
|
1108
|
+
fn default() -> Self {
|
|
1109
|
+
Self {
|
|
1110
|
+
url: Default::default(),
|
|
1111
|
+
normalized_url: Default::default(),
|
|
1112
|
+
status_code: Default::default(),
|
|
1113
|
+
content_type: Default::default(),
|
|
1114
|
+
html: Default::default(),
|
|
1115
|
+
body_size: Default::default(),
|
|
1116
|
+
metadata: Default::default(),
|
|
1117
|
+
links: Default::default(),
|
|
1118
|
+
images: Default::default(),
|
|
1119
|
+
feeds: Default::default(),
|
|
1120
|
+
json_ld: Default::default(),
|
|
1121
|
+
depth: Default::default(),
|
|
1122
|
+
stayed_on_domain: Default::default(),
|
|
1123
|
+
was_skipped: Default::default(),
|
|
1124
|
+
is_pdf: Default::default(),
|
|
1125
|
+
detected_charset: Default::default(),
|
|
1126
|
+
markdown: Default::default(),
|
|
1127
|
+
extracted_data: Default::default(),
|
|
1128
|
+
extraction_meta: Default::default(),
|
|
1129
|
+
downloaded_document: Default::default(),
|
|
1130
|
+
}
|
|
1131
|
+
}
|
|
1132
|
+
}
|
|
1133
|
+
|
|
1134
|
+
impl CrawlPageResult {
|
|
1135
|
+
fn new(kwargs: magnus::RHash) -> Result<Self, magnus::Error> {
|
|
1136
|
+
let ruby = unsafe { magnus::Ruby::get_unchecked() };
|
|
1137
|
+
Ok(Self {
|
|
1138
|
+
url: kwargs
|
|
1139
|
+
.get(ruby.to_symbol("url"))
|
|
1140
|
+
.and_then(|v| String::try_convert(v).ok())
|
|
1141
|
+
.unwrap_or_default(),
|
|
1142
|
+
normalized_url: kwargs
|
|
1143
|
+
.get(ruby.to_symbol("normalized_url"))
|
|
1144
|
+
.and_then(|v| String::try_convert(v).ok())
|
|
1145
|
+
.unwrap_or_default(),
|
|
1146
|
+
status_code: kwargs
|
|
1147
|
+
.get(ruby.to_symbol("status_code"))
|
|
1148
|
+
.and_then(|v| u16::try_convert(v).ok())
|
|
1149
|
+
.unwrap_or_default(),
|
|
1150
|
+
content_type: kwargs
|
|
1151
|
+
.get(ruby.to_symbol("content_type"))
|
|
1152
|
+
.and_then(|v| String::try_convert(v).ok())
|
|
1153
|
+
.unwrap_or_default(),
|
|
1154
|
+
html: kwargs
|
|
1155
|
+
.get(ruby.to_symbol("html"))
|
|
1156
|
+
.and_then(|v| String::try_convert(v).ok())
|
|
1157
|
+
.unwrap_or_default(),
|
|
1158
|
+
body_size: kwargs
|
|
1159
|
+
.get(ruby.to_symbol("body_size"))
|
|
1160
|
+
.and_then(|v| usize::try_convert(v).ok())
|
|
1161
|
+
.unwrap_or_default(),
|
|
1162
|
+
metadata: kwargs
|
|
1163
|
+
.get(ruby.to_symbol("metadata"))
|
|
1164
|
+
.and_then(|v| PageMetadata::try_convert(v).ok())
|
|
1165
|
+
.unwrap_or_default(),
|
|
1166
|
+
links: kwargs
|
|
1167
|
+
.get(ruby.to_symbol("links"))
|
|
1168
|
+
.and_then(|v| <Vec<LinkInfo>>::try_convert(v).ok())
|
|
1169
|
+
.unwrap_or_default(),
|
|
1170
|
+
images: kwargs
|
|
1171
|
+
.get(ruby.to_symbol("images"))
|
|
1172
|
+
.and_then(|v| <Vec<ImageInfo>>::try_convert(v).ok())
|
|
1173
|
+
.unwrap_or_default(),
|
|
1174
|
+
feeds: kwargs
|
|
1175
|
+
.get(ruby.to_symbol("feeds"))
|
|
1176
|
+
.and_then(|v| <Vec<FeedInfo>>::try_convert(v).ok())
|
|
1177
|
+
.unwrap_or_default(),
|
|
1178
|
+
json_ld: kwargs
|
|
1179
|
+
.get(ruby.to_symbol("json_ld"))
|
|
1180
|
+
.and_then(|v| <Vec<JsonLdEntry>>::try_convert(v).ok())
|
|
1181
|
+
.unwrap_or_default(),
|
|
1182
|
+
depth: kwargs
|
|
1183
|
+
.get(ruby.to_symbol("depth"))
|
|
1184
|
+
.and_then(|v| usize::try_convert(v).ok())
|
|
1185
|
+
.unwrap_or_default(),
|
|
1186
|
+
stayed_on_domain: kwargs
|
|
1187
|
+
.get(ruby.to_symbol("stayed_on_domain"))
|
|
1188
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
1189
|
+
.unwrap_or_default(),
|
|
1190
|
+
was_skipped: kwargs
|
|
1191
|
+
.get(ruby.to_symbol("was_skipped"))
|
|
1192
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
1193
|
+
.unwrap_or_default(),
|
|
1194
|
+
is_pdf: kwargs
|
|
1195
|
+
.get(ruby.to_symbol("is_pdf"))
|
|
1196
|
+
.and_then(|v| bool::try_convert(v).ok())
|
|
1197
|
+
.unwrap_or_default(),
|
|
1198
|
+
detected_charset: kwargs
|
|
1199
|
+
.get(ruby.to_symbol("detected_charset"))
|
|
1200
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
1201
|
+
markdown: kwargs
|
|
1202
|
+
.get(ruby.to_symbol("markdown"))
|
|
1203
|
+
.and_then(|v| MarkdownResult::try_convert(v).ok()),
|
|
1204
|
+
extracted_data: kwargs
|
|
1205
|
+
.get(ruby.to_symbol("extracted_data"))
|
|
1206
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
1207
|
+
extraction_meta: kwargs
|
|
1208
|
+
.get(ruby.to_symbol("extraction_meta"))
|
|
1209
|
+
.and_then(|v| ExtractionMeta::try_convert(v).ok()),
|
|
1210
|
+
downloaded_document: kwargs
|
|
1211
|
+
.get(ruby.to_symbol("downloaded_document"))
|
|
1212
|
+
.and_then(|v| DownloadedDocument::try_convert(v).ok()),
|
|
1213
|
+
})
|
|
1214
|
+
}
|
|
1215
|
+
|
|
1216
|
+
fn url(&self) -> String {
|
|
1217
|
+
self.url.clone()
|
|
1218
|
+
}
|
|
1219
|
+
|
|
1220
|
+
fn normalized_url(&self) -> String {
|
|
1221
|
+
self.normalized_url.clone()
|
|
1222
|
+
}
|
|
1223
|
+
|
|
1224
|
+
fn status_code(&self) -> u16 {
|
|
1225
|
+
self.status_code
|
|
1226
|
+
}
|
|
1227
|
+
|
|
1228
|
+
fn content_type(&self) -> String {
|
|
1229
|
+
self.content_type.clone()
|
|
1230
|
+
}
|
|
1231
|
+
|
|
1232
|
+
fn html(&self) -> String {
|
|
1233
|
+
self.html.clone()
|
|
1234
|
+
}
|
|
1235
|
+
|
|
1236
|
+
fn body_size(&self) -> usize {
|
|
1237
|
+
self.body_size
|
|
1238
|
+
}
|
|
1239
|
+
|
|
1240
|
+
fn metadata(&self) -> PageMetadata {
|
|
1241
|
+
self.metadata.clone()
|
|
1242
|
+
}
|
|
1243
|
+
|
|
1244
|
+
fn links(&self) -> Vec<LinkInfo> {
|
|
1245
|
+
self.links.clone()
|
|
1246
|
+
}
|
|
1247
|
+
|
|
1248
|
+
fn images(&self) -> Vec<ImageInfo> {
|
|
1249
|
+
self.images.clone()
|
|
1250
|
+
}
|
|
1251
|
+
|
|
1252
|
+
fn feeds(&self) -> Vec<FeedInfo> {
|
|
1253
|
+
self.feeds.clone()
|
|
1254
|
+
}
|
|
1255
|
+
|
|
1256
|
+
fn json_ld(&self) -> Vec<JsonLdEntry> {
|
|
1257
|
+
self.json_ld.clone()
|
|
1258
|
+
}
|
|
1259
|
+
|
|
1260
|
+
fn depth(&self) -> usize {
|
|
1261
|
+
self.depth
|
|
1262
|
+
}
|
|
1263
|
+
|
|
1264
|
+
fn stayed_on_domain(&self) -> bool {
|
|
1265
|
+
self.stayed_on_domain
|
|
1266
|
+
}
|
|
1267
|
+
|
|
1268
|
+
fn was_skipped(&self) -> bool {
|
|
1269
|
+
self.was_skipped
|
|
1270
|
+
}
|
|
1271
|
+
|
|
1272
|
+
fn is_pdf(&self) -> bool {
|
|
1273
|
+
self.is_pdf
|
|
1274
|
+
}
|
|
1275
|
+
|
|
1276
|
+
fn detected_charset(&self) -> Option<String> {
|
|
1277
|
+
self.detected_charset.clone()
|
|
1278
|
+
}
|
|
1279
|
+
|
|
1280
|
+
fn markdown(&self) -> Option<MarkdownResult> {
|
|
1281
|
+
self.markdown.clone()
|
|
1282
|
+
}
|
|
1283
|
+
|
|
1284
|
+
fn extracted_data(&self) -> Option<String> {
|
|
1285
|
+
self.extracted_data.clone()
|
|
1286
|
+
}
|
|
1287
|
+
|
|
1288
|
+
fn extraction_meta(&self) -> Option<ExtractionMeta> {
|
|
1289
|
+
self.extraction_meta.clone()
|
|
1290
|
+
}
|
|
1291
|
+
|
|
1292
|
+
fn downloaded_document(&self) -> Option<DownloadedDocument> {
|
|
1293
|
+
self.downloaded_document.clone()
|
|
1294
|
+
}
|
|
1295
|
+
}
|
|
1296
|
+
|
|
1297
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1298
|
+
#[magnus::wrap(class = "Kreuzcrawl::CrawlResult")]
|
|
1299
|
+
#[serde(default)]
|
|
1300
|
+
pub struct CrawlResult {
|
|
1301
|
+
pub pages: Vec<CrawlPageResult>,
|
|
1302
|
+
pub final_url: String,
|
|
1303
|
+
pub redirect_count: usize,
|
|
1304
|
+
pub was_skipped: bool,
|
|
1305
|
+
pub error: Option<String>,
|
|
1306
|
+
pub cookies: Vec<CookieInfo>,
|
|
1307
|
+
pub normalized_urls: Vec<String>,
|
|
1308
|
+
}
|
|
1309
|
+
|
|
1310
|
+
unsafe impl IntoValueFromNative for CrawlResult {}
|
|
1311
|
+
|
|
1312
|
+
impl magnus::TryConvert for CrawlResult {
|
|
1313
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1314
|
+
let r: &CrawlResult = magnus::TryConvert::try_convert(val)?;
|
|
1315
|
+
Ok(r.clone())
|
|
1316
|
+
}
|
|
1317
|
+
}
|
|
1318
|
+
unsafe impl TryConvertOwned for CrawlResult {}
|
|
1319
|
+
|
|
1320
|
+
impl Default for CrawlResult {
|
|
1321
|
+
fn default() -> Self {
|
|
1322
|
+
Self {
|
|
1323
|
+
pages: Default::default(),
|
|
1324
|
+
final_url: Default::default(),
|
|
1325
|
+
redirect_count: Default::default(),
|
|
1326
|
+
was_skipped: Default::default(),
|
|
1327
|
+
error: Default::default(),
|
|
1328
|
+
cookies: Default::default(),
|
|
1329
|
+
normalized_urls: Default::default(),
|
|
1330
|
+
}
|
|
1331
|
+
}
|
|
1332
|
+
}
|
|
1333
|
+
|
|
1334
|
+
impl CrawlResult {
|
|
1335
|
+
fn new(
|
|
1336
|
+
pages: Option<Vec<CrawlPageResult>>,
|
|
1337
|
+
final_url: Option<String>,
|
|
1338
|
+
redirect_count: Option<usize>,
|
|
1339
|
+
was_skipped: Option<bool>,
|
|
1340
|
+
error: Option<String>,
|
|
1341
|
+
cookies: Option<Vec<CookieInfo>>,
|
|
1342
|
+
normalized_urls: Option<Vec<String>>,
|
|
1343
|
+
) -> Self {
|
|
1344
|
+
Self {
|
|
1345
|
+
pages: pages.unwrap_or_default(),
|
|
1346
|
+
final_url: final_url.unwrap_or_default(),
|
|
1347
|
+
redirect_count: redirect_count.unwrap_or_default(),
|
|
1348
|
+
was_skipped: was_skipped.unwrap_or_default(),
|
|
1349
|
+
error,
|
|
1350
|
+
cookies: cookies.unwrap_or_default(),
|
|
1351
|
+
normalized_urls: normalized_urls.unwrap_or_default(),
|
|
1352
|
+
}
|
|
1353
|
+
}
|
|
1354
|
+
|
|
1355
|
+
fn pages(&self) -> Vec<CrawlPageResult> {
|
|
1356
|
+
self.pages.clone()
|
|
1357
|
+
}
|
|
1358
|
+
|
|
1359
|
+
fn final_url(&self) -> String {
|
|
1360
|
+
self.final_url.clone()
|
|
1361
|
+
}
|
|
1362
|
+
|
|
1363
|
+
fn redirect_count(&self) -> usize {
|
|
1364
|
+
self.redirect_count
|
|
1365
|
+
}
|
|
1366
|
+
|
|
1367
|
+
fn was_skipped(&self) -> bool {
|
|
1368
|
+
self.was_skipped
|
|
1369
|
+
}
|
|
1370
|
+
|
|
1371
|
+
fn error(&self) -> Option<String> {
|
|
1372
|
+
self.error.clone()
|
|
1373
|
+
}
|
|
1374
|
+
|
|
1375
|
+
fn cookies(&self) -> Vec<CookieInfo> {
|
|
1376
|
+
self.cookies.clone()
|
|
1377
|
+
}
|
|
1378
|
+
|
|
1379
|
+
fn normalized_urls(&self) -> Vec<String> {
|
|
1380
|
+
self.normalized_urls.clone()
|
|
1381
|
+
}
|
|
1382
|
+
}
|
|
1383
|
+
|
|
1384
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1385
|
+
#[magnus::wrap(class = "Kreuzcrawl::SitemapUrl")]
|
|
1386
|
+
#[serde(default)]
|
|
1387
|
+
pub struct SitemapUrl {
|
|
1388
|
+
pub url: String,
|
|
1389
|
+
pub lastmod: Option<String>,
|
|
1390
|
+
pub changefreq: Option<String>,
|
|
1391
|
+
pub priority: Option<String>,
|
|
1392
|
+
}
|
|
1393
|
+
|
|
1394
|
+
unsafe impl IntoValueFromNative for SitemapUrl {}
|
|
1395
|
+
|
|
1396
|
+
impl magnus::TryConvert for SitemapUrl {
|
|
1397
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1398
|
+
let r: &SitemapUrl = magnus::TryConvert::try_convert(val)?;
|
|
1399
|
+
Ok(r.clone())
|
|
1400
|
+
}
|
|
1401
|
+
}
|
|
1402
|
+
unsafe impl TryConvertOwned for SitemapUrl {}
|
|
1403
|
+
|
|
1404
|
+
impl Default for SitemapUrl {
|
|
1405
|
+
fn default() -> Self {
|
|
1406
|
+
Self {
|
|
1407
|
+
url: Default::default(),
|
|
1408
|
+
lastmod: Default::default(),
|
|
1409
|
+
changefreq: Default::default(),
|
|
1410
|
+
priority: Default::default(),
|
|
1411
|
+
}
|
|
1412
|
+
}
|
|
1413
|
+
}
|
|
1414
|
+
|
|
1415
|
+
impl SitemapUrl {
|
|
1416
|
+
fn new(url: Option<String>, lastmod: Option<String>, changefreq: Option<String>, priority: Option<String>) -> Self {
|
|
1417
|
+
Self {
|
|
1418
|
+
url: url.unwrap_or_default(),
|
|
1419
|
+
lastmod,
|
|
1420
|
+
changefreq,
|
|
1421
|
+
priority,
|
|
1422
|
+
}
|
|
1423
|
+
}
|
|
1424
|
+
|
|
1425
|
+
fn url(&self) -> String {
|
|
1426
|
+
self.url.clone()
|
|
1427
|
+
}
|
|
1428
|
+
|
|
1429
|
+
fn lastmod(&self) -> Option<String> {
|
|
1430
|
+
self.lastmod.clone()
|
|
1431
|
+
}
|
|
1432
|
+
|
|
1433
|
+
fn changefreq(&self) -> Option<String> {
|
|
1434
|
+
self.changefreq.clone()
|
|
1435
|
+
}
|
|
1436
|
+
|
|
1437
|
+
fn priority(&self) -> Option<String> {
|
|
1438
|
+
self.priority.clone()
|
|
1439
|
+
}
|
|
1440
|
+
}
|
|
1441
|
+
|
|
1442
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1443
|
+
#[magnus::wrap(class = "Kreuzcrawl::MapResult")]
|
|
1444
|
+
#[serde(default)]
|
|
1445
|
+
pub struct MapResult {
|
|
1446
|
+
pub urls: Vec<SitemapUrl>,
|
|
1447
|
+
}
|
|
1448
|
+
|
|
1449
|
+
unsafe impl IntoValueFromNative for MapResult {}
|
|
1450
|
+
|
|
1451
|
+
impl magnus::TryConvert for MapResult {
|
|
1452
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1453
|
+
let r: &MapResult = magnus::TryConvert::try_convert(val)?;
|
|
1454
|
+
Ok(r.clone())
|
|
1455
|
+
}
|
|
1456
|
+
}
|
|
1457
|
+
unsafe impl TryConvertOwned for MapResult {}
|
|
1458
|
+
|
|
1459
|
+
impl Default for MapResult {
|
|
1460
|
+
fn default() -> Self {
|
|
1461
|
+
Self {
|
|
1462
|
+
urls: Default::default(),
|
|
1463
|
+
}
|
|
1464
|
+
}
|
|
1465
|
+
}
|
|
1466
|
+
|
|
1467
|
+
impl MapResult {
|
|
1468
|
+
fn new(urls: Option<Vec<SitemapUrl>>) -> Self {
|
|
1469
|
+
Self {
|
|
1470
|
+
urls: urls.unwrap_or_default(),
|
|
1471
|
+
}
|
|
1472
|
+
}
|
|
1473
|
+
|
|
1474
|
+
fn urls(&self) -> Vec<SitemapUrl> {
|
|
1475
|
+
self.urls.clone()
|
|
1476
|
+
}
|
|
1477
|
+
}
|
|
1478
|
+
|
|
1479
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1480
|
+
#[magnus::wrap(class = "Kreuzcrawl::MarkdownResult")]
|
|
1481
|
+
#[serde(default)]
|
|
1482
|
+
pub struct MarkdownResult {
|
|
1483
|
+
pub content: String,
|
|
1484
|
+
pub document_structure: Option<String>,
|
|
1485
|
+
pub tables: Vec<String>,
|
|
1486
|
+
pub warnings: Vec<String>,
|
|
1487
|
+
pub citations: Option<CitationResult>,
|
|
1488
|
+
pub fit_content: Option<String>,
|
|
1489
|
+
}
|
|
1490
|
+
|
|
1491
|
+
unsafe impl IntoValueFromNative for MarkdownResult {}
|
|
1492
|
+
|
|
1493
|
+
impl magnus::TryConvert for MarkdownResult {
|
|
1494
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1495
|
+
let r: &MarkdownResult = magnus::TryConvert::try_convert(val)?;
|
|
1496
|
+
Ok(r.clone())
|
|
1497
|
+
}
|
|
1498
|
+
}
|
|
1499
|
+
unsafe impl TryConvertOwned for MarkdownResult {}
|
|
1500
|
+
|
|
1501
|
+
impl Default for MarkdownResult {
|
|
1502
|
+
fn default() -> Self {
|
|
1503
|
+
Self {
|
|
1504
|
+
content: Default::default(),
|
|
1505
|
+
document_structure: Default::default(),
|
|
1506
|
+
tables: Default::default(),
|
|
1507
|
+
warnings: Default::default(),
|
|
1508
|
+
citations: Default::default(),
|
|
1509
|
+
fit_content: Default::default(),
|
|
1510
|
+
}
|
|
1511
|
+
}
|
|
1512
|
+
}
|
|
1513
|
+
|
|
1514
|
+
impl MarkdownResult {
|
|
1515
|
+
fn new(
|
|
1516
|
+
content: Option<String>,
|
|
1517
|
+
document_structure: Option<String>,
|
|
1518
|
+
tables: Option<Vec<String>>,
|
|
1519
|
+
warnings: Option<Vec<String>>,
|
|
1520
|
+
citations: Option<CitationResult>,
|
|
1521
|
+
fit_content: Option<String>,
|
|
1522
|
+
) -> Self {
|
|
1523
|
+
Self {
|
|
1524
|
+
content: content.unwrap_or_default(),
|
|
1525
|
+
document_structure,
|
|
1526
|
+
tables: tables.unwrap_or_default(),
|
|
1527
|
+
warnings: warnings.unwrap_or_default(),
|
|
1528
|
+
citations,
|
|
1529
|
+
fit_content,
|
|
1530
|
+
}
|
|
1531
|
+
}
|
|
1532
|
+
|
|
1533
|
+
fn content(&self) -> String {
|
|
1534
|
+
self.content.clone()
|
|
1535
|
+
}
|
|
1536
|
+
|
|
1537
|
+
fn document_structure(&self) -> Option<String> {
|
|
1538
|
+
self.document_structure.clone()
|
|
1539
|
+
}
|
|
1540
|
+
|
|
1541
|
+
fn tables(&self) -> Vec<String> {
|
|
1542
|
+
self.tables.clone()
|
|
1543
|
+
}
|
|
1544
|
+
|
|
1545
|
+
fn warnings(&self) -> Vec<String> {
|
|
1546
|
+
self.warnings.clone()
|
|
1547
|
+
}
|
|
1548
|
+
|
|
1549
|
+
fn citations(&self) -> Option<CitationResult> {
|
|
1550
|
+
self.citations.clone()
|
|
1551
|
+
}
|
|
1552
|
+
|
|
1553
|
+
fn fit_content(&self) -> Option<String> {
|
|
1554
|
+
self.fit_content.clone()
|
|
1555
|
+
}
|
|
1556
|
+
}
|
|
1557
|
+
|
|
1558
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1559
|
+
#[magnus::wrap(class = "Kreuzcrawl::CachedPage")]
|
|
1560
|
+
#[serde(default)]
|
|
1561
|
+
pub struct CachedPage {
|
|
1562
|
+
pub url: String,
|
|
1563
|
+
pub status_code: u16,
|
|
1564
|
+
pub content_type: String,
|
|
1565
|
+
pub body: String,
|
|
1566
|
+
pub etag: Option<String>,
|
|
1567
|
+
pub last_modified: Option<String>,
|
|
1568
|
+
pub cached_at: u64,
|
|
1569
|
+
}
|
|
1570
|
+
|
|
1571
|
+
unsafe impl IntoValueFromNative for CachedPage {}
|
|
1572
|
+
|
|
1573
|
+
impl magnus::TryConvert for CachedPage {
|
|
1574
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1575
|
+
let r: &CachedPage = magnus::TryConvert::try_convert(val)?;
|
|
1576
|
+
Ok(r.clone())
|
|
1577
|
+
}
|
|
1578
|
+
}
|
|
1579
|
+
unsafe impl TryConvertOwned for CachedPage {}
|
|
1580
|
+
|
|
1581
|
+
impl Default for CachedPage {
|
|
1582
|
+
fn default() -> Self {
|
|
1583
|
+
Self {
|
|
1584
|
+
url: Default::default(),
|
|
1585
|
+
status_code: Default::default(),
|
|
1586
|
+
content_type: Default::default(),
|
|
1587
|
+
body: Default::default(),
|
|
1588
|
+
etag: Default::default(),
|
|
1589
|
+
last_modified: Default::default(),
|
|
1590
|
+
cached_at: Default::default(),
|
|
1591
|
+
}
|
|
1592
|
+
}
|
|
1593
|
+
}
|
|
1594
|
+
|
|
1595
|
+
impl CachedPage {
|
|
1596
|
+
fn new(
|
|
1597
|
+
url: Option<String>,
|
|
1598
|
+
status_code: Option<u16>,
|
|
1599
|
+
content_type: Option<String>,
|
|
1600
|
+
body: Option<String>,
|
|
1601
|
+
etag: Option<String>,
|
|
1602
|
+
last_modified: Option<String>,
|
|
1603
|
+
cached_at: Option<u64>,
|
|
1604
|
+
) -> Self {
|
|
1605
|
+
Self {
|
|
1606
|
+
url: url.unwrap_or_default(),
|
|
1607
|
+
status_code: status_code.unwrap_or_default(),
|
|
1608
|
+
content_type: content_type.unwrap_or_default(),
|
|
1609
|
+
body: body.unwrap_or_default(),
|
|
1610
|
+
etag,
|
|
1611
|
+
last_modified,
|
|
1612
|
+
cached_at: cached_at.unwrap_or_default(),
|
|
1613
|
+
}
|
|
1614
|
+
}
|
|
1615
|
+
|
|
1616
|
+
fn url(&self) -> String {
|
|
1617
|
+
self.url.clone()
|
|
1618
|
+
}
|
|
1619
|
+
|
|
1620
|
+
fn status_code(&self) -> u16 {
|
|
1621
|
+
self.status_code
|
|
1622
|
+
}
|
|
1623
|
+
|
|
1624
|
+
fn content_type(&self) -> String {
|
|
1625
|
+
self.content_type.clone()
|
|
1626
|
+
}
|
|
1627
|
+
|
|
1628
|
+
fn body(&self) -> String {
|
|
1629
|
+
self.body.clone()
|
|
1630
|
+
}
|
|
1631
|
+
|
|
1632
|
+
fn etag(&self) -> Option<String> {
|
|
1633
|
+
self.etag.clone()
|
|
1634
|
+
}
|
|
1635
|
+
|
|
1636
|
+
fn last_modified(&self) -> Option<String> {
|
|
1637
|
+
self.last_modified.clone()
|
|
1638
|
+
}
|
|
1639
|
+
|
|
1640
|
+
fn cached_at(&self) -> u64 {
|
|
1641
|
+
self.cached_at
|
|
1642
|
+
}
|
|
1643
|
+
}
|
|
1644
|
+
|
|
1645
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
|
1646
|
+
#[magnus::wrap(class = "Kreuzcrawl::LinkInfo")]
|
|
1647
|
+
#[serde(default)]
|
|
1648
|
+
pub struct LinkInfo {
|
|
1649
|
+
pub url: String,
|
|
1650
|
+
pub text: String,
|
|
1651
|
+
pub link_type: LinkType,
|
|
1652
|
+
pub rel: Option<String>,
|
|
1653
|
+
pub nofollow: bool,
|
|
1654
|
+
}
|
|
1655
|
+
|
|
1656
|
+
unsafe impl IntoValueFromNative for LinkInfo {}
|
|
1657
|
+
|
|
1658
|
+
impl magnus::TryConvert for LinkInfo {
|
|
1659
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1660
|
+
let r: &LinkInfo = magnus::TryConvert::try_convert(val)?;
|
|
1661
|
+
Ok(r.clone())
|
|
1662
|
+
}
|
|
1663
|
+
}
|
|
1664
|
+
unsafe impl TryConvertOwned for LinkInfo {}
|
|
1665
|
+
|
|
1666
|
+
impl LinkInfo {
|
|
1667
|
+
fn new(
|
|
1668
|
+
url: Option<String>,
|
|
1669
|
+
text: Option<String>,
|
|
1670
|
+
link_type: Option<LinkType>,
|
|
1671
|
+
rel: Option<String>,
|
|
1672
|
+
nofollow: Option<bool>,
|
|
1673
|
+
) -> Self {
|
|
1674
|
+
Self {
|
|
1675
|
+
url: url.unwrap_or_default(),
|
|
1676
|
+
text: text.unwrap_or_default(),
|
|
1677
|
+
link_type: link_type.unwrap_or_default(),
|
|
1678
|
+
rel,
|
|
1679
|
+
nofollow: nofollow.unwrap_or_default(),
|
|
1680
|
+
}
|
|
1681
|
+
}
|
|
1682
|
+
|
|
1683
|
+
fn url(&self) -> String {
|
|
1684
|
+
self.url.clone()
|
|
1685
|
+
}
|
|
1686
|
+
|
|
1687
|
+
fn text(&self) -> String {
|
|
1688
|
+
self.text.clone()
|
|
1689
|
+
}
|
|
1690
|
+
|
|
1691
|
+
fn link_type(&self) -> LinkType {
|
|
1692
|
+
self.link_type.clone()
|
|
1693
|
+
}
|
|
1694
|
+
|
|
1695
|
+
fn rel(&self) -> Option<String> {
|
|
1696
|
+
self.rel.clone()
|
|
1697
|
+
}
|
|
1698
|
+
|
|
1699
|
+
fn nofollow(&self) -> bool {
|
|
1700
|
+
self.nofollow
|
|
1701
|
+
}
|
|
1702
|
+
}
|
|
1703
|
+
|
|
1704
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
|
1705
|
+
#[magnus::wrap(class = "Kreuzcrawl::ImageInfo")]
|
|
1706
|
+
#[serde(default)]
|
|
1707
|
+
pub struct ImageInfo {
|
|
1708
|
+
pub url: String,
|
|
1709
|
+
pub alt: Option<String>,
|
|
1710
|
+
pub width: Option<u32>,
|
|
1711
|
+
pub height: Option<u32>,
|
|
1712
|
+
pub source: ImageSource,
|
|
1713
|
+
}
|
|
1714
|
+
|
|
1715
|
+
unsafe impl IntoValueFromNative for ImageInfo {}
|
|
1716
|
+
|
|
1717
|
+
impl magnus::TryConvert for ImageInfo {
|
|
1718
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1719
|
+
let r: &ImageInfo = magnus::TryConvert::try_convert(val)?;
|
|
1720
|
+
Ok(r.clone())
|
|
1721
|
+
}
|
|
1722
|
+
}
|
|
1723
|
+
unsafe impl TryConvertOwned for ImageInfo {}
|
|
1724
|
+
|
|
1725
|
+
impl ImageInfo {
|
|
1726
|
+
fn new(
|
|
1727
|
+
url: Option<String>,
|
|
1728
|
+
alt: Option<String>,
|
|
1729
|
+
width: Option<u32>,
|
|
1730
|
+
height: Option<u32>,
|
|
1731
|
+
source: Option<ImageSource>,
|
|
1732
|
+
) -> Self {
|
|
1733
|
+
Self {
|
|
1734
|
+
url: url.unwrap_or_default(),
|
|
1735
|
+
alt,
|
|
1736
|
+
width,
|
|
1737
|
+
height,
|
|
1738
|
+
source: source.unwrap_or_default(),
|
|
1739
|
+
}
|
|
1740
|
+
}
|
|
1741
|
+
|
|
1742
|
+
fn url(&self) -> String {
|
|
1743
|
+
self.url.clone()
|
|
1744
|
+
}
|
|
1745
|
+
|
|
1746
|
+
fn alt(&self) -> Option<String> {
|
|
1747
|
+
self.alt.clone()
|
|
1748
|
+
}
|
|
1749
|
+
|
|
1750
|
+
fn width(&self) -> Option<u32> {
|
|
1751
|
+
self.width
|
|
1752
|
+
}
|
|
1753
|
+
|
|
1754
|
+
fn height(&self) -> Option<u32> {
|
|
1755
|
+
self.height
|
|
1756
|
+
}
|
|
1757
|
+
|
|
1758
|
+
fn source(&self) -> ImageSource {
|
|
1759
|
+
self.source.clone()
|
|
1760
|
+
}
|
|
1761
|
+
}
|
|
1762
|
+
|
|
1763
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
|
1764
|
+
#[magnus::wrap(class = "Kreuzcrawl::FeedInfo")]
|
|
1765
|
+
#[serde(default)]
|
|
1766
|
+
pub struct FeedInfo {
|
|
1767
|
+
pub url: String,
|
|
1768
|
+
pub title: Option<String>,
|
|
1769
|
+
pub feed_type: FeedType,
|
|
1770
|
+
}
|
|
1771
|
+
|
|
1772
|
+
unsafe impl IntoValueFromNative for FeedInfo {}
|
|
1773
|
+
|
|
1774
|
+
impl magnus::TryConvert for FeedInfo {
|
|
1775
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1776
|
+
let r: &FeedInfo = magnus::TryConvert::try_convert(val)?;
|
|
1777
|
+
Ok(r.clone())
|
|
1778
|
+
}
|
|
1779
|
+
}
|
|
1780
|
+
unsafe impl TryConvertOwned for FeedInfo {}
|
|
1781
|
+
|
|
1782
|
+
impl FeedInfo {
|
|
1783
|
+
fn new(url: Option<String>, title: Option<String>, feed_type: Option<FeedType>) -> Self {
|
|
1784
|
+
Self {
|
|
1785
|
+
url: url.unwrap_or_default(),
|
|
1786
|
+
title,
|
|
1787
|
+
feed_type: feed_type.unwrap_or_default(),
|
|
1788
|
+
}
|
|
1789
|
+
}
|
|
1790
|
+
|
|
1791
|
+
fn url(&self) -> String {
|
|
1792
|
+
self.url.clone()
|
|
1793
|
+
}
|
|
1794
|
+
|
|
1795
|
+
fn title(&self) -> Option<String> {
|
|
1796
|
+
self.title.clone()
|
|
1797
|
+
}
|
|
1798
|
+
|
|
1799
|
+
fn feed_type(&self) -> FeedType {
|
|
1800
|
+
self.feed_type.clone()
|
|
1801
|
+
}
|
|
1802
|
+
}
|
|
1803
|
+
|
|
1804
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1805
|
+
#[magnus::wrap(class = "Kreuzcrawl::JsonLdEntry")]
|
|
1806
|
+
#[serde(default)]
|
|
1807
|
+
pub struct JsonLdEntry {
|
|
1808
|
+
pub schema_type: String,
|
|
1809
|
+
pub name: Option<String>,
|
|
1810
|
+
pub raw: String,
|
|
1811
|
+
}
|
|
1812
|
+
|
|
1813
|
+
unsafe impl IntoValueFromNative for JsonLdEntry {}
|
|
1814
|
+
|
|
1815
|
+
impl magnus::TryConvert for JsonLdEntry {
|
|
1816
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1817
|
+
let r: &JsonLdEntry = magnus::TryConvert::try_convert(val)?;
|
|
1818
|
+
Ok(r.clone())
|
|
1819
|
+
}
|
|
1820
|
+
}
|
|
1821
|
+
unsafe impl TryConvertOwned for JsonLdEntry {}
|
|
1822
|
+
|
|
1823
|
+
impl Default for JsonLdEntry {
|
|
1824
|
+
fn default() -> Self {
|
|
1825
|
+
Self {
|
|
1826
|
+
schema_type: Default::default(),
|
|
1827
|
+
name: Default::default(),
|
|
1828
|
+
raw: Default::default(),
|
|
1829
|
+
}
|
|
1830
|
+
}
|
|
1831
|
+
}
|
|
1832
|
+
|
|
1833
|
+
impl JsonLdEntry {
|
|
1834
|
+
fn new(schema_type: Option<String>, name: Option<String>, raw: Option<String>) -> Self {
|
|
1835
|
+
Self {
|
|
1836
|
+
schema_type: schema_type.unwrap_or_default(),
|
|
1837
|
+
name,
|
|
1838
|
+
raw: raw.unwrap_or_default(),
|
|
1839
|
+
}
|
|
1840
|
+
}
|
|
1841
|
+
|
|
1842
|
+
fn schema_type(&self) -> String {
|
|
1843
|
+
self.schema_type.clone()
|
|
1844
|
+
}
|
|
1845
|
+
|
|
1846
|
+
fn name(&self) -> Option<String> {
|
|
1847
|
+
self.name.clone()
|
|
1848
|
+
}
|
|
1849
|
+
|
|
1850
|
+
fn raw(&self) -> String {
|
|
1851
|
+
self.raw.clone()
|
|
1852
|
+
}
|
|
1853
|
+
}
|
|
1854
|
+
|
|
1855
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1856
|
+
#[magnus::wrap(class = "Kreuzcrawl::CookieInfo")]
|
|
1857
|
+
#[serde(default)]
|
|
1858
|
+
pub struct CookieInfo {
|
|
1859
|
+
pub name: String,
|
|
1860
|
+
pub value: String,
|
|
1861
|
+
pub domain: Option<String>,
|
|
1862
|
+
pub path: Option<String>,
|
|
1863
|
+
}
|
|
1864
|
+
|
|
1865
|
+
unsafe impl IntoValueFromNative for CookieInfo {}
|
|
1866
|
+
|
|
1867
|
+
impl magnus::TryConvert for CookieInfo {
|
|
1868
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1869
|
+
let r: &CookieInfo = magnus::TryConvert::try_convert(val)?;
|
|
1870
|
+
Ok(r.clone())
|
|
1871
|
+
}
|
|
1872
|
+
}
|
|
1873
|
+
unsafe impl TryConvertOwned for CookieInfo {}
|
|
1874
|
+
|
|
1875
|
+
impl Default for CookieInfo {
|
|
1876
|
+
fn default() -> Self {
|
|
1877
|
+
Self {
|
|
1878
|
+
name: Default::default(),
|
|
1879
|
+
value: Default::default(),
|
|
1880
|
+
domain: Default::default(),
|
|
1881
|
+
path: Default::default(),
|
|
1882
|
+
}
|
|
1883
|
+
}
|
|
1884
|
+
}
|
|
1885
|
+
|
|
1886
|
+
impl CookieInfo {
|
|
1887
|
+
fn new(name: Option<String>, value: Option<String>, domain: Option<String>, path: Option<String>) -> Self {
|
|
1888
|
+
Self {
|
|
1889
|
+
name: name.unwrap_or_default(),
|
|
1890
|
+
value: value.unwrap_or_default(),
|
|
1891
|
+
domain,
|
|
1892
|
+
path,
|
|
1893
|
+
}
|
|
1894
|
+
}
|
|
1895
|
+
|
|
1896
|
+
fn name(&self) -> String {
|
|
1897
|
+
self.name.clone()
|
|
1898
|
+
}
|
|
1899
|
+
|
|
1900
|
+
fn value(&self) -> String {
|
|
1901
|
+
self.value.clone()
|
|
1902
|
+
}
|
|
1903
|
+
|
|
1904
|
+
fn domain(&self) -> Option<String> {
|
|
1905
|
+
self.domain.clone()
|
|
1906
|
+
}
|
|
1907
|
+
|
|
1908
|
+
fn path(&self) -> Option<String> {
|
|
1909
|
+
self.path.clone()
|
|
1910
|
+
}
|
|
1911
|
+
}
|
|
1912
|
+
|
|
1913
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
|
1914
|
+
#[magnus::wrap(class = "Kreuzcrawl::DownloadedAsset")]
|
|
1915
|
+
#[serde(default)]
|
|
1916
|
+
pub struct DownloadedAsset {
|
|
1917
|
+
pub url: String,
|
|
1918
|
+
pub content_hash: String,
|
|
1919
|
+
pub mime_type: Option<String>,
|
|
1920
|
+
pub size: usize,
|
|
1921
|
+
pub asset_category: AssetCategory,
|
|
1922
|
+
pub html_tag: Option<String>,
|
|
1923
|
+
}
|
|
1924
|
+
|
|
1925
|
+
unsafe impl IntoValueFromNative for DownloadedAsset {}
|
|
1926
|
+
|
|
1927
|
+
impl magnus::TryConvert for DownloadedAsset {
|
|
1928
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1929
|
+
let r: &DownloadedAsset = magnus::TryConvert::try_convert(val)?;
|
|
1930
|
+
Ok(r.clone())
|
|
1931
|
+
}
|
|
1932
|
+
}
|
|
1933
|
+
unsafe impl TryConvertOwned for DownloadedAsset {}
|
|
1934
|
+
|
|
1935
|
+
impl DownloadedAsset {
|
|
1936
|
+
fn new(
|
|
1937
|
+
url: Option<String>,
|
|
1938
|
+
content_hash: Option<String>,
|
|
1939
|
+
mime_type: Option<String>,
|
|
1940
|
+
size: Option<usize>,
|
|
1941
|
+
asset_category: Option<AssetCategory>,
|
|
1942
|
+
html_tag: Option<String>,
|
|
1943
|
+
) -> Self {
|
|
1944
|
+
Self {
|
|
1945
|
+
url: url.unwrap_or_default(),
|
|
1946
|
+
content_hash: content_hash.unwrap_or_default(),
|
|
1947
|
+
mime_type,
|
|
1948
|
+
size: size.unwrap_or_default(),
|
|
1949
|
+
asset_category: asset_category.unwrap_or_default(),
|
|
1950
|
+
html_tag,
|
|
1951
|
+
}
|
|
1952
|
+
}
|
|
1953
|
+
|
|
1954
|
+
fn url(&self) -> String {
|
|
1955
|
+
self.url.clone()
|
|
1956
|
+
}
|
|
1957
|
+
|
|
1958
|
+
fn content_hash(&self) -> String {
|
|
1959
|
+
self.content_hash.clone()
|
|
1960
|
+
}
|
|
1961
|
+
|
|
1962
|
+
fn mime_type(&self) -> Option<String> {
|
|
1963
|
+
self.mime_type.clone()
|
|
1964
|
+
}
|
|
1965
|
+
|
|
1966
|
+
fn size(&self) -> usize {
|
|
1967
|
+
self.size
|
|
1968
|
+
}
|
|
1969
|
+
|
|
1970
|
+
fn asset_category(&self) -> AssetCategory {
|
|
1971
|
+
self.asset_category.clone()
|
|
1972
|
+
}
|
|
1973
|
+
|
|
1974
|
+
fn html_tag(&self) -> Option<String> {
|
|
1975
|
+
self.html_tag.clone()
|
|
1976
|
+
}
|
|
1977
|
+
}
|
|
1978
|
+
|
|
1979
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
1980
|
+
#[magnus::wrap(class = "Kreuzcrawl::ArticleMetadata")]
|
|
1981
|
+
#[serde(default)]
|
|
1982
|
+
pub struct ArticleMetadata {
|
|
1983
|
+
pub published_time: Option<String>,
|
|
1984
|
+
pub modified_time: Option<String>,
|
|
1985
|
+
pub author: Option<String>,
|
|
1986
|
+
pub section: Option<String>,
|
|
1987
|
+
pub tags: Vec<String>,
|
|
1988
|
+
}
|
|
1989
|
+
|
|
1990
|
+
unsafe impl IntoValueFromNative for ArticleMetadata {}
|
|
1991
|
+
|
|
1992
|
+
impl magnus::TryConvert for ArticleMetadata {
|
|
1993
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
1994
|
+
let r: &ArticleMetadata = magnus::TryConvert::try_convert(val)?;
|
|
1995
|
+
Ok(r.clone())
|
|
1996
|
+
}
|
|
1997
|
+
}
|
|
1998
|
+
unsafe impl TryConvertOwned for ArticleMetadata {}
|
|
1999
|
+
|
|
2000
|
+
impl Default for ArticleMetadata {
|
|
2001
|
+
fn default() -> Self {
|
|
2002
|
+
Self {
|
|
2003
|
+
published_time: Default::default(),
|
|
2004
|
+
modified_time: Default::default(),
|
|
2005
|
+
author: Default::default(),
|
|
2006
|
+
section: Default::default(),
|
|
2007
|
+
tags: Default::default(),
|
|
2008
|
+
}
|
|
2009
|
+
}
|
|
2010
|
+
}
|
|
2011
|
+
|
|
2012
|
+
impl ArticleMetadata {
|
|
2013
|
+
fn new(
|
|
2014
|
+
published_time: Option<String>,
|
|
2015
|
+
modified_time: Option<String>,
|
|
2016
|
+
author: Option<String>,
|
|
2017
|
+
section: Option<String>,
|
|
2018
|
+
tags: Option<Vec<String>>,
|
|
2019
|
+
) -> Self {
|
|
2020
|
+
Self {
|
|
2021
|
+
published_time,
|
|
2022
|
+
modified_time,
|
|
2023
|
+
author,
|
|
2024
|
+
section,
|
|
2025
|
+
tags: tags.unwrap_or_default(),
|
|
2026
|
+
}
|
|
2027
|
+
}
|
|
2028
|
+
|
|
2029
|
+
fn published_time(&self) -> Option<String> {
|
|
2030
|
+
self.published_time.clone()
|
|
2031
|
+
}
|
|
2032
|
+
|
|
2033
|
+
fn modified_time(&self) -> Option<String> {
|
|
2034
|
+
self.modified_time.clone()
|
|
2035
|
+
}
|
|
2036
|
+
|
|
2037
|
+
fn author(&self) -> Option<String> {
|
|
2038
|
+
self.author.clone()
|
|
2039
|
+
}
|
|
2040
|
+
|
|
2041
|
+
fn section(&self) -> Option<String> {
|
|
2042
|
+
self.section.clone()
|
|
2043
|
+
}
|
|
2044
|
+
|
|
2045
|
+
fn tags(&self) -> Vec<String> {
|
|
2046
|
+
self.tags.clone()
|
|
2047
|
+
}
|
|
2048
|
+
}
|
|
2049
|
+
|
|
2050
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2051
|
+
#[magnus::wrap(class = "Kreuzcrawl::HreflangEntry")]
|
|
2052
|
+
#[serde(default)]
|
|
2053
|
+
pub struct HreflangEntry {
|
|
2054
|
+
pub lang: String,
|
|
2055
|
+
pub url: String,
|
|
2056
|
+
}
|
|
2057
|
+
|
|
2058
|
+
unsafe impl IntoValueFromNative for HreflangEntry {}
|
|
2059
|
+
|
|
2060
|
+
impl magnus::TryConvert for HreflangEntry {
|
|
2061
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2062
|
+
let r: &HreflangEntry = magnus::TryConvert::try_convert(val)?;
|
|
2063
|
+
Ok(r.clone())
|
|
2064
|
+
}
|
|
2065
|
+
}
|
|
2066
|
+
unsafe impl TryConvertOwned for HreflangEntry {}
|
|
2067
|
+
|
|
2068
|
+
impl Default for HreflangEntry {
|
|
2069
|
+
fn default() -> Self {
|
|
2070
|
+
Self {
|
|
2071
|
+
lang: Default::default(),
|
|
2072
|
+
url: Default::default(),
|
|
2073
|
+
}
|
|
2074
|
+
}
|
|
2075
|
+
}
|
|
2076
|
+
|
|
2077
|
+
impl HreflangEntry {
|
|
2078
|
+
fn new(lang: Option<String>, url: Option<String>) -> Self {
|
|
2079
|
+
Self {
|
|
2080
|
+
lang: lang.unwrap_or_default(),
|
|
2081
|
+
url: url.unwrap_or_default(),
|
|
2082
|
+
}
|
|
2083
|
+
}
|
|
2084
|
+
|
|
2085
|
+
fn lang(&self) -> String {
|
|
2086
|
+
self.lang.clone()
|
|
2087
|
+
}
|
|
2088
|
+
|
|
2089
|
+
fn url(&self) -> String {
|
|
2090
|
+
self.url.clone()
|
|
2091
|
+
}
|
|
2092
|
+
}
|
|
2093
|
+
|
|
2094
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2095
|
+
#[magnus::wrap(class = "Kreuzcrawl::FaviconInfo")]
|
|
2096
|
+
#[serde(default)]
|
|
2097
|
+
pub struct FaviconInfo {
|
|
2098
|
+
pub url: String,
|
|
2099
|
+
pub rel: String,
|
|
2100
|
+
pub sizes: Option<String>,
|
|
2101
|
+
pub mime_type: Option<String>,
|
|
2102
|
+
}
|
|
2103
|
+
|
|
2104
|
+
unsafe impl IntoValueFromNative for FaviconInfo {}
|
|
2105
|
+
|
|
2106
|
+
impl magnus::TryConvert for FaviconInfo {
|
|
2107
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2108
|
+
let r: &FaviconInfo = magnus::TryConvert::try_convert(val)?;
|
|
2109
|
+
Ok(r.clone())
|
|
2110
|
+
}
|
|
2111
|
+
}
|
|
2112
|
+
unsafe impl TryConvertOwned for FaviconInfo {}
|
|
2113
|
+
|
|
2114
|
+
impl Default for FaviconInfo {
|
|
2115
|
+
fn default() -> Self {
|
|
2116
|
+
Self {
|
|
2117
|
+
url: Default::default(),
|
|
2118
|
+
rel: Default::default(),
|
|
2119
|
+
sizes: Default::default(),
|
|
2120
|
+
mime_type: Default::default(),
|
|
2121
|
+
}
|
|
2122
|
+
}
|
|
2123
|
+
}
|
|
2124
|
+
|
|
2125
|
+
impl FaviconInfo {
|
|
2126
|
+
fn new(url: Option<String>, rel: Option<String>, sizes: Option<String>, mime_type: Option<String>) -> Self {
|
|
2127
|
+
Self {
|
|
2128
|
+
url: url.unwrap_or_default(),
|
|
2129
|
+
rel: rel.unwrap_or_default(),
|
|
2130
|
+
sizes,
|
|
2131
|
+
mime_type,
|
|
2132
|
+
}
|
|
2133
|
+
}
|
|
2134
|
+
|
|
2135
|
+
fn url(&self) -> String {
|
|
2136
|
+
self.url.clone()
|
|
2137
|
+
}
|
|
2138
|
+
|
|
2139
|
+
fn rel(&self) -> String {
|
|
2140
|
+
self.rel.clone()
|
|
2141
|
+
}
|
|
2142
|
+
|
|
2143
|
+
fn sizes(&self) -> Option<String> {
|
|
2144
|
+
self.sizes.clone()
|
|
2145
|
+
}
|
|
2146
|
+
|
|
2147
|
+
fn mime_type(&self) -> Option<String> {
|
|
2148
|
+
self.mime_type.clone()
|
|
2149
|
+
}
|
|
2150
|
+
}
|
|
2151
|
+
|
|
2152
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2153
|
+
#[magnus::wrap(class = "Kreuzcrawl::HeadingInfo")]
|
|
2154
|
+
#[serde(default)]
|
|
2155
|
+
pub struct HeadingInfo {
|
|
2156
|
+
pub level: u8,
|
|
2157
|
+
pub text: String,
|
|
2158
|
+
}
|
|
2159
|
+
|
|
2160
|
+
unsafe impl IntoValueFromNative for HeadingInfo {}
|
|
2161
|
+
|
|
2162
|
+
impl magnus::TryConvert for HeadingInfo {
|
|
2163
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2164
|
+
let r: &HeadingInfo = magnus::TryConvert::try_convert(val)?;
|
|
2165
|
+
Ok(r.clone())
|
|
2166
|
+
}
|
|
2167
|
+
}
|
|
2168
|
+
unsafe impl TryConvertOwned for HeadingInfo {}
|
|
2169
|
+
|
|
2170
|
+
impl Default for HeadingInfo {
|
|
2171
|
+
fn default() -> Self {
|
|
2172
|
+
Self {
|
|
2173
|
+
level: Default::default(),
|
|
2174
|
+
text: Default::default(),
|
|
2175
|
+
}
|
|
2176
|
+
}
|
|
2177
|
+
}
|
|
2178
|
+
|
|
2179
|
+
impl HeadingInfo {
|
|
2180
|
+
fn new(level: Option<u8>, text: Option<String>) -> Self {
|
|
2181
|
+
Self {
|
|
2182
|
+
level: level.unwrap_or_default(),
|
|
2183
|
+
text: text.unwrap_or_default(),
|
|
2184
|
+
}
|
|
2185
|
+
}
|
|
2186
|
+
|
|
2187
|
+
fn level(&self) -> u8 {
|
|
2188
|
+
self.level
|
|
2189
|
+
}
|
|
2190
|
+
|
|
2191
|
+
fn text(&self) -> String {
|
|
2192
|
+
self.text.clone()
|
|
2193
|
+
}
|
|
2194
|
+
}
|
|
2195
|
+
|
|
2196
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2197
|
+
#[magnus::wrap(class = "Kreuzcrawl::ResponseMeta")]
|
|
2198
|
+
#[serde(default)]
|
|
2199
|
+
pub struct ResponseMeta {
|
|
2200
|
+
pub etag: Option<String>,
|
|
2201
|
+
pub last_modified: Option<String>,
|
|
2202
|
+
pub cache_control: Option<String>,
|
|
2203
|
+
pub server: Option<String>,
|
|
2204
|
+
pub x_powered_by: Option<String>,
|
|
2205
|
+
pub content_language: Option<String>,
|
|
2206
|
+
pub content_encoding: Option<String>,
|
|
2207
|
+
}
|
|
2208
|
+
|
|
2209
|
+
unsafe impl IntoValueFromNative for ResponseMeta {}
|
|
2210
|
+
|
|
2211
|
+
impl magnus::TryConvert for ResponseMeta {
|
|
2212
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2213
|
+
let r: &ResponseMeta = magnus::TryConvert::try_convert(val)?;
|
|
2214
|
+
Ok(r.clone())
|
|
2215
|
+
}
|
|
2216
|
+
}
|
|
2217
|
+
unsafe impl TryConvertOwned for ResponseMeta {}
|
|
2218
|
+
|
|
2219
|
+
impl Default for ResponseMeta {
|
|
2220
|
+
fn default() -> Self {
|
|
2221
|
+
Self {
|
|
2222
|
+
etag: Default::default(),
|
|
2223
|
+
last_modified: Default::default(),
|
|
2224
|
+
cache_control: Default::default(),
|
|
2225
|
+
server: Default::default(),
|
|
2226
|
+
x_powered_by: Default::default(),
|
|
2227
|
+
content_language: Default::default(),
|
|
2228
|
+
content_encoding: Default::default(),
|
|
2229
|
+
}
|
|
2230
|
+
}
|
|
2231
|
+
}
|
|
2232
|
+
|
|
2233
|
+
impl ResponseMeta {
|
|
2234
|
+
fn new(
|
|
2235
|
+
etag: Option<String>,
|
|
2236
|
+
last_modified: Option<String>,
|
|
2237
|
+
cache_control: Option<String>,
|
|
2238
|
+
server: Option<String>,
|
|
2239
|
+
x_powered_by: Option<String>,
|
|
2240
|
+
content_language: Option<String>,
|
|
2241
|
+
content_encoding: Option<String>,
|
|
2242
|
+
) -> Self {
|
|
2243
|
+
Self {
|
|
2244
|
+
etag,
|
|
2245
|
+
last_modified,
|
|
2246
|
+
cache_control,
|
|
2247
|
+
server,
|
|
2248
|
+
x_powered_by,
|
|
2249
|
+
content_language,
|
|
2250
|
+
content_encoding,
|
|
2251
|
+
}
|
|
2252
|
+
}
|
|
2253
|
+
|
|
2254
|
+
fn etag(&self) -> Option<String> {
|
|
2255
|
+
self.etag.clone()
|
|
2256
|
+
}
|
|
2257
|
+
|
|
2258
|
+
fn last_modified(&self) -> Option<String> {
|
|
2259
|
+
self.last_modified.clone()
|
|
2260
|
+
}
|
|
2261
|
+
|
|
2262
|
+
fn cache_control(&self) -> Option<String> {
|
|
2263
|
+
self.cache_control.clone()
|
|
2264
|
+
}
|
|
2265
|
+
|
|
2266
|
+
fn server(&self) -> Option<String> {
|
|
2267
|
+
self.server.clone()
|
|
2268
|
+
}
|
|
2269
|
+
|
|
2270
|
+
fn x_powered_by(&self) -> Option<String> {
|
|
2271
|
+
self.x_powered_by.clone()
|
|
2272
|
+
}
|
|
2273
|
+
|
|
2274
|
+
fn content_language(&self) -> Option<String> {
|
|
2275
|
+
self.content_language.clone()
|
|
2276
|
+
}
|
|
2277
|
+
|
|
2278
|
+
fn content_encoding(&self) -> Option<String> {
|
|
2279
|
+
self.content_encoding.clone()
|
|
2280
|
+
}
|
|
2281
|
+
}
|
|
2282
|
+
|
|
2283
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2284
|
+
#[magnus::wrap(class = "Kreuzcrawl::PageMetadata")]
|
|
2285
|
+
#[serde(default)]
|
|
2286
|
+
pub struct PageMetadata {
|
|
2287
|
+
pub title: Option<String>,
|
|
2288
|
+
pub description: Option<String>,
|
|
2289
|
+
pub canonical_url: Option<String>,
|
|
2290
|
+
pub keywords: Option<String>,
|
|
2291
|
+
pub author: Option<String>,
|
|
2292
|
+
pub viewport: Option<String>,
|
|
2293
|
+
pub theme_color: Option<String>,
|
|
2294
|
+
pub generator: Option<String>,
|
|
2295
|
+
pub robots: Option<String>,
|
|
2296
|
+
pub html_lang: Option<String>,
|
|
2297
|
+
pub html_dir: Option<String>,
|
|
2298
|
+
pub og_title: Option<String>,
|
|
2299
|
+
pub og_type: Option<String>,
|
|
2300
|
+
pub og_image: Option<String>,
|
|
2301
|
+
pub og_description: Option<String>,
|
|
2302
|
+
pub og_url: Option<String>,
|
|
2303
|
+
pub og_site_name: Option<String>,
|
|
2304
|
+
pub og_locale: Option<String>,
|
|
2305
|
+
pub og_video: Option<String>,
|
|
2306
|
+
pub og_audio: Option<String>,
|
|
2307
|
+
pub og_locale_alternates: Option<Vec<String>>,
|
|
2308
|
+
pub twitter_card: Option<String>,
|
|
2309
|
+
pub twitter_title: Option<String>,
|
|
2310
|
+
pub twitter_description: Option<String>,
|
|
2311
|
+
pub twitter_image: Option<String>,
|
|
2312
|
+
pub twitter_site: Option<String>,
|
|
2313
|
+
pub twitter_creator: Option<String>,
|
|
2314
|
+
pub dc_title: Option<String>,
|
|
2315
|
+
pub dc_creator: Option<String>,
|
|
2316
|
+
pub dc_subject: Option<String>,
|
|
2317
|
+
pub dc_description: Option<String>,
|
|
2318
|
+
pub dc_publisher: Option<String>,
|
|
2319
|
+
pub dc_date: Option<String>,
|
|
2320
|
+
pub dc_type: Option<String>,
|
|
2321
|
+
pub dc_format: Option<String>,
|
|
2322
|
+
pub dc_identifier: Option<String>,
|
|
2323
|
+
pub dc_language: Option<String>,
|
|
2324
|
+
pub dc_rights: Option<String>,
|
|
2325
|
+
pub article: Option<ArticleMetadata>,
|
|
2326
|
+
pub hreflangs: Option<Vec<HreflangEntry>>,
|
|
2327
|
+
pub favicons: Option<Vec<FaviconInfo>>,
|
|
2328
|
+
pub headings: Option<Vec<HeadingInfo>>,
|
|
2329
|
+
pub word_count: Option<usize>,
|
|
2330
|
+
}
|
|
2331
|
+
|
|
2332
|
+
unsafe impl IntoValueFromNative for PageMetadata {}
|
|
2333
|
+
|
|
2334
|
+
impl magnus::TryConvert for PageMetadata {
|
|
2335
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2336
|
+
let r: &PageMetadata = magnus::TryConvert::try_convert(val)?;
|
|
2337
|
+
Ok(r.clone())
|
|
2338
|
+
}
|
|
2339
|
+
}
|
|
2340
|
+
unsafe impl TryConvertOwned for PageMetadata {}
|
|
2341
|
+
|
|
2342
|
+
impl Default for PageMetadata {
|
|
2343
|
+
fn default() -> Self {
|
|
2344
|
+
Self {
|
|
2345
|
+
title: Default::default(),
|
|
2346
|
+
description: Default::default(),
|
|
2347
|
+
canonical_url: Default::default(),
|
|
2348
|
+
keywords: Default::default(),
|
|
2349
|
+
author: Default::default(),
|
|
2350
|
+
viewport: Default::default(),
|
|
2351
|
+
theme_color: Default::default(),
|
|
2352
|
+
generator: Default::default(),
|
|
2353
|
+
robots: Default::default(),
|
|
2354
|
+
html_lang: Default::default(),
|
|
2355
|
+
html_dir: Default::default(),
|
|
2356
|
+
og_title: Default::default(),
|
|
2357
|
+
og_type: Default::default(),
|
|
2358
|
+
og_image: Default::default(),
|
|
2359
|
+
og_description: Default::default(),
|
|
2360
|
+
og_url: Default::default(),
|
|
2361
|
+
og_site_name: Default::default(),
|
|
2362
|
+
og_locale: Default::default(),
|
|
2363
|
+
og_video: Default::default(),
|
|
2364
|
+
og_audio: Default::default(),
|
|
2365
|
+
og_locale_alternates: Default::default(),
|
|
2366
|
+
twitter_card: Default::default(),
|
|
2367
|
+
twitter_title: Default::default(),
|
|
2368
|
+
twitter_description: Default::default(),
|
|
2369
|
+
twitter_image: Default::default(),
|
|
2370
|
+
twitter_site: Default::default(),
|
|
2371
|
+
twitter_creator: Default::default(),
|
|
2372
|
+
dc_title: Default::default(),
|
|
2373
|
+
dc_creator: Default::default(),
|
|
2374
|
+
dc_subject: Default::default(),
|
|
2375
|
+
dc_description: Default::default(),
|
|
2376
|
+
dc_publisher: Default::default(),
|
|
2377
|
+
dc_date: Default::default(),
|
|
2378
|
+
dc_type: Default::default(),
|
|
2379
|
+
dc_format: Default::default(),
|
|
2380
|
+
dc_identifier: Default::default(),
|
|
2381
|
+
dc_language: Default::default(),
|
|
2382
|
+
dc_rights: Default::default(),
|
|
2383
|
+
article: Default::default(),
|
|
2384
|
+
hreflangs: Default::default(),
|
|
2385
|
+
favicons: Default::default(),
|
|
2386
|
+
headings: Default::default(),
|
|
2387
|
+
word_count: Default::default(),
|
|
2388
|
+
}
|
|
2389
|
+
}
|
|
2390
|
+
}
|
|
2391
|
+
|
|
2392
|
+
impl PageMetadata {
|
|
2393
|
+
fn new(kwargs: magnus::RHash) -> Result<Self, magnus::Error> {
|
|
2394
|
+
let ruby = unsafe { magnus::Ruby::get_unchecked() };
|
|
2395
|
+
Ok(Self {
|
|
2396
|
+
title: kwargs
|
|
2397
|
+
.get(ruby.to_symbol("title"))
|
|
2398
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2399
|
+
description: kwargs
|
|
2400
|
+
.get(ruby.to_symbol("description"))
|
|
2401
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2402
|
+
canonical_url: kwargs
|
|
2403
|
+
.get(ruby.to_symbol("canonical_url"))
|
|
2404
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2405
|
+
keywords: kwargs
|
|
2406
|
+
.get(ruby.to_symbol("keywords"))
|
|
2407
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2408
|
+
author: kwargs
|
|
2409
|
+
.get(ruby.to_symbol("author"))
|
|
2410
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2411
|
+
viewport: kwargs
|
|
2412
|
+
.get(ruby.to_symbol("viewport"))
|
|
2413
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2414
|
+
theme_color: kwargs
|
|
2415
|
+
.get(ruby.to_symbol("theme_color"))
|
|
2416
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2417
|
+
generator: kwargs
|
|
2418
|
+
.get(ruby.to_symbol("generator"))
|
|
2419
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2420
|
+
robots: kwargs
|
|
2421
|
+
.get(ruby.to_symbol("robots"))
|
|
2422
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2423
|
+
html_lang: kwargs
|
|
2424
|
+
.get(ruby.to_symbol("html_lang"))
|
|
2425
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2426
|
+
html_dir: kwargs
|
|
2427
|
+
.get(ruby.to_symbol("html_dir"))
|
|
2428
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2429
|
+
og_title: kwargs
|
|
2430
|
+
.get(ruby.to_symbol("og_title"))
|
|
2431
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2432
|
+
og_type: kwargs
|
|
2433
|
+
.get(ruby.to_symbol("og_type"))
|
|
2434
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2435
|
+
og_image: kwargs
|
|
2436
|
+
.get(ruby.to_symbol("og_image"))
|
|
2437
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2438
|
+
og_description: kwargs
|
|
2439
|
+
.get(ruby.to_symbol("og_description"))
|
|
2440
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2441
|
+
og_url: kwargs
|
|
2442
|
+
.get(ruby.to_symbol("og_url"))
|
|
2443
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2444
|
+
og_site_name: kwargs
|
|
2445
|
+
.get(ruby.to_symbol("og_site_name"))
|
|
2446
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2447
|
+
og_locale: kwargs
|
|
2448
|
+
.get(ruby.to_symbol("og_locale"))
|
|
2449
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2450
|
+
og_video: kwargs
|
|
2451
|
+
.get(ruby.to_symbol("og_video"))
|
|
2452
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2453
|
+
og_audio: kwargs
|
|
2454
|
+
.get(ruby.to_symbol("og_audio"))
|
|
2455
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2456
|
+
og_locale_alternates: kwargs
|
|
2457
|
+
.get(ruby.to_symbol("og_locale_alternates"))
|
|
2458
|
+
.and_then(|v| <Vec<String>>::try_convert(v).ok()),
|
|
2459
|
+
twitter_card: kwargs
|
|
2460
|
+
.get(ruby.to_symbol("twitter_card"))
|
|
2461
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2462
|
+
twitter_title: kwargs
|
|
2463
|
+
.get(ruby.to_symbol("twitter_title"))
|
|
2464
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2465
|
+
twitter_description: kwargs
|
|
2466
|
+
.get(ruby.to_symbol("twitter_description"))
|
|
2467
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2468
|
+
twitter_image: kwargs
|
|
2469
|
+
.get(ruby.to_symbol("twitter_image"))
|
|
2470
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2471
|
+
twitter_site: kwargs
|
|
2472
|
+
.get(ruby.to_symbol("twitter_site"))
|
|
2473
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2474
|
+
twitter_creator: kwargs
|
|
2475
|
+
.get(ruby.to_symbol("twitter_creator"))
|
|
2476
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2477
|
+
dc_title: kwargs
|
|
2478
|
+
.get(ruby.to_symbol("dc_title"))
|
|
2479
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2480
|
+
dc_creator: kwargs
|
|
2481
|
+
.get(ruby.to_symbol("dc_creator"))
|
|
2482
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2483
|
+
dc_subject: kwargs
|
|
2484
|
+
.get(ruby.to_symbol("dc_subject"))
|
|
2485
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2486
|
+
dc_description: kwargs
|
|
2487
|
+
.get(ruby.to_symbol("dc_description"))
|
|
2488
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2489
|
+
dc_publisher: kwargs
|
|
2490
|
+
.get(ruby.to_symbol("dc_publisher"))
|
|
2491
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2492
|
+
dc_date: kwargs
|
|
2493
|
+
.get(ruby.to_symbol("dc_date"))
|
|
2494
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2495
|
+
dc_type: kwargs
|
|
2496
|
+
.get(ruby.to_symbol("dc_type"))
|
|
2497
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2498
|
+
dc_format: kwargs
|
|
2499
|
+
.get(ruby.to_symbol("dc_format"))
|
|
2500
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2501
|
+
dc_identifier: kwargs
|
|
2502
|
+
.get(ruby.to_symbol("dc_identifier"))
|
|
2503
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2504
|
+
dc_language: kwargs
|
|
2505
|
+
.get(ruby.to_symbol("dc_language"))
|
|
2506
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2507
|
+
dc_rights: kwargs
|
|
2508
|
+
.get(ruby.to_symbol("dc_rights"))
|
|
2509
|
+
.and_then(|v| String::try_convert(v).ok()),
|
|
2510
|
+
article: kwargs
|
|
2511
|
+
.get(ruby.to_symbol("article"))
|
|
2512
|
+
.and_then(|v| ArticleMetadata::try_convert(v).ok()),
|
|
2513
|
+
hreflangs: kwargs
|
|
2514
|
+
.get(ruby.to_symbol("hreflangs"))
|
|
2515
|
+
.and_then(|v| <Vec<HreflangEntry>>::try_convert(v).ok()),
|
|
2516
|
+
favicons: kwargs
|
|
2517
|
+
.get(ruby.to_symbol("favicons"))
|
|
2518
|
+
.and_then(|v| <Vec<FaviconInfo>>::try_convert(v).ok()),
|
|
2519
|
+
headings: kwargs
|
|
2520
|
+
.get(ruby.to_symbol("headings"))
|
|
2521
|
+
.and_then(|v| <Vec<HeadingInfo>>::try_convert(v).ok()),
|
|
2522
|
+
word_count: kwargs
|
|
2523
|
+
.get(ruby.to_symbol("word_count"))
|
|
2524
|
+
.and_then(|v| usize::try_convert(v).ok()),
|
|
2525
|
+
})
|
|
2526
|
+
}
|
|
2527
|
+
|
|
2528
|
+
fn title(&self) -> Option<String> {
|
|
2529
|
+
self.title.clone()
|
|
2530
|
+
}
|
|
2531
|
+
|
|
2532
|
+
fn description(&self) -> Option<String> {
|
|
2533
|
+
self.description.clone()
|
|
2534
|
+
}
|
|
2535
|
+
|
|
2536
|
+
fn canonical_url(&self) -> Option<String> {
|
|
2537
|
+
self.canonical_url.clone()
|
|
2538
|
+
}
|
|
2539
|
+
|
|
2540
|
+
fn keywords(&self) -> Option<String> {
|
|
2541
|
+
self.keywords.clone()
|
|
2542
|
+
}
|
|
2543
|
+
|
|
2544
|
+
fn author(&self) -> Option<String> {
|
|
2545
|
+
self.author.clone()
|
|
2546
|
+
}
|
|
2547
|
+
|
|
2548
|
+
fn viewport(&self) -> Option<String> {
|
|
2549
|
+
self.viewport.clone()
|
|
2550
|
+
}
|
|
2551
|
+
|
|
2552
|
+
fn theme_color(&self) -> Option<String> {
|
|
2553
|
+
self.theme_color.clone()
|
|
2554
|
+
}
|
|
2555
|
+
|
|
2556
|
+
fn generator(&self) -> Option<String> {
|
|
2557
|
+
self.generator.clone()
|
|
2558
|
+
}
|
|
2559
|
+
|
|
2560
|
+
fn robots(&self) -> Option<String> {
|
|
2561
|
+
self.robots.clone()
|
|
2562
|
+
}
|
|
2563
|
+
|
|
2564
|
+
fn html_lang(&self) -> Option<String> {
|
|
2565
|
+
self.html_lang.clone()
|
|
2566
|
+
}
|
|
2567
|
+
|
|
2568
|
+
fn html_dir(&self) -> Option<String> {
|
|
2569
|
+
self.html_dir.clone()
|
|
2570
|
+
}
|
|
2571
|
+
|
|
2572
|
+
fn og_title(&self) -> Option<String> {
|
|
2573
|
+
self.og_title.clone()
|
|
2574
|
+
}
|
|
2575
|
+
|
|
2576
|
+
fn og_type(&self) -> Option<String> {
|
|
2577
|
+
self.og_type.clone()
|
|
2578
|
+
}
|
|
2579
|
+
|
|
2580
|
+
fn og_image(&self) -> Option<String> {
|
|
2581
|
+
self.og_image.clone()
|
|
2582
|
+
}
|
|
2583
|
+
|
|
2584
|
+
fn og_description(&self) -> Option<String> {
|
|
2585
|
+
self.og_description.clone()
|
|
2586
|
+
}
|
|
2587
|
+
|
|
2588
|
+
fn og_url(&self) -> Option<String> {
|
|
2589
|
+
self.og_url.clone()
|
|
2590
|
+
}
|
|
2591
|
+
|
|
2592
|
+
fn og_site_name(&self) -> Option<String> {
|
|
2593
|
+
self.og_site_name.clone()
|
|
2594
|
+
}
|
|
2595
|
+
|
|
2596
|
+
fn og_locale(&self) -> Option<String> {
|
|
2597
|
+
self.og_locale.clone()
|
|
2598
|
+
}
|
|
2599
|
+
|
|
2600
|
+
fn og_video(&self) -> Option<String> {
|
|
2601
|
+
self.og_video.clone()
|
|
2602
|
+
}
|
|
2603
|
+
|
|
2604
|
+
fn og_audio(&self) -> Option<String> {
|
|
2605
|
+
self.og_audio.clone()
|
|
2606
|
+
}
|
|
2607
|
+
|
|
2608
|
+
fn og_locale_alternates(&self) -> Option<Vec<String>> {
|
|
2609
|
+
self.og_locale_alternates.clone()
|
|
2610
|
+
}
|
|
2611
|
+
|
|
2612
|
+
fn twitter_card(&self) -> Option<String> {
|
|
2613
|
+
self.twitter_card.clone()
|
|
2614
|
+
}
|
|
2615
|
+
|
|
2616
|
+
fn twitter_title(&self) -> Option<String> {
|
|
2617
|
+
self.twitter_title.clone()
|
|
2618
|
+
}
|
|
2619
|
+
|
|
2620
|
+
fn twitter_description(&self) -> Option<String> {
|
|
2621
|
+
self.twitter_description.clone()
|
|
2622
|
+
}
|
|
2623
|
+
|
|
2624
|
+
fn twitter_image(&self) -> Option<String> {
|
|
2625
|
+
self.twitter_image.clone()
|
|
2626
|
+
}
|
|
2627
|
+
|
|
2628
|
+
fn twitter_site(&self) -> Option<String> {
|
|
2629
|
+
self.twitter_site.clone()
|
|
2630
|
+
}
|
|
2631
|
+
|
|
2632
|
+
fn twitter_creator(&self) -> Option<String> {
|
|
2633
|
+
self.twitter_creator.clone()
|
|
2634
|
+
}
|
|
2635
|
+
|
|
2636
|
+
fn dc_title(&self) -> Option<String> {
|
|
2637
|
+
self.dc_title.clone()
|
|
2638
|
+
}
|
|
2639
|
+
|
|
2640
|
+
fn dc_creator(&self) -> Option<String> {
|
|
2641
|
+
self.dc_creator.clone()
|
|
2642
|
+
}
|
|
2643
|
+
|
|
2644
|
+
fn dc_subject(&self) -> Option<String> {
|
|
2645
|
+
self.dc_subject.clone()
|
|
2646
|
+
}
|
|
2647
|
+
|
|
2648
|
+
fn dc_description(&self) -> Option<String> {
|
|
2649
|
+
self.dc_description.clone()
|
|
2650
|
+
}
|
|
2651
|
+
|
|
2652
|
+
fn dc_publisher(&self) -> Option<String> {
|
|
2653
|
+
self.dc_publisher.clone()
|
|
2654
|
+
}
|
|
2655
|
+
|
|
2656
|
+
fn dc_date(&self) -> Option<String> {
|
|
2657
|
+
self.dc_date.clone()
|
|
2658
|
+
}
|
|
2659
|
+
|
|
2660
|
+
fn dc_type(&self) -> Option<String> {
|
|
2661
|
+
self.dc_type.clone()
|
|
2662
|
+
}
|
|
2663
|
+
|
|
2664
|
+
fn dc_format(&self) -> Option<String> {
|
|
2665
|
+
self.dc_format.clone()
|
|
2666
|
+
}
|
|
2667
|
+
|
|
2668
|
+
fn dc_identifier(&self) -> Option<String> {
|
|
2669
|
+
self.dc_identifier.clone()
|
|
2670
|
+
}
|
|
2671
|
+
|
|
2672
|
+
fn dc_language(&self) -> Option<String> {
|
|
2673
|
+
self.dc_language.clone()
|
|
2674
|
+
}
|
|
2675
|
+
|
|
2676
|
+
fn dc_rights(&self) -> Option<String> {
|
|
2677
|
+
self.dc_rights.clone()
|
|
2678
|
+
}
|
|
2679
|
+
|
|
2680
|
+
fn article(&self) -> Option<ArticleMetadata> {
|
|
2681
|
+
self.article.clone()
|
|
2682
|
+
}
|
|
2683
|
+
|
|
2684
|
+
fn hreflangs(&self) -> Option<Vec<HreflangEntry>> {
|
|
2685
|
+
self.hreflangs.clone()
|
|
2686
|
+
}
|
|
2687
|
+
|
|
2688
|
+
fn favicons(&self) -> Option<Vec<FaviconInfo>> {
|
|
2689
|
+
self.favicons.clone()
|
|
2690
|
+
}
|
|
2691
|
+
|
|
2692
|
+
fn headings(&self) -> Option<Vec<HeadingInfo>> {
|
|
2693
|
+
self.headings.clone()
|
|
2694
|
+
}
|
|
2695
|
+
|
|
2696
|
+
fn word_count(&self) -> Option<usize> {
|
|
2697
|
+
self.word_count
|
|
2698
|
+
}
|
|
2699
|
+
}
|
|
2700
|
+
|
|
2701
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2702
|
+
#[magnus::wrap(class = "Kreuzcrawl::CitationResult")]
|
|
2703
|
+
#[serde(default)]
|
|
2704
|
+
pub struct CitationResult {
|
|
2705
|
+
pub content: String,
|
|
2706
|
+
pub references: Vec<CitationReference>,
|
|
2707
|
+
}
|
|
2708
|
+
|
|
2709
|
+
unsafe impl IntoValueFromNative for CitationResult {}
|
|
2710
|
+
|
|
2711
|
+
impl magnus::TryConvert for CitationResult {
|
|
2712
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2713
|
+
let r: &CitationResult = magnus::TryConvert::try_convert(val)?;
|
|
2714
|
+
Ok(r.clone())
|
|
2715
|
+
}
|
|
2716
|
+
}
|
|
2717
|
+
unsafe impl TryConvertOwned for CitationResult {}
|
|
2718
|
+
|
|
2719
|
+
impl Default for CitationResult {
|
|
2720
|
+
fn default() -> Self {
|
|
2721
|
+
Self {
|
|
2722
|
+
content: Default::default(),
|
|
2723
|
+
references: Default::default(),
|
|
2724
|
+
}
|
|
2725
|
+
}
|
|
2726
|
+
}
|
|
2727
|
+
|
|
2728
|
+
impl CitationResult {
|
|
2729
|
+
fn new(content: Option<String>, references: Option<Vec<CitationReference>>) -> Self {
|
|
2730
|
+
Self {
|
|
2731
|
+
content: content.unwrap_or_default(),
|
|
2732
|
+
references: references.unwrap_or_default(),
|
|
2733
|
+
}
|
|
2734
|
+
}
|
|
2735
|
+
|
|
2736
|
+
fn content(&self) -> String {
|
|
2737
|
+
self.content.clone()
|
|
2738
|
+
}
|
|
2739
|
+
|
|
2740
|
+
fn references(&self) -> Vec<CitationReference> {
|
|
2741
|
+
self.references.clone()
|
|
2742
|
+
}
|
|
2743
|
+
}
|
|
2744
|
+
|
|
2745
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2746
|
+
#[magnus::wrap(class = "Kreuzcrawl::CitationReference")]
|
|
2747
|
+
#[serde(default)]
|
|
2748
|
+
pub struct CitationReference {
|
|
2749
|
+
pub index: usize,
|
|
2750
|
+
pub url: String,
|
|
2751
|
+
pub text: String,
|
|
2752
|
+
}
|
|
2753
|
+
|
|
2754
|
+
unsafe impl IntoValueFromNative for CitationReference {}
|
|
2755
|
+
|
|
2756
|
+
impl magnus::TryConvert for CitationReference {
|
|
2757
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2758
|
+
let r: &CitationReference = magnus::TryConvert::try_convert(val)?;
|
|
2759
|
+
Ok(r.clone())
|
|
2760
|
+
}
|
|
2761
|
+
}
|
|
2762
|
+
unsafe impl TryConvertOwned for CitationReference {}
|
|
2763
|
+
|
|
2764
|
+
impl Default for CitationReference {
|
|
2765
|
+
fn default() -> Self {
|
|
2766
|
+
Self {
|
|
2767
|
+
index: Default::default(),
|
|
2768
|
+
url: Default::default(),
|
|
2769
|
+
text: Default::default(),
|
|
2770
|
+
}
|
|
2771
|
+
}
|
|
2772
|
+
}
|
|
2773
|
+
|
|
2774
|
+
impl CitationReference {
|
|
2775
|
+
fn new(index: Option<usize>, url: Option<String>, text: Option<String>) -> Self {
|
|
2776
|
+
Self {
|
|
2777
|
+
index: index.unwrap_or_default(),
|
|
2778
|
+
url: url.unwrap_or_default(),
|
|
2779
|
+
text: text.unwrap_or_default(),
|
|
2780
|
+
}
|
|
2781
|
+
}
|
|
2782
|
+
|
|
2783
|
+
fn index(&self) -> usize {
|
|
2784
|
+
self.index
|
|
2785
|
+
}
|
|
2786
|
+
|
|
2787
|
+
fn url(&self) -> String {
|
|
2788
|
+
self.url.clone()
|
|
2789
|
+
}
|
|
2790
|
+
|
|
2791
|
+
fn text(&self) -> String {
|
|
2792
|
+
self.text.clone()
|
|
2793
|
+
}
|
|
2794
|
+
}
|
|
2795
|
+
|
|
2796
|
+
#[derive(Clone)]
|
|
2797
|
+
#[magnus::wrap(class = "Kreuzcrawl::CrawlEngineHandle")]
|
|
2798
|
+
pub struct CrawlEngineHandle {
|
|
2799
|
+
inner: Arc<kreuzcrawl::CrawlEngineHandle>,
|
|
2800
|
+
}
|
|
2801
|
+
|
|
2802
|
+
unsafe impl IntoValueFromNative for CrawlEngineHandle {}
|
|
2803
|
+
|
|
2804
|
+
impl magnus::TryConvert for CrawlEngineHandle {
|
|
2805
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2806
|
+
let r: &CrawlEngineHandle = magnus::TryConvert::try_convert(val)?;
|
|
2807
|
+
Ok(r.clone())
|
|
2808
|
+
}
|
|
2809
|
+
}
|
|
2810
|
+
unsafe impl TryConvertOwned for CrawlEngineHandle {}
|
|
2811
|
+
|
|
2812
|
+
impl CrawlEngineHandle {}
|
|
2813
|
+
|
|
2814
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2815
|
+
#[magnus::wrap(class = "Kreuzcrawl::BatchScrapeResult")]
|
|
2816
|
+
#[serde(default)]
|
|
2817
|
+
pub struct BatchScrapeResult {
|
|
2818
|
+
pub url: String,
|
|
2819
|
+
pub result: Option<ScrapeResult>,
|
|
2820
|
+
pub error: Option<String>,
|
|
2821
|
+
}
|
|
2822
|
+
|
|
2823
|
+
unsafe impl IntoValueFromNative for BatchScrapeResult {}
|
|
2824
|
+
|
|
2825
|
+
impl magnus::TryConvert for BatchScrapeResult {
|
|
2826
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2827
|
+
let r: &BatchScrapeResult = magnus::TryConvert::try_convert(val)?;
|
|
2828
|
+
Ok(r.clone())
|
|
2829
|
+
}
|
|
2830
|
+
}
|
|
2831
|
+
unsafe impl TryConvertOwned for BatchScrapeResult {}
|
|
2832
|
+
|
|
2833
|
+
impl Default for BatchScrapeResult {
|
|
2834
|
+
fn default() -> Self {
|
|
2835
|
+
Self {
|
|
2836
|
+
url: Default::default(),
|
|
2837
|
+
result: Default::default(),
|
|
2838
|
+
error: Default::default(),
|
|
2839
|
+
}
|
|
2840
|
+
}
|
|
2841
|
+
}
|
|
2842
|
+
|
|
2843
|
+
impl BatchScrapeResult {
|
|
2844
|
+
fn new(url: Option<String>, result: Option<ScrapeResult>, error: Option<String>) -> Self {
|
|
2845
|
+
Self {
|
|
2846
|
+
url: url.unwrap_or_default(),
|
|
2847
|
+
result,
|
|
2848
|
+
error,
|
|
2849
|
+
}
|
|
2850
|
+
}
|
|
2851
|
+
|
|
2852
|
+
fn url(&self) -> String {
|
|
2853
|
+
self.url.clone()
|
|
2854
|
+
}
|
|
2855
|
+
|
|
2856
|
+
fn result(&self) -> Option<ScrapeResult> {
|
|
2857
|
+
self.result.clone()
|
|
2858
|
+
}
|
|
2859
|
+
|
|
2860
|
+
fn error(&self) -> Option<String> {
|
|
2861
|
+
self.error.clone()
|
|
2862
|
+
}
|
|
2863
|
+
}
|
|
2864
|
+
|
|
2865
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
2866
|
+
#[magnus::wrap(class = "Kreuzcrawl::BatchCrawlResult")]
|
|
2867
|
+
#[serde(default)]
|
|
2868
|
+
pub struct BatchCrawlResult {
|
|
2869
|
+
pub url: String,
|
|
2870
|
+
pub result: Option<CrawlResult>,
|
|
2871
|
+
pub error: Option<String>,
|
|
2872
|
+
}
|
|
2873
|
+
|
|
2874
|
+
unsafe impl IntoValueFromNative for BatchCrawlResult {}
|
|
2875
|
+
|
|
2876
|
+
impl magnus::TryConvert for BatchCrawlResult {
|
|
2877
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2878
|
+
let r: &BatchCrawlResult = magnus::TryConvert::try_convert(val)?;
|
|
2879
|
+
Ok(r.clone())
|
|
2880
|
+
}
|
|
2881
|
+
}
|
|
2882
|
+
unsafe impl TryConvertOwned for BatchCrawlResult {}
|
|
2883
|
+
|
|
2884
|
+
impl Default for BatchCrawlResult {
|
|
2885
|
+
fn default() -> Self {
|
|
2886
|
+
Self {
|
|
2887
|
+
url: Default::default(),
|
|
2888
|
+
result: Default::default(),
|
|
2889
|
+
error: Default::default(),
|
|
2890
|
+
}
|
|
2891
|
+
}
|
|
2892
|
+
}
|
|
2893
|
+
|
|
2894
|
+
impl BatchCrawlResult {
|
|
2895
|
+
fn new(url: Option<String>, result: Option<CrawlResult>, error: Option<String>) -> Self {
|
|
2896
|
+
Self {
|
|
2897
|
+
url: url.unwrap_or_default(),
|
|
2898
|
+
result,
|
|
2899
|
+
error,
|
|
2900
|
+
}
|
|
2901
|
+
}
|
|
2902
|
+
|
|
2903
|
+
fn url(&self) -> String {
|
|
2904
|
+
self.url.clone()
|
|
2905
|
+
}
|
|
2906
|
+
|
|
2907
|
+
fn result(&self) -> Option<CrawlResult> {
|
|
2908
|
+
self.result.clone()
|
|
2909
|
+
}
|
|
2910
|
+
|
|
2911
|
+
fn error(&self) -> Option<String> {
|
|
2912
|
+
self.error.clone()
|
|
2913
|
+
}
|
|
2914
|
+
}
|
|
2915
|
+
|
|
2916
|
+
#[derive(Clone, Copy, PartialEq, Eq, Debug, serde::Serialize, serde::Deserialize)]
|
|
2917
|
+
pub enum BrowserMode {
|
|
2918
|
+
Auto,
|
|
2919
|
+
Always,
|
|
2920
|
+
Never,
|
|
2921
|
+
}
|
|
2922
|
+
|
|
2923
|
+
impl Default for BrowserMode {
|
|
2924
|
+
fn default() -> Self {
|
|
2925
|
+
Self::Auto
|
|
2926
|
+
}
|
|
2927
|
+
}
|
|
2928
|
+
|
|
2929
|
+
impl magnus::IntoValue for BrowserMode {
|
|
2930
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
2931
|
+
let sym = match self {
|
|
2932
|
+
BrowserMode::Auto => "auto",
|
|
2933
|
+
BrowserMode::Always => "always",
|
|
2934
|
+
BrowserMode::Never => "never",
|
|
2935
|
+
};
|
|
2936
|
+
handle.to_symbol(sym).into_value_with(handle)
|
|
2937
|
+
}
|
|
2938
|
+
}
|
|
2939
|
+
|
|
2940
|
+
impl magnus::TryConvert for BrowserMode {
|
|
2941
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2942
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
2943
|
+
match s.as_str() {
|
|
2944
|
+
"auto" => Ok(BrowserMode::Auto),
|
|
2945
|
+
"always" => Ok(BrowserMode::Always),
|
|
2946
|
+
"never" => Ok(BrowserMode::Never),
|
|
2947
|
+
other => Err(magnus::Error::new(
|
|
2948
|
+
unsafe { Ruby::get_unchecked() }.exception_arg_error(),
|
|
2949
|
+
format!("invalid BrowserMode value: {other}"),
|
|
2950
|
+
)),
|
|
2951
|
+
}
|
|
2952
|
+
}
|
|
2953
|
+
}
|
|
2954
|
+
|
|
2955
|
+
unsafe impl IntoValueFromNative for BrowserMode {}
|
|
2956
|
+
unsafe impl TryConvertOwned for BrowserMode {}
|
|
2957
|
+
|
|
2958
|
+
#[derive(Clone, Copy, PartialEq, Eq, Debug, serde::Serialize, serde::Deserialize)]
|
|
2959
|
+
pub enum BrowserWait {
|
|
2960
|
+
NetworkIdle,
|
|
2961
|
+
Selector,
|
|
2962
|
+
Fixed,
|
|
2963
|
+
}
|
|
2964
|
+
|
|
2965
|
+
impl Default for BrowserWait {
|
|
2966
|
+
fn default() -> Self {
|
|
2967
|
+
Self::NetworkIdle
|
|
2968
|
+
}
|
|
2969
|
+
}
|
|
2970
|
+
|
|
2971
|
+
impl magnus::IntoValue for BrowserWait {
|
|
2972
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
2973
|
+
let sym = match self {
|
|
2974
|
+
BrowserWait::NetworkIdle => "network_idle",
|
|
2975
|
+
BrowserWait::Selector => "selector",
|
|
2976
|
+
BrowserWait::Fixed => "fixed",
|
|
2977
|
+
};
|
|
2978
|
+
handle.to_symbol(sym).into_value_with(handle)
|
|
2979
|
+
}
|
|
2980
|
+
}
|
|
2981
|
+
|
|
2982
|
+
impl magnus::TryConvert for BrowserWait {
|
|
2983
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
2984
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
2985
|
+
match s.as_str() {
|
|
2986
|
+
"network_idle" => Ok(BrowserWait::NetworkIdle),
|
|
2987
|
+
"selector" => Ok(BrowserWait::Selector),
|
|
2988
|
+
"fixed" => Ok(BrowserWait::Fixed),
|
|
2989
|
+
other => Err(magnus::Error::new(
|
|
2990
|
+
unsafe { Ruby::get_unchecked() }.exception_arg_error(),
|
|
2991
|
+
format!("invalid BrowserWait value: {other}"),
|
|
2992
|
+
)),
|
|
2993
|
+
}
|
|
2994
|
+
}
|
|
2995
|
+
}
|
|
2996
|
+
|
|
2997
|
+
unsafe impl IntoValueFromNative for BrowserWait {}
|
|
2998
|
+
unsafe impl TryConvertOwned for BrowserWait {}
|
|
2999
|
+
|
|
3000
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
3001
|
+
#[serde(tag = "type")]
|
|
3002
|
+
pub enum AuthConfig {
|
|
3003
|
+
#[serde(rename = "basic")]
|
|
3004
|
+
Basic { username: String, password: String },
|
|
3005
|
+
#[serde(rename = "bearer")]
|
|
3006
|
+
Bearer { token: String },
|
|
3007
|
+
#[serde(rename = "header")]
|
|
3008
|
+
Header { name: String, value: String },
|
|
3009
|
+
}
|
|
3010
|
+
|
|
3011
|
+
impl Default for AuthConfig {
|
|
3012
|
+
fn default() -> Self {
|
|
3013
|
+
Self::Basic {
|
|
3014
|
+
username: Default::default(),
|
|
3015
|
+
password: Default::default(),
|
|
3016
|
+
}
|
|
3017
|
+
}
|
|
3018
|
+
}
|
|
3019
|
+
|
|
3020
|
+
impl magnus::IntoValue for AuthConfig {
|
|
3021
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
3022
|
+
match serde_json::to_value(&self) {
|
|
3023
|
+
Ok(v) => json_to_ruby(handle, v),
|
|
3024
|
+
Err(_) => handle.qnil().into_value_with(handle),
|
|
3025
|
+
}
|
|
3026
|
+
}
|
|
3027
|
+
}
|
|
3028
|
+
|
|
3029
|
+
impl magnus::TryConvert for AuthConfig {
|
|
3030
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
3031
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
3032
|
+
serde_json::from_str(&s)
|
|
3033
|
+
.map_err(|e| magnus::Error::new(unsafe { Ruby::get_unchecked() }.exception_type_error(), e.to_string()))
|
|
3034
|
+
}
|
|
3035
|
+
}
|
|
3036
|
+
|
|
3037
|
+
unsafe impl IntoValueFromNative for AuthConfig {}
|
|
3038
|
+
unsafe impl TryConvertOwned for AuthConfig {}
|
|
3039
|
+
|
|
3040
|
+
#[derive(Clone, Copy, PartialEq, Eq, Debug, serde::Serialize, serde::Deserialize)]
|
|
3041
|
+
pub enum LinkType {
|
|
3042
|
+
Internal,
|
|
3043
|
+
External,
|
|
3044
|
+
Anchor,
|
|
3045
|
+
Document,
|
|
3046
|
+
}
|
|
3047
|
+
|
|
3048
|
+
impl Default for LinkType {
|
|
3049
|
+
fn default() -> Self {
|
|
3050
|
+
Self::Internal
|
|
3051
|
+
}
|
|
3052
|
+
}
|
|
3053
|
+
|
|
3054
|
+
impl magnus::IntoValue for LinkType {
|
|
3055
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
3056
|
+
let sym = match self {
|
|
3057
|
+
LinkType::Internal => "internal",
|
|
3058
|
+
LinkType::External => "external",
|
|
3059
|
+
LinkType::Anchor => "anchor",
|
|
3060
|
+
LinkType::Document => "document",
|
|
3061
|
+
};
|
|
3062
|
+
handle.to_symbol(sym).into_value_with(handle)
|
|
3063
|
+
}
|
|
3064
|
+
}
|
|
3065
|
+
|
|
3066
|
+
impl magnus::TryConvert for LinkType {
|
|
3067
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
3068
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
3069
|
+
match s.as_str() {
|
|
3070
|
+
"internal" => Ok(LinkType::Internal),
|
|
3071
|
+
"external" => Ok(LinkType::External),
|
|
3072
|
+
"anchor" => Ok(LinkType::Anchor),
|
|
3073
|
+
"document" => Ok(LinkType::Document),
|
|
3074
|
+
other => Err(magnus::Error::new(
|
|
3075
|
+
unsafe { Ruby::get_unchecked() }.exception_arg_error(),
|
|
3076
|
+
format!("invalid LinkType value: {other}"),
|
|
3077
|
+
)),
|
|
3078
|
+
}
|
|
3079
|
+
}
|
|
3080
|
+
}
|
|
3081
|
+
|
|
3082
|
+
unsafe impl IntoValueFromNative for LinkType {}
|
|
3083
|
+
unsafe impl TryConvertOwned for LinkType {}
|
|
3084
|
+
|
|
3085
|
+
#[derive(Clone, Copy, PartialEq, Eq, Debug, serde::Serialize, serde::Deserialize)]
|
|
3086
|
+
pub enum ImageSource {
|
|
3087
|
+
Img,
|
|
3088
|
+
PictureSource,
|
|
3089
|
+
#[serde(rename = "og:image")]
|
|
3090
|
+
OgImage,
|
|
3091
|
+
#[serde(rename = "twitter:image")]
|
|
3092
|
+
TwitterImage,
|
|
3093
|
+
}
|
|
3094
|
+
|
|
3095
|
+
impl Default for ImageSource {
|
|
3096
|
+
fn default() -> Self {
|
|
3097
|
+
Self::Img
|
|
3098
|
+
}
|
|
3099
|
+
}
|
|
3100
|
+
|
|
3101
|
+
impl magnus::IntoValue for ImageSource {
|
|
3102
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
3103
|
+
let sym = match self {
|
|
3104
|
+
ImageSource::Img => "img",
|
|
3105
|
+
ImageSource::PictureSource => "picture_source",
|
|
3106
|
+
ImageSource::OgImage => "og_image",
|
|
3107
|
+
ImageSource::TwitterImage => "twitter_image",
|
|
3108
|
+
};
|
|
3109
|
+
handle.to_symbol(sym).into_value_with(handle)
|
|
3110
|
+
}
|
|
3111
|
+
}
|
|
3112
|
+
|
|
3113
|
+
impl magnus::TryConvert for ImageSource {
|
|
3114
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
3115
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
3116
|
+
match s.as_str() {
|
|
3117
|
+
"img" => Ok(ImageSource::Img),
|
|
3118
|
+
"picture_source" => Ok(ImageSource::PictureSource),
|
|
3119
|
+
"og_image" => Ok(ImageSource::OgImage),
|
|
3120
|
+
"twitter_image" => Ok(ImageSource::TwitterImage),
|
|
3121
|
+
other => Err(magnus::Error::new(
|
|
3122
|
+
unsafe { Ruby::get_unchecked() }.exception_arg_error(),
|
|
3123
|
+
format!("invalid ImageSource value: {other}"),
|
|
3124
|
+
)),
|
|
3125
|
+
}
|
|
3126
|
+
}
|
|
3127
|
+
}
|
|
3128
|
+
|
|
3129
|
+
unsafe impl IntoValueFromNative for ImageSource {}
|
|
3130
|
+
unsafe impl TryConvertOwned for ImageSource {}
|
|
3131
|
+
|
|
3132
|
+
#[derive(Clone, Copy, PartialEq, Eq, Debug, serde::Serialize, serde::Deserialize)]
|
|
3133
|
+
pub enum FeedType {
|
|
3134
|
+
Rss,
|
|
3135
|
+
Atom,
|
|
3136
|
+
JsonFeed,
|
|
3137
|
+
}
|
|
3138
|
+
|
|
3139
|
+
impl Default for FeedType {
|
|
3140
|
+
fn default() -> Self {
|
|
3141
|
+
Self::Rss
|
|
3142
|
+
}
|
|
3143
|
+
}
|
|
3144
|
+
|
|
3145
|
+
impl magnus::IntoValue for FeedType {
|
|
3146
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
3147
|
+
let sym = match self {
|
|
3148
|
+
FeedType::Rss => "rss",
|
|
3149
|
+
FeedType::Atom => "atom",
|
|
3150
|
+
FeedType::JsonFeed => "json_feed",
|
|
3151
|
+
};
|
|
3152
|
+
handle.to_symbol(sym).into_value_with(handle)
|
|
3153
|
+
}
|
|
3154
|
+
}
|
|
3155
|
+
|
|
3156
|
+
impl magnus::TryConvert for FeedType {
|
|
3157
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
3158
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
3159
|
+
match s.as_str() {
|
|
3160
|
+
"rss" => Ok(FeedType::Rss),
|
|
3161
|
+
"atom" => Ok(FeedType::Atom),
|
|
3162
|
+
"json_feed" => Ok(FeedType::JsonFeed),
|
|
3163
|
+
other => Err(magnus::Error::new(
|
|
3164
|
+
unsafe { Ruby::get_unchecked() }.exception_arg_error(),
|
|
3165
|
+
format!("invalid FeedType value: {other}"),
|
|
3166
|
+
)),
|
|
3167
|
+
}
|
|
3168
|
+
}
|
|
3169
|
+
}
|
|
3170
|
+
|
|
3171
|
+
unsafe impl IntoValueFromNative for FeedType {}
|
|
3172
|
+
unsafe impl TryConvertOwned for FeedType {}
|
|
3173
|
+
|
|
3174
|
+
#[derive(Clone, Copy, PartialEq, Eq, Debug, serde::Serialize, serde::Deserialize)]
|
|
3175
|
+
pub enum AssetCategory {
|
|
3176
|
+
Document,
|
|
3177
|
+
Image,
|
|
3178
|
+
Audio,
|
|
3179
|
+
Video,
|
|
3180
|
+
Font,
|
|
3181
|
+
Stylesheet,
|
|
3182
|
+
Script,
|
|
3183
|
+
Archive,
|
|
3184
|
+
Data,
|
|
3185
|
+
Other,
|
|
3186
|
+
}
|
|
3187
|
+
|
|
3188
|
+
impl Default for AssetCategory {
|
|
3189
|
+
fn default() -> Self {
|
|
3190
|
+
Self::Document
|
|
3191
|
+
}
|
|
3192
|
+
}
|
|
3193
|
+
|
|
3194
|
+
impl magnus::IntoValue for AssetCategory {
|
|
3195
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
3196
|
+
let sym = match self {
|
|
3197
|
+
AssetCategory::Document => "document",
|
|
3198
|
+
AssetCategory::Image => "image",
|
|
3199
|
+
AssetCategory::Audio => "audio",
|
|
3200
|
+
AssetCategory::Video => "video",
|
|
3201
|
+
AssetCategory::Font => "font",
|
|
3202
|
+
AssetCategory::Stylesheet => "stylesheet",
|
|
3203
|
+
AssetCategory::Script => "script",
|
|
3204
|
+
AssetCategory::Archive => "archive",
|
|
3205
|
+
AssetCategory::Data => "data",
|
|
3206
|
+
AssetCategory::Other => "other",
|
|
3207
|
+
};
|
|
3208
|
+
handle.to_symbol(sym).into_value_with(handle)
|
|
3209
|
+
}
|
|
3210
|
+
}
|
|
3211
|
+
|
|
3212
|
+
impl magnus::TryConvert for AssetCategory {
|
|
3213
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
3214
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
3215
|
+
match s.as_str() {
|
|
3216
|
+
"document" => Ok(AssetCategory::Document),
|
|
3217
|
+
"image" => Ok(AssetCategory::Image),
|
|
3218
|
+
"audio" => Ok(AssetCategory::Audio),
|
|
3219
|
+
"video" => Ok(AssetCategory::Video),
|
|
3220
|
+
"font" => Ok(AssetCategory::Font),
|
|
3221
|
+
"stylesheet" => Ok(AssetCategory::Stylesheet),
|
|
3222
|
+
"script" => Ok(AssetCategory::Script),
|
|
3223
|
+
"archive" => Ok(AssetCategory::Archive),
|
|
3224
|
+
"data" => Ok(AssetCategory::Data),
|
|
3225
|
+
"other" => Ok(AssetCategory::Other),
|
|
3226
|
+
other => Err(magnus::Error::new(
|
|
3227
|
+
unsafe { Ruby::get_unchecked() }.exception_arg_error(),
|
|
3228
|
+
format!("invalid AssetCategory value: {other}"),
|
|
3229
|
+
)),
|
|
3230
|
+
}
|
|
3231
|
+
}
|
|
3232
|
+
}
|
|
3233
|
+
|
|
3234
|
+
unsafe impl IntoValueFromNative for AssetCategory {}
|
|
3235
|
+
unsafe impl TryConvertOwned for AssetCategory {}
|
|
3236
|
+
|
|
3237
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
3238
|
+
pub enum CrawlEvent {
|
|
3239
|
+
Page { _0: CrawlPageResult },
|
|
3240
|
+
Error { url: String, error: String },
|
|
3241
|
+
Complete { pages_crawled: usize },
|
|
3242
|
+
}
|
|
3243
|
+
|
|
3244
|
+
impl Default for CrawlEvent {
|
|
3245
|
+
fn default() -> Self {
|
|
3246
|
+
Self::Page { _0: Default::default() }
|
|
3247
|
+
}
|
|
3248
|
+
}
|
|
3249
|
+
|
|
3250
|
+
impl magnus::IntoValue for CrawlEvent {
|
|
3251
|
+
fn into_value_with(self, handle: &Ruby) -> magnus::Value {
|
|
3252
|
+
match serde_json::to_value(&self) {
|
|
3253
|
+
Ok(v) => json_to_ruby(handle, v),
|
|
3254
|
+
Err(_) => handle.qnil().into_value_with(handle),
|
|
3255
|
+
}
|
|
3256
|
+
}
|
|
3257
|
+
}
|
|
3258
|
+
|
|
3259
|
+
impl magnus::TryConvert for CrawlEvent {
|
|
3260
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
3261
|
+
let s: String = magnus::TryConvert::try_convert(val)?;
|
|
3262
|
+
serde_json::from_str(&s)
|
|
3263
|
+
.map_err(|e| magnus::Error::new(unsafe { Ruby::get_unchecked() }.exception_type_error(), e.to_string()))
|
|
3264
|
+
}
|
|
3265
|
+
}
|
|
3266
|
+
|
|
3267
|
+
unsafe impl IntoValueFromNative for CrawlEvent {}
|
|
3268
|
+
unsafe impl TryConvertOwned for CrawlEvent {}
|
|
3269
|
+
|
|
3270
|
+
fn create_engine(config: Option<String>) -> Result<CrawlEngineHandle, Error> {
|
|
3271
|
+
let config: Option<CrawlConfig> = config
|
|
3272
|
+
.as_deref()
|
|
3273
|
+
.filter(|s| *s != "nil")
|
|
3274
|
+
.map(|s| {
|
|
3275
|
+
let core: kreuzcrawl::CrawlConfig = serde_json::from_str(s).map_err(|e| {
|
|
3276
|
+
magnus::Error::new(unsafe { Ruby::get_unchecked() }.exception_type_error(), e.to_string())
|
|
3277
|
+
})?;
|
|
3278
|
+
Ok::<_, magnus::Error>(core.into())
|
|
3279
|
+
})
|
|
3280
|
+
.transpose()?;
|
|
3281
|
+
let result = kreuzcrawl::create_engine(config.map(Into::into)).map_err(|e| {
|
|
3282
|
+
magnus::Error::new(
|
|
3283
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3284
|
+
e.to_string(),
|
|
3285
|
+
)
|
|
3286
|
+
})?;
|
|
3287
|
+
Ok(CrawlEngineHandle {
|
|
3288
|
+
inner: Arc::new(result),
|
|
3289
|
+
})
|
|
3290
|
+
}
|
|
3291
|
+
|
|
3292
|
+
fn scrape(engine: CrawlEngineHandle, url: String) -> Result<ScrapeResult, Error> {
|
|
3293
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3294
|
+
magnus::Error::new(
|
|
3295
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3296
|
+
e.to_string(),
|
|
3297
|
+
)
|
|
3298
|
+
})?;
|
|
3299
|
+
let result = rt
|
|
3300
|
+
.block_on(async { kreuzcrawl::scrape(&engine.inner, &url).await })
|
|
3301
|
+
.map_err(|e| {
|
|
3302
|
+
magnus::Error::new(
|
|
3303
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3304
|
+
e.to_string(),
|
|
3305
|
+
)
|
|
3306
|
+
})?;
|
|
3307
|
+
Ok(result.into())
|
|
3308
|
+
}
|
|
3309
|
+
|
|
3310
|
+
fn scrape_async(engine: CrawlEngineHandle, url: String) -> Result<ScrapeResult, Error> {
|
|
3311
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3312
|
+
magnus::Error::new(
|
|
3313
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3314
|
+
e.to_string(),
|
|
3315
|
+
)
|
|
3316
|
+
})?;
|
|
3317
|
+
let result = rt
|
|
3318
|
+
.block_on(async { kreuzcrawl::scrape(&engine.inner, &url).await })
|
|
3319
|
+
.map_err(|e| {
|
|
3320
|
+
magnus::Error::new(
|
|
3321
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3322
|
+
e.to_string(),
|
|
3323
|
+
)
|
|
3324
|
+
})?;
|
|
3325
|
+
Ok(result.into())
|
|
3326
|
+
}
|
|
3327
|
+
|
|
3328
|
+
fn crawl(engine: CrawlEngineHandle, url: String) -> Result<CrawlResult, Error> {
|
|
3329
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3330
|
+
magnus::Error::new(
|
|
3331
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3332
|
+
e.to_string(),
|
|
3333
|
+
)
|
|
3334
|
+
})?;
|
|
3335
|
+
let result = rt
|
|
3336
|
+
.block_on(async { kreuzcrawl::crawl(&engine.inner, &url).await })
|
|
3337
|
+
.map_err(|e| {
|
|
3338
|
+
magnus::Error::new(
|
|
3339
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3340
|
+
e.to_string(),
|
|
3341
|
+
)
|
|
3342
|
+
})?;
|
|
3343
|
+
Ok(result.into())
|
|
3344
|
+
}
|
|
3345
|
+
|
|
3346
|
+
fn crawl_async(engine: CrawlEngineHandle, url: String) -> Result<CrawlResult, Error> {
|
|
3347
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3348
|
+
magnus::Error::new(
|
|
3349
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3350
|
+
e.to_string(),
|
|
3351
|
+
)
|
|
3352
|
+
})?;
|
|
3353
|
+
let result = rt
|
|
3354
|
+
.block_on(async { kreuzcrawl::crawl(&engine.inner, &url).await })
|
|
3355
|
+
.map_err(|e| {
|
|
3356
|
+
magnus::Error::new(
|
|
3357
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3358
|
+
e.to_string(),
|
|
3359
|
+
)
|
|
3360
|
+
})?;
|
|
3361
|
+
Ok(result.into())
|
|
3362
|
+
}
|
|
3363
|
+
|
|
3364
|
+
fn map_urls(engine: CrawlEngineHandle, url: String) -> Result<MapResult, Error> {
|
|
3365
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3366
|
+
magnus::Error::new(
|
|
3367
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3368
|
+
e.to_string(),
|
|
3369
|
+
)
|
|
3370
|
+
})?;
|
|
3371
|
+
let result = rt
|
|
3372
|
+
.block_on(async { kreuzcrawl::map_urls(&engine.inner, &url).await })
|
|
3373
|
+
.map_err(|e| {
|
|
3374
|
+
magnus::Error::new(
|
|
3375
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3376
|
+
e.to_string(),
|
|
3377
|
+
)
|
|
3378
|
+
})?;
|
|
3379
|
+
Ok(result.into())
|
|
3380
|
+
}
|
|
3381
|
+
|
|
3382
|
+
fn map_urls_async(engine: CrawlEngineHandle, url: String) -> Result<MapResult, Error> {
|
|
3383
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3384
|
+
magnus::Error::new(
|
|
3385
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3386
|
+
e.to_string(),
|
|
3387
|
+
)
|
|
3388
|
+
})?;
|
|
3389
|
+
let result = rt
|
|
3390
|
+
.block_on(async { kreuzcrawl::map_urls(&engine.inner, &url).await })
|
|
3391
|
+
.map_err(|e| {
|
|
3392
|
+
magnus::Error::new(
|
|
3393
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3394
|
+
e.to_string(),
|
|
3395
|
+
)
|
|
3396
|
+
})?;
|
|
3397
|
+
Ok(result.into())
|
|
3398
|
+
}
|
|
3399
|
+
|
|
3400
|
+
fn batch_scrape(engine: CrawlEngineHandle, urls: Vec<String>) -> Result<Vec<BatchScrapeResult>, Error> {
|
|
3401
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3402
|
+
magnus::Error::new(
|
|
3403
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3404
|
+
e.to_string(),
|
|
3405
|
+
)
|
|
3406
|
+
})?;
|
|
3407
|
+
let result = rt.block_on(async { kreuzcrawl::batch_scrape(&engine.inner, urls).await });
|
|
3408
|
+
Ok(result.into_iter().map(Into::into).collect())
|
|
3409
|
+
}
|
|
3410
|
+
|
|
3411
|
+
fn batch_scrape_async(engine: CrawlEngineHandle, urls: Vec<String>) -> Result<Vec<BatchScrapeResult>, Error> {
|
|
3412
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3413
|
+
magnus::Error::new(
|
|
3414
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3415
|
+
e.to_string(),
|
|
3416
|
+
)
|
|
3417
|
+
})?;
|
|
3418
|
+
let result = rt.block_on(async { kreuzcrawl::batch_scrape(&engine.inner, urls).await });
|
|
3419
|
+
Ok(result.into_iter().map(Into::into).collect())
|
|
3420
|
+
}
|
|
3421
|
+
|
|
3422
|
+
fn batch_crawl(engine: CrawlEngineHandle, urls: Vec<String>) -> Result<Vec<BatchCrawlResult>, Error> {
|
|
3423
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3424
|
+
magnus::Error::new(
|
|
3425
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3426
|
+
e.to_string(),
|
|
3427
|
+
)
|
|
3428
|
+
})?;
|
|
3429
|
+
let result = rt.block_on(async { kreuzcrawl::batch_crawl(&engine.inner, urls).await });
|
|
3430
|
+
Ok(result.into_iter().map(Into::into).collect())
|
|
3431
|
+
}
|
|
3432
|
+
|
|
3433
|
+
fn batch_crawl_async(engine: CrawlEngineHandle, urls: Vec<String>) -> Result<Vec<BatchCrawlResult>, Error> {
|
|
3434
|
+
let rt = tokio::runtime::Runtime::new().map_err(|e| {
|
|
3435
|
+
magnus::Error::new(
|
|
3436
|
+
unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
|
|
3437
|
+
e.to_string(),
|
|
3438
|
+
)
|
|
3439
|
+
})?;
|
|
3440
|
+
let result = rt.block_on(async { kreuzcrawl::batch_crawl(&engine.inner, urls).await });
|
|
3441
|
+
Ok(result.into_iter().map(Into::into).collect())
|
|
3442
|
+
}
|
|
3443
|
+
|
|
3444
|
+
impl From<ExtractionMeta> for kreuzcrawl::ExtractionMeta {
|
|
3445
|
+
fn from(val: ExtractionMeta) -> Self {
|
|
3446
|
+
Self {
|
|
3447
|
+
cost: val.cost,
|
|
3448
|
+
prompt_tokens: val.prompt_tokens,
|
|
3449
|
+
completion_tokens: val.completion_tokens,
|
|
3450
|
+
model: val.model,
|
|
3451
|
+
chunks_processed: val.chunks_processed,
|
|
3452
|
+
}
|
|
3453
|
+
}
|
|
3454
|
+
}
|
|
3455
|
+
|
|
3456
|
+
impl From<kreuzcrawl::ExtractionMeta> for ExtractionMeta {
|
|
3457
|
+
fn from(val: kreuzcrawl::ExtractionMeta) -> Self {
|
|
3458
|
+
Self {
|
|
3459
|
+
cost: val.cost,
|
|
3460
|
+
prompt_tokens: val.prompt_tokens,
|
|
3461
|
+
completion_tokens: val.completion_tokens,
|
|
3462
|
+
model: val.model,
|
|
3463
|
+
chunks_processed: val.chunks_processed,
|
|
3464
|
+
}
|
|
3465
|
+
}
|
|
3466
|
+
}
|
|
3467
|
+
|
|
3468
|
+
impl From<ProxyConfig> for kreuzcrawl::ProxyConfig {
|
|
3469
|
+
fn from(val: ProxyConfig) -> Self {
|
|
3470
|
+
Self {
|
|
3471
|
+
url: val.url,
|
|
3472
|
+
username: val.username,
|
|
3473
|
+
password: val.password,
|
|
3474
|
+
}
|
|
3475
|
+
}
|
|
3476
|
+
}
|
|
3477
|
+
|
|
3478
|
+
impl From<kreuzcrawl::ProxyConfig> for ProxyConfig {
|
|
3479
|
+
fn from(val: kreuzcrawl::ProxyConfig) -> Self {
|
|
3480
|
+
Self {
|
|
3481
|
+
url: val.url,
|
|
3482
|
+
username: val.username,
|
|
3483
|
+
password: val.password,
|
|
3484
|
+
}
|
|
3485
|
+
}
|
|
3486
|
+
}
|
|
3487
|
+
|
|
3488
|
+
impl From<BrowserConfig> for kreuzcrawl::BrowserConfig {
|
|
3489
|
+
fn from(val: BrowserConfig) -> Self {
|
|
3490
|
+
Self {
|
|
3491
|
+
mode: val.mode.into(),
|
|
3492
|
+
endpoint: val.endpoint,
|
|
3493
|
+
timeout: std::time::Duration::from_millis(val.timeout),
|
|
3494
|
+
wait: val.wait.into(),
|
|
3495
|
+
wait_selector: val.wait_selector,
|
|
3496
|
+
extra_wait: val.extra_wait.map(std::time::Duration::from_millis),
|
|
3497
|
+
}
|
|
3498
|
+
}
|
|
3499
|
+
}
|
|
3500
|
+
|
|
3501
|
+
impl From<kreuzcrawl::BrowserConfig> for BrowserConfig {
|
|
3502
|
+
fn from(val: kreuzcrawl::BrowserConfig) -> Self {
|
|
3503
|
+
Self {
|
|
3504
|
+
mode: val.mode.into(),
|
|
3505
|
+
endpoint: val.endpoint,
|
|
3506
|
+
timeout: val.timeout.as_millis() as u64,
|
|
3507
|
+
wait: val.wait.into(),
|
|
3508
|
+
wait_selector: val.wait_selector,
|
|
3509
|
+
extra_wait: val.extra_wait.map(|d| d.as_millis() as u64),
|
|
3510
|
+
}
|
|
3511
|
+
}
|
|
3512
|
+
}
|
|
3513
|
+
|
|
3514
|
+
#[allow(clippy::needless_update)]
|
|
3515
|
+
impl From<CrawlConfig> for kreuzcrawl::CrawlConfig {
|
|
3516
|
+
fn from(val: CrawlConfig) -> Self {
|
|
3517
|
+
Self {
|
|
3518
|
+
max_depth: val.max_depth,
|
|
3519
|
+
max_pages: val.max_pages,
|
|
3520
|
+
max_concurrent: val.max_concurrent,
|
|
3521
|
+
respect_robots_txt: val.respect_robots_txt,
|
|
3522
|
+
user_agent: val.user_agent,
|
|
3523
|
+
stay_on_domain: val.stay_on_domain,
|
|
3524
|
+
allow_subdomains: val.allow_subdomains,
|
|
3525
|
+
include_paths: val.include_paths,
|
|
3526
|
+
exclude_paths: val.exclude_paths,
|
|
3527
|
+
custom_headers: val.custom_headers.into_iter().collect(),
|
|
3528
|
+
request_timeout: std::time::Duration::from_millis(val.request_timeout),
|
|
3529
|
+
max_redirects: val.max_redirects,
|
|
3530
|
+
retry_count: val.retry_count,
|
|
3531
|
+
retry_codes: val.retry_codes,
|
|
3532
|
+
cookies_enabled: val.cookies_enabled,
|
|
3533
|
+
auth: val.auth.map(Into::into),
|
|
3534
|
+
max_body_size: val.max_body_size,
|
|
3535
|
+
main_content_only: val.main_content_only,
|
|
3536
|
+
remove_tags: val.remove_tags,
|
|
3537
|
+
map_limit: val.map_limit,
|
|
3538
|
+
map_search: val.map_search,
|
|
3539
|
+
download_assets: val.download_assets,
|
|
3540
|
+
asset_types: val.asset_types.into_iter().map(Into::into).collect(),
|
|
3541
|
+
max_asset_size: val.max_asset_size,
|
|
3542
|
+
browser: val.browser.into(),
|
|
3543
|
+
proxy: val.proxy.map(Into::into),
|
|
3544
|
+
user_agents: val.user_agents,
|
|
3545
|
+
capture_screenshot: val.capture_screenshot,
|
|
3546
|
+
download_documents: val.download_documents,
|
|
3547
|
+
document_max_size: val.document_max_size,
|
|
3548
|
+
document_mime_types: val.document_mime_types,
|
|
3549
|
+
warc_output: val.warc_output.map(Into::into),
|
|
3550
|
+
browser_profile: val.browser_profile,
|
|
3551
|
+
save_browser_profile: val.save_browser_profile,
|
|
3552
|
+
..Default::default()
|
|
3553
|
+
}
|
|
3554
|
+
}
|
|
3555
|
+
}
|
|
3556
|
+
|
|
3557
|
+
impl From<kreuzcrawl::CrawlConfig> for CrawlConfig {
|
|
3558
|
+
fn from(val: kreuzcrawl::CrawlConfig) -> Self {
|
|
3559
|
+
Self {
|
|
3560
|
+
max_depth: val.max_depth,
|
|
3561
|
+
max_pages: val.max_pages,
|
|
3562
|
+
max_concurrent: val.max_concurrent,
|
|
3563
|
+
respect_robots_txt: val.respect_robots_txt,
|
|
3564
|
+
user_agent: val.user_agent,
|
|
3565
|
+
stay_on_domain: val.stay_on_domain,
|
|
3566
|
+
allow_subdomains: val.allow_subdomains,
|
|
3567
|
+
include_paths: val.include_paths,
|
|
3568
|
+
exclude_paths: val.exclude_paths,
|
|
3569
|
+
custom_headers: val.custom_headers.into_iter().collect(),
|
|
3570
|
+
request_timeout: val.request_timeout.as_millis() as u64,
|
|
3571
|
+
max_redirects: val.max_redirects,
|
|
3572
|
+
retry_count: val.retry_count,
|
|
3573
|
+
retry_codes: val.retry_codes,
|
|
3574
|
+
cookies_enabled: val.cookies_enabled,
|
|
3575
|
+
auth: val.auth.map(Into::into),
|
|
3576
|
+
max_body_size: val.max_body_size,
|
|
3577
|
+
main_content_only: val.main_content_only,
|
|
3578
|
+
remove_tags: val.remove_tags,
|
|
3579
|
+
map_limit: val.map_limit,
|
|
3580
|
+
map_search: val.map_search,
|
|
3581
|
+
download_assets: val.download_assets,
|
|
3582
|
+
asset_types: val.asset_types.into_iter().map(Into::into).collect(),
|
|
3583
|
+
max_asset_size: val.max_asset_size,
|
|
3584
|
+
browser: val.browser.into(),
|
|
3585
|
+
proxy: val.proxy.map(Into::into),
|
|
3586
|
+
user_agents: val.user_agents,
|
|
3587
|
+
capture_screenshot: val.capture_screenshot,
|
|
3588
|
+
download_documents: val.download_documents,
|
|
3589
|
+
document_max_size: val.document_max_size,
|
|
3590
|
+
document_mime_types: val.document_mime_types,
|
|
3591
|
+
warc_output: val.warc_output.map(|p| p.to_string_lossy().to_string()),
|
|
3592
|
+
browser_profile: val.browser_profile,
|
|
3593
|
+
save_browser_profile: val.save_browser_profile,
|
|
3594
|
+
}
|
|
3595
|
+
}
|
|
3596
|
+
}
|
|
3597
|
+
|
|
3598
|
+
impl From<DownloadedDocument> for kreuzcrawl::DownloadedDocument {
|
|
3599
|
+
fn from(val: DownloadedDocument) -> Self {
|
|
3600
|
+
Self {
|
|
3601
|
+
url: val.url,
|
|
3602
|
+
mime_type: Default::default(),
|
|
3603
|
+
content: val.content,
|
|
3604
|
+
size: val.size,
|
|
3605
|
+
filename: Default::default(),
|
|
3606
|
+
content_hash: Default::default(),
|
|
3607
|
+
headers: Default::default(),
|
|
3608
|
+
}
|
|
3609
|
+
}
|
|
3610
|
+
}
|
|
3611
|
+
|
|
3612
|
+
impl From<kreuzcrawl::DownloadedDocument> for DownloadedDocument {
|
|
3613
|
+
fn from(val: kreuzcrawl::DownloadedDocument) -> Self {
|
|
3614
|
+
Self {
|
|
3615
|
+
url: val.url,
|
|
3616
|
+
mime_type: format!("{:?}", val.mime_type),
|
|
3617
|
+
content: val.content.to_vec(),
|
|
3618
|
+
size: val.size,
|
|
3619
|
+
filename: val.filename.as_ref().map(|v| format!("{:?}", v)),
|
|
3620
|
+
content_hash: format!("{:?}", val.content_hash),
|
|
3621
|
+
headers: val
|
|
3622
|
+
.headers
|
|
3623
|
+
.into_iter()
|
|
3624
|
+
.map(|(k, v)| (format!("{:?}", k), format!("{:?}", v)))
|
|
3625
|
+
.collect(),
|
|
3626
|
+
}
|
|
3627
|
+
}
|
|
3628
|
+
}
|
|
3629
|
+
|
|
3630
|
+
impl From<kreuzcrawl::InteractionResult> for InteractionResult {
|
|
3631
|
+
fn from(val: kreuzcrawl::InteractionResult) -> Self {
|
|
3632
|
+
Self {
|
|
3633
|
+
action_results: val.action_results.into_iter().map(Into::into).collect(),
|
|
3634
|
+
final_html: val.final_html,
|
|
3635
|
+
final_url: val.final_url,
|
|
3636
|
+
screenshot: val.screenshot.map(|v| v.to_vec()),
|
|
3637
|
+
}
|
|
3638
|
+
}
|
|
3639
|
+
}
|
|
3640
|
+
|
|
3641
|
+
impl From<kreuzcrawl::ActionResult> for ActionResult {
|
|
3642
|
+
fn from(val: kreuzcrawl::ActionResult) -> Self {
|
|
3643
|
+
Self {
|
|
3644
|
+
action_index: val.action_index,
|
|
3645
|
+
action_type: format!("{:?}", val.action_type),
|
|
3646
|
+
success: val.success,
|
|
3647
|
+
data: val.data.as_ref().map(ToString::to_string),
|
|
3648
|
+
error: val.error,
|
|
3649
|
+
}
|
|
3650
|
+
}
|
|
3651
|
+
}
|
|
3652
|
+
|
|
3653
|
+
impl From<ScrapeResult> for kreuzcrawl::ScrapeResult {
|
|
3654
|
+
fn from(val: ScrapeResult) -> Self {
|
|
3655
|
+
Self {
|
|
3656
|
+
status_code: val.status_code,
|
|
3657
|
+
content_type: val.content_type,
|
|
3658
|
+
html: val.html,
|
|
3659
|
+
body_size: val.body_size,
|
|
3660
|
+
metadata: val.metadata.into(),
|
|
3661
|
+
links: val.links.into_iter().map(Into::into).collect(),
|
|
3662
|
+
images: val.images.into_iter().map(Into::into).collect(),
|
|
3663
|
+
feeds: val.feeds.into_iter().map(Into::into).collect(),
|
|
3664
|
+
json_ld: val.json_ld.into_iter().map(Into::into).collect(),
|
|
3665
|
+
is_allowed: val.is_allowed,
|
|
3666
|
+
crawl_delay: val.crawl_delay,
|
|
3667
|
+
noindex_detected: val.noindex_detected,
|
|
3668
|
+
nofollow_detected: val.nofollow_detected,
|
|
3669
|
+
x_robots_tag: val.x_robots_tag,
|
|
3670
|
+
is_pdf: val.is_pdf,
|
|
3671
|
+
was_skipped: val.was_skipped,
|
|
3672
|
+
detected_charset: val.detected_charset,
|
|
3673
|
+
main_content_only: val.main_content_only,
|
|
3674
|
+
auth_header_sent: val.auth_header_sent,
|
|
3675
|
+
response_meta: val.response_meta.map(Into::into),
|
|
3676
|
+
assets: val.assets.into_iter().map(Into::into).collect(),
|
|
3677
|
+
js_render_hint: val.js_render_hint,
|
|
3678
|
+
browser_used: val.browser_used,
|
|
3679
|
+
markdown: val.markdown.map(Into::into),
|
|
3680
|
+
extracted_data: val.extracted_data.as_ref().and_then(|s| serde_json::from_str(s).ok()),
|
|
3681
|
+
extraction_meta: val.extraction_meta.map(Into::into),
|
|
3682
|
+
screenshot: val.screenshot,
|
|
3683
|
+
downloaded_document: val.downloaded_document.map(Into::into),
|
|
3684
|
+
}
|
|
3685
|
+
}
|
|
3686
|
+
}
|
|
3687
|
+
|
|
3688
|
+
impl From<kreuzcrawl::ScrapeResult> for ScrapeResult {
|
|
3689
|
+
fn from(val: kreuzcrawl::ScrapeResult) -> Self {
|
|
3690
|
+
Self {
|
|
3691
|
+
status_code: val.status_code,
|
|
3692
|
+
content_type: val.content_type,
|
|
3693
|
+
html: val.html,
|
|
3694
|
+
body_size: val.body_size,
|
|
3695
|
+
metadata: val.metadata.into(),
|
|
3696
|
+
links: val.links.into_iter().map(Into::into).collect(),
|
|
3697
|
+
images: val.images.into_iter().map(Into::into).collect(),
|
|
3698
|
+
feeds: val.feeds.into_iter().map(Into::into).collect(),
|
|
3699
|
+
json_ld: val.json_ld.into_iter().map(Into::into).collect(),
|
|
3700
|
+
is_allowed: val.is_allowed,
|
|
3701
|
+
crawl_delay: val.crawl_delay,
|
|
3702
|
+
noindex_detected: val.noindex_detected,
|
|
3703
|
+
nofollow_detected: val.nofollow_detected,
|
|
3704
|
+
x_robots_tag: val.x_robots_tag,
|
|
3705
|
+
is_pdf: val.is_pdf,
|
|
3706
|
+
was_skipped: val.was_skipped,
|
|
3707
|
+
detected_charset: val.detected_charset,
|
|
3708
|
+
main_content_only: val.main_content_only,
|
|
3709
|
+
auth_header_sent: val.auth_header_sent,
|
|
3710
|
+
response_meta: val.response_meta.map(Into::into),
|
|
3711
|
+
assets: val.assets.into_iter().map(Into::into).collect(),
|
|
3712
|
+
js_render_hint: val.js_render_hint,
|
|
3713
|
+
browser_used: val.browser_used,
|
|
3714
|
+
markdown: val.markdown.map(Into::into),
|
|
3715
|
+
extracted_data: val.extracted_data.as_ref().map(ToString::to_string),
|
|
3716
|
+
extraction_meta: val.extraction_meta.map(Into::into),
|
|
3717
|
+
screenshot: val.screenshot.map(|v| v.to_vec()),
|
|
3718
|
+
downloaded_document: val.downloaded_document.map(Into::into),
|
|
3719
|
+
}
|
|
3720
|
+
}
|
|
3721
|
+
}
|
|
3722
|
+
|
|
3723
|
+
impl From<CrawlPageResult> for kreuzcrawl::CrawlPageResult {
|
|
3724
|
+
fn from(val: CrawlPageResult) -> Self {
|
|
3725
|
+
Self {
|
|
3726
|
+
url: val.url,
|
|
3727
|
+
normalized_url: val.normalized_url,
|
|
3728
|
+
status_code: val.status_code,
|
|
3729
|
+
content_type: val.content_type,
|
|
3730
|
+
html: val.html,
|
|
3731
|
+
body_size: val.body_size,
|
|
3732
|
+
metadata: val.metadata.into(),
|
|
3733
|
+
links: val.links.into_iter().map(Into::into).collect(),
|
|
3734
|
+
images: val.images.into_iter().map(Into::into).collect(),
|
|
3735
|
+
feeds: val.feeds.into_iter().map(Into::into).collect(),
|
|
3736
|
+
json_ld: val.json_ld.into_iter().map(Into::into).collect(),
|
|
3737
|
+
depth: val.depth,
|
|
3738
|
+
stayed_on_domain: val.stayed_on_domain,
|
|
3739
|
+
was_skipped: val.was_skipped,
|
|
3740
|
+
is_pdf: val.is_pdf,
|
|
3741
|
+
detected_charset: val.detected_charset,
|
|
3742
|
+
markdown: val.markdown.map(Into::into),
|
|
3743
|
+
extracted_data: val.extracted_data.as_ref().and_then(|s| serde_json::from_str(s).ok()),
|
|
3744
|
+
extraction_meta: val.extraction_meta.map(Into::into),
|
|
3745
|
+
downloaded_document: val.downloaded_document.map(Into::into),
|
|
3746
|
+
}
|
|
3747
|
+
}
|
|
3748
|
+
}
|
|
3749
|
+
|
|
3750
|
+
impl From<kreuzcrawl::CrawlPageResult> for CrawlPageResult {
|
|
3751
|
+
fn from(val: kreuzcrawl::CrawlPageResult) -> Self {
|
|
3752
|
+
Self {
|
|
3753
|
+
url: val.url,
|
|
3754
|
+
normalized_url: val.normalized_url,
|
|
3755
|
+
status_code: val.status_code,
|
|
3756
|
+
content_type: val.content_type,
|
|
3757
|
+
html: val.html,
|
|
3758
|
+
body_size: val.body_size,
|
|
3759
|
+
metadata: val.metadata.into(),
|
|
3760
|
+
links: val.links.into_iter().map(Into::into).collect(),
|
|
3761
|
+
images: val.images.into_iter().map(Into::into).collect(),
|
|
3762
|
+
feeds: val.feeds.into_iter().map(Into::into).collect(),
|
|
3763
|
+
json_ld: val.json_ld.into_iter().map(Into::into).collect(),
|
|
3764
|
+
depth: val.depth,
|
|
3765
|
+
stayed_on_domain: val.stayed_on_domain,
|
|
3766
|
+
was_skipped: val.was_skipped,
|
|
3767
|
+
is_pdf: val.is_pdf,
|
|
3768
|
+
detected_charset: val.detected_charset,
|
|
3769
|
+
markdown: val.markdown.map(Into::into),
|
|
3770
|
+
extracted_data: val.extracted_data.as_ref().map(ToString::to_string),
|
|
3771
|
+
extraction_meta: val.extraction_meta.map(Into::into),
|
|
3772
|
+
downloaded_document: val.downloaded_document.map(Into::into),
|
|
3773
|
+
}
|
|
3774
|
+
}
|
|
3775
|
+
}
|
|
3776
|
+
|
|
3777
|
+
impl From<CrawlResult> for kreuzcrawl::CrawlResult {
|
|
3778
|
+
fn from(val: CrawlResult) -> Self {
|
|
3779
|
+
Self {
|
|
3780
|
+
pages: val.pages.into_iter().map(Into::into).collect(),
|
|
3781
|
+
final_url: val.final_url,
|
|
3782
|
+
redirect_count: val.redirect_count,
|
|
3783
|
+
was_skipped: val.was_skipped,
|
|
3784
|
+
error: val.error,
|
|
3785
|
+
cookies: val.cookies.into_iter().map(Into::into).collect(),
|
|
3786
|
+
normalized_urls: val.normalized_urls,
|
|
3787
|
+
}
|
|
3788
|
+
}
|
|
3789
|
+
}
|
|
3790
|
+
|
|
3791
|
+
impl From<kreuzcrawl::CrawlResult> for CrawlResult {
|
|
3792
|
+
fn from(val: kreuzcrawl::CrawlResult) -> Self {
|
|
3793
|
+
Self {
|
|
3794
|
+
pages: val.pages.into_iter().map(Into::into).collect(),
|
|
3795
|
+
final_url: val.final_url,
|
|
3796
|
+
redirect_count: val.redirect_count,
|
|
3797
|
+
was_skipped: val.was_skipped,
|
|
3798
|
+
error: val.error,
|
|
3799
|
+
cookies: val.cookies.into_iter().map(Into::into).collect(),
|
|
3800
|
+
normalized_urls: val.normalized_urls,
|
|
3801
|
+
}
|
|
3802
|
+
}
|
|
3803
|
+
}
|
|
3804
|
+
|
|
3805
|
+
impl From<SitemapUrl> for kreuzcrawl::SitemapUrl {
|
|
3806
|
+
fn from(val: SitemapUrl) -> Self {
|
|
3807
|
+
Self {
|
|
3808
|
+
url: val.url,
|
|
3809
|
+
lastmod: val.lastmod,
|
|
3810
|
+
changefreq: val.changefreq,
|
|
3811
|
+
priority: val.priority,
|
|
3812
|
+
}
|
|
3813
|
+
}
|
|
3814
|
+
}
|
|
3815
|
+
|
|
3816
|
+
impl From<kreuzcrawl::SitemapUrl> for SitemapUrl {
|
|
3817
|
+
fn from(val: kreuzcrawl::SitemapUrl) -> Self {
|
|
3818
|
+
Self {
|
|
3819
|
+
url: val.url,
|
|
3820
|
+
lastmod: val.lastmod,
|
|
3821
|
+
changefreq: val.changefreq,
|
|
3822
|
+
priority: val.priority,
|
|
3823
|
+
}
|
|
3824
|
+
}
|
|
3825
|
+
}
|
|
3826
|
+
|
|
3827
|
+
impl From<MapResult> for kreuzcrawl::MapResult {
|
|
3828
|
+
fn from(val: MapResult) -> Self {
|
|
3829
|
+
Self {
|
|
3830
|
+
urls: val.urls.into_iter().map(Into::into).collect(),
|
|
3831
|
+
}
|
|
3832
|
+
}
|
|
3833
|
+
}
|
|
3834
|
+
|
|
3835
|
+
impl From<kreuzcrawl::MapResult> for MapResult {
|
|
3836
|
+
fn from(val: kreuzcrawl::MapResult) -> Self {
|
|
3837
|
+
Self {
|
|
3838
|
+
urls: val.urls.into_iter().map(Into::into).collect(),
|
|
3839
|
+
}
|
|
3840
|
+
}
|
|
3841
|
+
}
|
|
3842
|
+
|
|
3843
|
+
impl From<MarkdownResult> for kreuzcrawl::MarkdownResult {
|
|
3844
|
+
fn from(val: MarkdownResult) -> Self {
|
|
3845
|
+
Self {
|
|
3846
|
+
content: val.content,
|
|
3847
|
+
document_structure: val
|
|
3848
|
+
.document_structure
|
|
3849
|
+
.as_ref()
|
|
3850
|
+
.and_then(|s| serde_json::from_str(s).ok()),
|
|
3851
|
+
tables: val
|
|
3852
|
+
.tables
|
|
3853
|
+
.into_iter()
|
|
3854
|
+
.filter_map(|s| serde_json::from_str(&s).ok())
|
|
3855
|
+
.collect(),
|
|
3856
|
+
warnings: val.warnings,
|
|
3857
|
+
citations: val.citations.map(Into::into),
|
|
3858
|
+
fit_content: val.fit_content,
|
|
3859
|
+
}
|
|
3860
|
+
}
|
|
3861
|
+
}
|
|
3862
|
+
|
|
3863
|
+
impl From<kreuzcrawl::MarkdownResult> for MarkdownResult {
|
|
3864
|
+
fn from(val: kreuzcrawl::MarkdownResult) -> Self {
|
|
3865
|
+
Self {
|
|
3866
|
+
content: val.content,
|
|
3867
|
+
document_structure: val.document_structure.as_ref().map(ToString::to_string),
|
|
3868
|
+
tables: val.tables.iter().map(ToString::to_string).collect(),
|
|
3869
|
+
warnings: val.warnings,
|
|
3870
|
+
citations: val.citations.map(Into::into),
|
|
3871
|
+
fit_content: val.fit_content,
|
|
3872
|
+
}
|
|
3873
|
+
}
|
|
3874
|
+
}
|
|
3875
|
+
|
|
3876
|
+
impl From<kreuzcrawl::CachedPage> for CachedPage {
|
|
3877
|
+
fn from(val: kreuzcrawl::CachedPage) -> Self {
|
|
3878
|
+
Self {
|
|
3879
|
+
url: val.url,
|
|
3880
|
+
status_code: val.status_code,
|
|
3881
|
+
content_type: val.content_type,
|
|
3882
|
+
body: val.body,
|
|
3883
|
+
etag: val.etag,
|
|
3884
|
+
last_modified: val.last_modified,
|
|
3885
|
+
cached_at: val.cached_at,
|
|
3886
|
+
}
|
|
3887
|
+
}
|
|
3888
|
+
}
|
|
3889
|
+
|
|
3890
|
+
impl From<LinkInfo> for kreuzcrawl::LinkInfo {
|
|
3891
|
+
fn from(val: LinkInfo) -> Self {
|
|
3892
|
+
Self {
|
|
3893
|
+
url: val.url,
|
|
3894
|
+
text: val.text,
|
|
3895
|
+
link_type: val.link_type.into(),
|
|
3896
|
+
rel: val.rel,
|
|
3897
|
+
nofollow: val.nofollow,
|
|
3898
|
+
}
|
|
3899
|
+
}
|
|
3900
|
+
}
|
|
3901
|
+
|
|
3902
|
+
impl From<kreuzcrawl::LinkInfo> for LinkInfo {
|
|
3903
|
+
fn from(val: kreuzcrawl::LinkInfo) -> Self {
|
|
3904
|
+
Self {
|
|
3905
|
+
url: val.url,
|
|
3906
|
+
text: val.text,
|
|
3907
|
+
link_type: val.link_type.into(),
|
|
3908
|
+
rel: val.rel,
|
|
3909
|
+
nofollow: val.nofollow,
|
|
3910
|
+
}
|
|
3911
|
+
}
|
|
3912
|
+
}
|
|
3913
|
+
|
|
3914
|
+
impl From<ImageInfo> for kreuzcrawl::ImageInfo {
|
|
3915
|
+
fn from(val: ImageInfo) -> Self {
|
|
3916
|
+
Self {
|
|
3917
|
+
url: val.url,
|
|
3918
|
+
alt: val.alt,
|
|
3919
|
+
width: val.width,
|
|
3920
|
+
height: val.height,
|
|
3921
|
+
source: val.source.into(),
|
|
3922
|
+
}
|
|
3923
|
+
}
|
|
3924
|
+
}
|
|
3925
|
+
|
|
3926
|
+
impl From<kreuzcrawl::ImageInfo> for ImageInfo {
|
|
3927
|
+
fn from(val: kreuzcrawl::ImageInfo) -> Self {
|
|
3928
|
+
Self {
|
|
3929
|
+
url: val.url,
|
|
3930
|
+
alt: val.alt,
|
|
3931
|
+
width: val.width,
|
|
3932
|
+
height: val.height,
|
|
3933
|
+
source: val.source.into(),
|
|
3934
|
+
}
|
|
3935
|
+
}
|
|
3936
|
+
}
|
|
3937
|
+
|
|
3938
|
+
impl From<FeedInfo> for kreuzcrawl::FeedInfo {
|
|
3939
|
+
fn from(val: FeedInfo) -> Self {
|
|
3940
|
+
Self {
|
|
3941
|
+
url: val.url,
|
|
3942
|
+
title: val.title,
|
|
3943
|
+
feed_type: val.feed_type.into(),
|
|
3944
|
+
}
|
|
3945
|
+
}
|
|
3946
|
+
}
|
|
3947
|
+
|
|
3948
|
+
impl From<kreuzcrawl::FeedInfo> for FeedInfo {
|
|
3949
|
+
fn from(val: kreuzcrawl::FeedInfo) -> Self {
|
|
3950
|
+
Self {
|
|
3951
|
+
url: val.url,
|
|
3952
|
+
title: val.title,
|
|
3953
|
+
feed_type: val.feed_type.into(),
|
|
3954
|
+
}
|
|
3955
|
+
}
|
|
3956
|
+
}
|
|
3957
|
+
|
|
3958
|
+
impl From<JsonLdEntry> for kreuzcrawl::JsonLdEntry {
|
|
3959
|
+
fn from(val: JsonLdEntry) -> Self {
|
|
3960
|
+
Self {
|
|
3961
|
+
schema_type: val.schema_type,
|
|
3962
|
+
name: val.name,
|
|
3963
|
+
raw: val.raw,
|
|
3964
|
+
}
|
|
3965
|
+
}
|
|
3966
|
+
}
|
|
3967
|
+
|
|
3968
|
+
impl From<kreuzcrawl::JsonLdEntry> for JsonLdEntry {
|
|
3969
|
+
fn from(val: kreuzcrawl::JsonLdEntry) -> Self {
|
|
3970
|
+
Self {
|
|
3971
|
+
schema_type: val.schema_type,
|
|
3972
|
+
name: val.name,
|
|
3973
|
+
raw: val.raw,
|
|
3974
|
+
}
|
|
3975
|
+
}
|
|
3976
|
+
}
|
|
3977
|
+
|
|
3978
|
+
impl From<CookieInfo> for kreuzcrawl::CookieInfo {
|
|
3979
|
+
fn from(val: CookieInfo) -> Self {
|
|
3980
|
+
Self {
|
|
3981
|
+
name: val.name,
|
|
3982
|
+
value: val.value,
|
|
3983
|
+
domain: val.domain,
|
|
3984
|
+
path: val.path,
|
|
3985
|
+
}
|
|
3986
|
+
}
|
|
3987
|
+
}
|
|
3988
|
+
|
|
3989
|
+
impl From<kreuzcrawl::CookieInfo> for CookieInfo {
|
|
3990
|
+
fn from(val: kreuzcrawl::CookieInfo) -> Self {
|
|
3991
|
+
Self {
|
|
3992
|
+
name: val.name,
|
|
3993
|
+
value: val.value,
|
|
3994
|
+
domain: val.domain,
|
|
3995
|
+
path: val.path,
|
|
3996
|
+
}
|
|
3997
|
+
}
|
|
3998
|
+
}
|
|
3999
|
+
|
|
4000
|
+
impl From<DownloadedAsset> for kreuzcrawl::DownloadedAsset {
|
|
4001
|
+
fn from(val: DownloadedAsset) -> Self {
|
|
4002
|
+
Self {
|
|
4003
|
+
url: val.url,
|
|
4004
|
+
content_hash: val.content_hash,
|
|
4005
|
+
mime_type: val.mime_type,
|
|
4006
|
+
size: val.size,
|
|
4007
|
+
asset_category: val.asset_category.into(),
|
|
4008
|
+
html_tag: val.html_tag,
|
|
4009
|
+
}
|
|
4010
|
+
}
|
|
4011
|
+
}
|
|
4012
|
+
|
|
4013
|
+
impl From<kreuzcrawl::DownloadedAsset> for DownloadedAsset {
|
|
4014
|
+
fn from(val: kreuzcrawl::DownloadedAsset) -> Self {
|
|
4015
|
+
Self {
|
|
4016
|
+
url: val.url,
|
|
4017
|
+
content_hash: val.content_hash,
|
|
4018
|
+
mime_type: val.mime_type,
|
|
4019
|
+
size: val.size,
|
|
4020
|
+
asset_category: val.asset_category.into(),
|
|
4021
|
+
html_tag: val.html_tag,
|
|
4022
|
+
}
|
|
4023
|
+
}
|
|
4024
|
+
}
|
|
4025
|
+
|
|
4026
|
+
impl From<ArticleMetadata> for kreuzcrawl::ArticleMetadata {
|
|
4027
|
+
fn from(val: ArticleMetadata) -> Self {
|
|
4028
|
+
Self {
|
|
4029
|
+
published_time: val.published_time,
|
|
4030
|
+
modified_time: val.modified_time,
|
|
4031
|
+
author: val.author,
|
|
4032
|
+
section: val.section,
|
|
4033
|
+
tags: val.tags,
|
|
4034
|
+
}
|
|
4035
|
+
}
|
|
4036
|
+
}
|
|
4037
|
+
|
|
4038
|
+
impl From<kreuzcrawl::ArticleMetadata> for ArticleMetadata {
|
|
4039
|
+
fn from(val: kreuzcrawl::ArticleMetadata) -> Self {
|
|
4040
|
+
Self {
|
|
4041
|
+
published_time: val.published_time,
|
|
4042
|
+
modified_time: val.modified_time,
|
|
4043
|
+
author: val.author,
|
|
4044
|
+
section: val.section,
|
|
4045
|
+
tags: val.tags,
|
|
4046
|
+
}
|
|
4047
|
+
}
|
|
4048
|
+
}
|
|
4049
|
+
|
|
4050
|
+
impl From<HreflangEntry> for kreuzcrawl::HreflangEntry {
|
|
4051
|
+
fn from(val: HreflangEntry) -> Self {
|
|
4052
|
+
Self {
|
|
4053
|
+
lang: val.lang,
|
|
4054
|
+
url: val.url,
|
|
4055
|
+
}
|
|
4056
|
+
}
|
|
4057
|
+
}
|
|
4058
|
+
|
|
4059
|
+
impl From<kreuzcrawl::HreflangEntry> for HreflangEntry {
|
|
4060
|
+
fn from(val: kreuzcrawl::HreflangEntry) -> Self {
|
|
4061
|
+
Self {
|
|
4062
|
+
lang: val.lang,
|
|
4063
|
+
url: val.url,
|
|
4064
|
+
}
|
|
4065
|
+
}
|
|
4066
|
+
}
|
|
4067
|
+
|
|
4068
|
+
impl From<FaviconInfo> for kreuzcrawl::FaviconInfo {
|
|
4069
|
+
fn from(val: FaviconInfo) -> Self {
|
|
4070
|
+
Self {
|
|
4071
|
+
url: val.url,
|
|
4072
|
+
rel: val.rel,
|
|
4073
|
+
sizes: val.sizes,
|
|
4074
|
+
mime_type: val.mime_type,
|
|
4075
|
+
}
|
|
4076
|
+
}
|
|
4077
|
+
}
|
|
4078
|
+
|
|
4079
|
+
impl From<kreuzcrawl::FaviconInfo> for FaviconInfo {
|
|
4080
|
+
fn from(val: kreuzcrawl::FaviconInfo) -> Self {
|
|
4081
|
+
Self {
|
|
4082
|
+
url: val.url,
|
|
4083
|
+
rel: val.rel,
|
|
4084
|
+
sizes: val.sizes,
|
|
4085
|
+
mime_type: val.mime_type,
|
|
4086
|
+
}
|
|
4087
|
+
}
|
|
4088
|
+
}
|
|
4089
|
+
|
|
4090
|
+
impl From<HeadingInfo> for kreuzcrawl::HeadingInfo {
|
|
4091
|
+
fn from(val: HeadingInfo) -> Self {
|
|
4092
|
+
Self {
|
|
4093
|
+
level: val.level,
|
|
4094
|
+
text: val.text,
|
|
4095
|
+
}
|
|
4096
|
+
}
|
|
4097
|
+
}
|
|
4098
|
+
|
|
4099
|
+
impl From<kreuzcrawl::HeadingInfo> for HeadingInfo {
|
|
4100
|
+
fn from(val: kreuzcrawl::HeadingInfo) -> Self {
|
|
4101
|
+
Self {
|
|
4102
|
+
level: val.level,
|
|
4103
|
+
text: val.text,
|
|
4104
|
+
}
|
|
4105
|
+
}
|
|
4106
|
+
}
|
|
4107
|
+
|
|
4108
|
+
impl From<ResponseMeta> for kreuzcrawl::ResponseMeta {
|
|
4109
|
+
fn from(val: ResponseMeta) -> Self {
|
|
4110
|
+
Self {
|
|
4111
|
+
etag: val.etag,
|
|
4112
|
+
last_modified: val.last_modified,
|
|
4113
|
+
cache_control: val.cache_control,
|
|
4114
|
+
server: val.server,
|
|
4115
|
+
x_powered_by: val.x_powered_by,
|
|
4116
|
+
content_language: val.content_language,
|
|
4117
|
+
content_encoding: val.content_encoding,
|
|
4118
|
+
}
|
|
4119
|
+
}
|
|
4120
|
+
}
|
|
4121
|
+
|
|
4122
|
+
impl From<kreuzcrawl::ResponseMeta> for ResponseMeta {
|
|
4123
|
+
fn from(val: kreuzcrawl::ResponseMeta) -> Self {
|
|
4124
|
+
Self {
|
|
4125
|
+
etag: val.etag,
|
|
4126
|
+
last_modified: val.last_modified,
|
|
4127
|
+
cache_control: val.cache_control,
|
|
4128
|
+
server: val.server,
|
|
4129
|
+
x_powered_by: val.x_powered_by,
|
|
4130
|
+
content_language: val.content_language,
|
|
4131
|
+
content_encoding: val.content_encoding,
|
|
4132
|
+
}
|
|
4133
|
+
}
|
|
4134
|
+
}
|
|
4135
|
+
|
|
4136
|
+
impl From<PageMetadata> for kreuzcrawl::PageMetadata {
|
|
4137
|
+
fn from(val: PageMetadata) -> Self {
|
|
4138
|
+
Self {
|
|
4139
|
+
title: val.title,
|
|
4140
|
+
description: val.description,
|
|
4141
|
+
canonical_url: val.canonical_url,
|
|
4142
|
+
keywords: val.keywords,
|
|
4143
|
+
author: val.author,
|
|
4144
|
+
viewport: val.viewport,
|
|
4145
|
+
theme_color: val.theme_color,
|
|
4146
|
+
generator: val.generator,
|
|
4147
|
+
robots: val.robots,
|
|
4148
|
+
html_lang: val.html_lang,
|
|
4149
|
+
html_dir: val.html_dir,
|
|
4150
|
+
og_title: val.og_title,
|
|
4151
|
+
og_type: val.og_type,
|
|
4152
|
+
og_image: val.og_image,
|
|
4153
|
+
og_description: val.og_description,
|
|
4154
|
+
og_url: val.og_url,
|
|
4155
|
+
og_site_name: val.og_site_name,
|
|
4156
|
+
og_locale: val.og_locale,
|
|
4157
|
+
og_video: val.og_video,
|
|
4158
|
+
og_audio: val.og_audio,
|
|
4159
|
+
og_locale_alternates: val.og_locale_alternates,
|
|
4160
|
+
twitter_card: val.twitter_card,
|
|
4161
|
+
twitter_title: val.twitter_title,
|
|
4162
|
+
twitter_description: val.twitter_description,
|
|
4163
|
+
twitter_image: val.twitter_image,
|
|
4164
|
+
twitter_site: val.twitter_site,
|
|
4165
|
+
twitter_creator: val.twitter_creator,
|
|
4166
|
+
dc_title: val.dc_title,
|
|
4167
|
+
dc_creator: val.dc_creator,
|
|
4168
|
+
dc_subject: val.dc_subject,
|
|
4169
|
+
dc_description: val.dc_description,
|
|
4170
|
+
dc_publisher: val.dc_publisher,
|
|
4171
|
+
dc_date: val.dc_date,
|
|
4172
|
+
dc_type: val.dc_type,
|
|
4173
|
+
dc_format: val.dc_format,
|
|
4174
|
+
dc_identifier: val.dc_identifier,
|
|
4175
|
+
dc_language: val.dc_language,
|
|
4176
|
+
dc_rights: val.dc_rights,
|
|
4177
|
+
article: val.article.map(Into::into),
|
|
4178
|
+
hreflangs: val.hreflangs.map(|v| v.into_iter().map(Into::into).collect()),
|
|
4179
|
+
favicons: val.favicons.map(|v| v.into_iter().map(Into::into).collect()),
|
|
4180
|
+
headings: val.headings.map(|v| v.into_iter().map(Into::into).collect()),
|
|
4181
|
+
word_count: val.word_count,
|
|
4182
|
+
}
|
|
4183
|
+
}
|
|
4184
|
+
}
|
|
4185
|
+
|
|
4186
|
+
impl From<kreuzcrawl::PageMetadata> for PageMetadata {
|
|
4187
|
+
fn from(val: kreuzcrawl::PageMetadata) -> Self {
|
|
4188
|
+
Self {
|
|
4189
|
+
title: val.title,
|
|
4190
|
+
description: val.description,
|
|
4191
|
+
canonical_url: val.canonical_url,
|
|
4192
|
+
keywords: val.keywords,
|
|
4193
|
+
author: val.author,
|
|
4194
|
+
viewport: val.viewport,
|
|
4195
|
+
theme_color: val.theme_color,
|
|
4196
|
+
generator: val.generator,
|
|
4197
|
+
robots: val.robots,
|
|
4198
|
+
html_lang: val.html_lang,
|
|
4199
|
+
html_dir: val.html_dir,
|
|
4200
|
+
og_title: val.og_title,
|
|
4201
|
+
og_type: val.og_type,
|
|
4202
|
+
og_image: val.og_image,
|
|
4203
|
+
og_description: val.og_description,
|
|
4204
|
+
og_url: val.og_url,
|
|
4205
|
+
og_site_name: val.og_site_name,
|
|
4206
|
+
og_locale: val.og_locale,
|
|
4207
|
+
og_video: val.og_video,
|
|
4208
|
+
og_audio: val.og_audio,
|
|
4209
|
+
og_locale_alternates: val.og_locale_alternates,
|
|
4210
|
+
twitter_card: val.twitter_card,
|
|
4211
|
+
twitter_title: val.twitter_title,
|
|
4212
|
+
twitter_description: val.twitter_description,
|
|
4213
|
+
twitter_image: val.twitter_image,
|
|
4214
|
+
twitter_site: val.twitter_site,
|
|
4215
|
+
twitter_creator: val.twitter_creator,
|
|
4216
|
+
dc_title: val.dc_title,
|
|
4217
|
+
dc_creator: val.dc_creator,
|
|
4218
|
+
dc_subject: val.dc_subject,
|
|
4219
|
+
dc_description: val.dc_description,
|
|
4220
|
+
dc_publisher: val.dc_publisher,
|
|
4221
|
+
dc_date: val.dc_date,
|
|
4222
|
+
dc_type: val.dc_type,
|
|
4223
|
+
dc_format: val.dc_format,
|
|
4224
|
+
dc_identifier: val.dc_identifier,
|
|
4225
|
+
dc_language: val.dc_language,
|
|
4226
|
+
dc_rights: val.dc_rights,
|
|
4227
|
+
article: val.article.map(Into::into),
|
|
4228
|
+
hreflangs: val.hreflangs.map(|v| v.into_iter().map(Into::into).collect()),
|
|
4229
|
+
favicons: val.favicons.map(|v| v.into_iter().map(Into::into).collect()),
|
|
4230
|
+
headings: val.headings.map(|v| v.into_iter().map(Into::into).collect()),
|
|
4231
|
+
word_count: val.word_count,
|
|
4232
|
+
}
|
|
4233
|
+
}
|
|
4234
|
+
}
|
|
4235
|
+
|
|
4236
|
+
impl From<CitationResult> for kreuzcrawl::CitationResult {
|
|
4237
|
+
fn from(val: CitationResult) -> Self {
|
|
4238
|
+
Self {
|
|
4239
|
+
content: val.content,
|
|
4240
|
+
references: val.references.into_iter().map(Into::into).collect(),
|
|
4241
|
+
}
|
|
4242
|
+
}
|
|
4243
|
+
}
|
|
4244
|
+
|
|
4245
|
+
impl From<kreuzcrawl::CitationResult> for CitationResult {
|
|
4246
|
+
fn from(val: kreuzcrawl::CitationResult) -> Self {
|
|
4247
|
+
Self {
|
|
4248
|
+
content: val.content,
|
|
4249
|
+
references: val.references.into_iter().map(Into::into).collect(),
|
|
4250
|
+
}
|
|
4251
|
+
}
|
|
4252
|
+
}
|
|
4253
|
+
|
|
4254
|
+
impl From<CitationReference> for kreuzcrawl::CitationReference {
|
|
4255
|
+
fn from(val: CitationReference) -> Self {
|
|
4256
|
+
Self {
|
|
4257
|
+
index: val.index,
|
|
4258
|
+
url: val.url,
|
|
4259
|
+
text: val.text,
|
|
4260
|
+
}
|
|
4261
|
+
}
|
|
4262
|
+
}
|
|
4263
|
+
|
|
4264
|
+
impl From<kreuzcrawl::CitationReference> for CitationReference {
|
|
4265
|
+
fn from(val: kreuzcrawl::CitationReference) -> Self {
|
|
4266
|
+
Self {
|
|
4267
|
+
index: val.index,
|
|
4268
|
+
url: val.url,
|
|
4269
|
+
text: val.text,
|
|
4270
|
+
}
|
|
4271
|
+
}
|
|
4272
|
+
}
|
|
4273
|
+
|
|
4274
|
+
impl From<BatchScrapeResult> for kreuzcrawl::BatchScrapeResult {
|
|
4275
|
+
fn from(val: BatchScrapeResult) -> Self {
|
|
4276
|
+
Self {
|
|
4277
|
+
url: val.url,
|
|
4278
|
+
result: val.result.map(Into::into),
|
|
4279
|
+
error: val.error,
|
|
4280
|
+
}
|
|
4281
|
+
}
|
|
4282
|
+
}
|
|
4283
|
+
|
|
4284
|
+
impl From<kreuzcrawl::BatchScrapeResult> for BatchScrapeResult {
|
|
4285
|
+
fn from(val: kreuzcrawl::BatchScrapeResult) -> Self {
|
|
4286
|
+
Self {
|
|
4287
|
+
url: val.url,
|
|
4288
|
+
result: val.result.map(Into::into),
|
|
4289
|
+
error: val.error,
|
|
4290
|
+
}
|
|
4291
|
+
}
|
|
4292
|
+
}
|
|
4293
|
+
|
|
4294
|
+
impl From<BatchCrawlResult> for kreuzcrawl::BatchCrawlResult {
|
|
4295
|
+
fn from(val: BatchCrawlResult) -> Self {
|
|
4296
|
+
Self {
|
|
4297
|
+
url: val.url,
|
|
4298
|
+
result: val.result.map(Into::into),
|
|
4299
|
+
error: val.error,
|
|
4300
|
+
}
|
|
4301
|
+
}
|
|
4302
|
+
}
|
|
4303
|
+
|
|
4304
|
+
impl From<kreuzcrawl::BatchCrawlResult> for BatchCrawlResult {
|
|
4305
|
+
fn from(val: kreuzcrawl::BatchCrawlResult) -> Self {
|
|
4306
|
+
Self {
|
|
4307
|
+
url: val.url,
|
|
4308
|
+
result: val.result.map(Into::into),
|
|
4309
|
+
error: val.error,
|
|
4310
|
+
}
|
|
4311
|
+
}
|
|
4312
|
+
}
|
|
4313
|
+
|
|
4314
|
+
impl From<BrowserMode> for kreuzcrawl::BrowserMode {
|
|
4315
|
+
fn from(val: BrowserMode) -> Self {
|
|
4316
|
+
match val {
|
|
4317
|
+
BrowserMode::Auto => Self::Auto,
|
|
4318
|
+
BrowserMode::Always => Self::Always,
|
|
4319
|
+
BrowserMode::Never => Self::Never,
|
|
4320
|
+
}
|
|
4321
|
+
}
|
|
4322
|
+
}
|
|
4323
|
+
|
|
4324
|
+
impl From<kreuzcrawl::BrowserMode> for BrowserMode {
|
|
4325
|
+
fn from(val: kreuzcrawl::BrowserMode) -> Self {
|
|
4326
|
+
match val {
|
|
4327
|
+
kreuzcrawl::BrowserMode::Auto => Self::Auto,
|
|
4328
|
+
kreuzcrawl::BrowserMode::Always => Self::Always,
|
|
4329
|
+
kreuzcrawl::BrowserMode::Never => Self::Never,
|
|
4330
|
+
}
|
|
4331
|
+
}
|
|
4332
|
+
}
|
|
4333
|
+
|
|
4334
|
+
impl From<BrowserWait> for kreuzcrawl::BrowserWait {
|
|
4335
|
+
fn from(val: BrowserWait) -> Self {
|
|
4336
|
+
match val {
|
|
4337
|
+
BrowserWait::NetworkIdle => Self::NetworkIdle,
|
|
4338
|
+
BrowserWait::Selector => Self::Selector,
|
|
4339
|
+
BrowserWait::Fixed => Self::Fixed,
|
|
4340
|
+
}
|
|
4341
|
+
}
|
|
4342
|
+
}
|
|
4343
|
+
|
|
4344
|
+
impl From<kreuzcrawl::BrowserWait> for BrowserWait {
|
|
4345
|
+
fn from(val: kreuzcrawl::BrowserWait) -> Self {
|
|
4346
|
+
match val {
|
|
4347
|
+
kreuzcrawl::BrowserWait::NetworkIdle => Self::NetworkIdle,
|
|
4348
|
+
kreuzcrawl::BrowserWait::Selector => Self::Selector,
|
|
4349
|
+
kreuzcrawl::BrowserWait::Fixed => Self::Fixed,
|
|
4350
|
+
}
|
|
4351
|
+
}
|
|
4352
|
+
}
|
|
4353
|
+
|
|
4354
|
+
impl From<AuthConfig> for kreuzcrawl::AuthConfig {
|
|
4355
|
+
fn from(val: AuthConfig) -> Self {
|
|
4356
|
+
match val {
|
|
4357
|
+
AuthConfig::Basic { username, password } => Self::Basic { username, password },
|
|
4358
|
+
AuthConfig::Bearer { token } => Self::Bearer { token },
|
|
4359
|
+
AuthConfig::Header { name, value } => Self::Header { name, value },
|
|
4360
|
+
}
|
|
4361
|
+
}
|
|
4362
|
+
}
|
|
4363
|
+
|
|
4364
|
+
impl From<kreuzcrawl::AuthConfig> for AuthConfig {
|
|
4365
|
+
fn from(val: kreuzcrawl::AuthConfig) -> Self {
|
|
4366
|
+
match val {
|
|
4367
|
+
kreuzcrawl::AuthConfig::Basic { username, password } => Self::Basic { username, password },
|
|
4368
|
+
kreuzcrawl::AuthConfig::Bearer { token } => Self::Bearer { token },
|
|
4369
|
+
kreuzcrawl::AuthConfig::Header { name, value } => Self::Header { name, value },
|
|
4370
|
+
}
|
|
4371
|
+
}
|
|
4372
|
+
}
|
|
4373
|
+
|
|
4374
|
+
impl From<LinkType> for kreuzcrawl::LinkType {
|
|
4375
|
+
fn from(val: LinkType) -> Self {
|
|
4376
|
+
match val {
|
|
4377
|
+
LinkType::Internal => Self::Internal,
|
|
4378
|
+
LinkType::External => Self::External,
|
|
4379
|
+
LinkType::Anchor => Self::Anchor,
|
|
4380
|
+
LinkType::Document => Self::Document,
|
|
4381
|
+
}
|
|
4382
|
+
}
|
|
4383
|
+
}
|
|
4384
|
+
|
|
4385
|
+
impl From<kreuzcrawl::LinkType> for LinkType {
|
|
4386
|
+
fn from(val: kreuzcrawl::LinkType) -> Self {
|
|
4387
|
+
match val {
|
|
4388
|
+
kreuzcrawl::LinkType::Internal => Self::Internal,
|
|
4389
|
+
kreuzcrawl::LinkType::External => Self::External,
|
|
4390
|
+
kreuzcrawl::LinkType::Anchor => Self::Anchor,
|
|
4391
|
+
kreuzcrawl::LinkType::Document => Self::Document,
|
|
4392
|
+
}
|
|
4393
|
+
}
|
|
4394
|
+
}
|
|
4395
|
+
|
|
4396
|
+
impl From<ImageSource> for kreuzcrawl::ImageSource {
|
|
4397
|
+
fn from(val: ImageSource) -> Self {
|
|
4398
|
+
match val {
|
|
4399
|
+
ImageSource::Img => Self::Img,
|
|
4400
|
+
ImageSource::PictureSource => Self::PictureSource,
|
|
4401
|
+
ImageSource::OgImage => Self::OgImage,
|
|
4402
|
+
ImageSource::TwitterImage => Self::TwitterImage,
|
|
4403
|
+
}
|
|
4404
|
+
}
|
|
4405
|
+
}
|
|
4406
|
+
|
|
4407
|
+
impl From<kreuzcrawl::ImageSource> for ImageSource {
|
|
4408
|
+
fn from(val: kreuzcrawl::ImageSource) -> Self {
|
|
4409
|
+
match val {
|
|
4410
|
+
kreuzcrawl::ImageSource::Img => Self::Img,
|
|
4411
|
+
kreuzcrawl::ImageSource::PictureSource => Self::PictureSource,
|
|
4412
|
+
kreuzcrawl::ImageSource::OgImage => Self::OgImage,
|
|
4413
|
+
kreuzcrawl::ImageSource::TwitterImage => Self::TwitterImage,
|
|
4414
|
+
}
|
|
4415
|
+
}
|
|
4416
|
+
}
|
|
4417
|
+
|
|
4418
|
+
impl From<FeedType> for kreuzcrawl::FeedType {
|
|
4419
|
+
fn from(val: FeedType) -> Self {
|
|
4420
|
+
match val {
|
|
4421
|
+
FeedType::Rss => Self::Rss,
|
|
4422
|
+
FeedType::Atom => Self::Atom,
|
|
4423
|
+
FeedType::JsonFeed => Self::JsonFeed,
|
|
4424
|
+
}
|
|
4425
|
+
}
|
|
4426
|
+
}
|
|
4427
|
+
|
|
4428
|
+
impl From<kreuzcrawl::FeedType> for FeedType {
|
|
4429
|
+
fn from(val: kreuzcrawl::FeedType) -> Self {
|
|
4430
|
+
match val {
|
|
4431
|
+
kreuzcrawl::FeedType::Rss => Self::Rss,
|
|
4432
|
+
kreuzcrawl::FeedType::Atom => Self::Atom,
|
|
4433
|
+
kreuzcrawl::FeedType::JsonFeed => Self::JsonFeed,
|
|
4434
|
+
}
|
|
4435
|
+
}
|
|
4436
|
+
}
|
|
4437
|
+
|
|
4438
|
+
impl From<AssetCategory> for kreuzcrawl::AssetCategory {
|
|
4439
|
+
fn from(val: AssetCategory) -> Self {
|
|
4440
|
+
match val {
|
|
4441
|
+
AssetCategory::Document => Self::Document,
|
|
4442
|
+
AssetCategory::Image => Self::Image,
|
|
4443
|
+
AssetCategory::Audio => Self::Audio,
|
|
4444
|
+
AssetCategory::Video => Self::Video,
|
|
4445
|
+
AssetCategory::Font => Self::Font,
|
|
4446
|
+
AssetCategory::Stylesheet => Self::Stylesheet,
|
|
4447
|
+
AssetCategory::Script => Self::Script,
|
|
4448
|
+
AssetCategory::Archive => Self::Archive,
|
|
4449
|
+
AssetCategory::Data => Self::Data,
|
|
4450
|
+
AssetCategory::Other => Self::Other,
|
|
4451
|
+
}
|
|
4452
|
+
}
|
|
4453
|
+
}
|
|
4454
|
+
|
|
4455
|
+
impl From<kreuzcrawl::AssetCategory> for AssetCategory {
|
|
4456
|
+
fn from(val: kreuzcrawl::AssetCategory) -> Self {
|
|
4457
|
+
match val {
|
|
4458
|
+
kreuzcrawl::AssetCategory::Document => Self::Document,
|
|
4459
|
+
kreuzcrawl::AssetCategory::Image => Self::Image,
|
|
4460
|
+
kreuzcrawl::AssetCategory::Audio => Self::Audio,
|
|
4461
|
+
kreuzcrawl::AssetCategory::Video => Self::Video,
|
|
4462
|
+
kreuzcrawl::AssetCategory::Font => Self::Font,
|
|
4463
|
+
kreuzcrawl::AssetCategory::Stylesheet => Self::Stylesheet,
|
|
4464
|
+
kreuzcrawl::AssetCategory::Script => Self::Script,
|
|
4465
|
+
kreuzcrawl::AssetCategory::Archive => Self::Archive,
|
|
4466
|
+
kreuzcrawl::AssetCategory::Data => Self::Data,
|
|
4467
|
+
kreuzcrawl::AssetCategory::Other => Self::Other,
|
|
4468
|
+
}
|
|
4469
|
+
}
|
|
4470
|
+
}
|
|
4471
|
+
|
|
4472
|
+
impl From<kreuzcrawl::CrawlEvent> for CrawlEvent {
|
|
4473
|
+
fn from(val: kreuzcrawl::CrawlEvent) -> Self {
|
|
4474
|
+
match val {
|
|
4475
|
+
kreuzcrawl::CrawlEvent::Page(_0) => Self::Page { _0: (*_0).into() },
|
|
4476
|
+
kreuzcrawl::CrawlEvent::Error { url, error } => Self::Error { url, error },
|
|
4477
|
+
kreuzcrawl::CrawlEvent::Complete { pages_crawled } => Self::Complete { pages_crawled },
|
|
4478
|
+
}
|
|
4479
|
+
}
|
|
4480
|
+
}
|
|
4481
|
+
|
|
4482
|
+
/// Convert a `kreuzcrawl::CrawlError` error to a Magnus runtime error.
|
|
4483
|
+
#[allow(dead_code)]
|
|
4484
|
+
fn crawl_error_to_magnus_err(e: kreuzcrawl::CrawlError) -> magnus::Error {
|
|
4485
|
+
let msg = e.to_string();
|
|
4486
|
+
magnus::Error::new(unsafe { magnus::Ruby::get_unchecked() }.exception_runtime_error(), msg)
|
|
4487
|
+
}
|
|
4488
|
+
|
|
4489
|
+
#[magnus::init]
|
|
4490
|
+
fn init(ruby: &Ruby) -> Result<(), Error> {
|
|
4491
|
+
let module = ruby.define_module("Kreuzcrawl")?;
|
|
4492
|
+
|
|
4493
|
+
let class = module.define_class("ExtractionMeta", ruby.class_object())?;
|
|
4494
|
+
class.define_singleton_method("new", function!(ExtractionMeta::new, 5))?;
|
|
4495
|
+
class.define_method("cost", method!(ExtractionMeta::cost, 0))?;
|
|
4496
|
+
class.define_method("prompt_tokens", method!(ExtractionMeta::prompt_tokens, 0))?;
|
|
4497
|
+
class.define_method("completion_tokens", method!(ExtractionMeta::completion_tokens, 0))?;
|
|
4498
|
+
class.define_method("model", method!(ExtractionMeta::model, 0))?;
|
|
4499
|
+
class.define_method("chunks_processed", method!(ExtractionMeta::chunks_processed, 0))?;
|
|
4500
|
+
|
|
4501
|
+
let class = module.define_class("ProxyConfig", ruby.class_object())?;
|
|
4502
|
+
class.define_singleton_method("new", function!(ProxyConfig::new, 3))?;
|
|
4503
|
+
class.define_method("url", method!(ProxyConfig::url, 0))?;
|
|
4504
|
+
class.define_method("username", method!(ProxyConfig::username, 0))?;
|
|
4505
|
+
class.define_method("password", method!(ProxyConfig::password, 0))?;
|
|
4506
|
+
|
|
4507
|
+
let class = module.define_class("BrowserConfig", ruby.class_object())?;
|
|
4508
|
+
class.define_singleton_method("new", function!(BrowserConfig::new, 6))?;
|
|
4509
|
+
class.define_method("mode", method!(BrowserConfig::mode, 0))?;
|
|
4510
|
+
class.define_method("endpoint", method!(BrowserConfig::endpoint, 0))?;
|
|
4511
|
+
class.define_method("timeout", method!(BrowserConfig::timeout, 0))?;
|
|
4512
|
+
class.define_method("wait", method!(BrowserConfig::wait, 0))?;
|
|
4513
|
+
class.define_method("wait_selector", method!(BrowserConfig::wait_selector, 0))?;
|
|
4514
|
+
class.define_method("extra_wait", method!(BrowserConfig::extra_wait, 0))?;
|
|
4515
|
+
|
|
4516
|
+
let class = module.define_class("CrawlConfig", ruby.class_object())?;
|
|
4517
|
+
class.define_singleton_method("new", function!(CrawlConfig::new, 1))?;
|
|
4518
|
+
class.define_method("max_depth", method!(CrawlConfig::max_depth, 0))?;
|
|
4519
|
+
class.define_method("max_pages", method!(CrawlConfig::max_pages, 0))?;
|
|
4520
|
+
class.define_method("max_concurrent", method!(CrawlConfig::max_concurrent, 0))?;
|
|
4521
|
+
class.define_method("respect_robots_txt", method!(CrawlConfig::respect_robots_txt, 0))?;
|
|
4522
|
+
class.define_method("user_agent", method!(CrawlConfig::user_agent, 0))?;
|
|
4523
|
+
class.define_method("stay_on_domain", method!(CrawlConfig::stay_on_domain, 0))?;
|
|
4524
|
+
class.define_method("allow_subdomains", method!(CrawlConfig::allow_subdomains, 0))?;
|
|
4525
|
+
class.define_method("include_paths", method!(CrawlConfig::include_paths, 0))?;
|
|
4526
|
+
class.define_method("exclude_paths", method!(CrawlConfig::exclude_paths, 0))?;
|
|
4527
|
+
class.define_method("custom_headers", method!(CrawlConfig::custom_headers, 0))?;
|
|
4528
|
+
class.define_method("request_timeout", method!(CrawlConfig::request_timeout, 0))?;
|
|
4529
|
+
class.define_method("max_redirects", method!(CrawlConfig::max_redirects, 0))?;
|
|
4530
|
+
class.define_method("retry_count", method!(CrawlConfig::retry_count, 0))?;
|
|
4531
|
+
class.define_method("retry_codes", method!(CrawlConfig::retry_codes, 0))?;
|
|
4532
|
+
class.define_method("cookies_enabled", method!(CrawlConfig::cookies_enabled, 0))?;
|
|
4533
|
+
class.define_method("auth", method!(CrawlConfig::auth, 0))?;
|
|
4534
|
+
class.define_method("max_body_size", method!(CrawlConfig::max_body_size, 0))?;
|
|
4535
|
+
class.define_method("main_content_only", method!(CrawlConfig::main_content_only, 0))?;
|
|
4536
|
+
class.define_method("remove_tags", method!(CrawlConfig::remove_tags, 0))?;
|
|
4537
|
+
class.define_method("map_limit", method!(CrawlConfig::map_limit, 0))?;
|
|
4538
|
+
class.define_method("map_search", method!(CrawlConfig::map_search, 0))?;
|
|
4539
|
+
class.define_method("download_assets", method!(CrawlConfig::download_assets, 0))?;
|
|
4540
|
+
class.define_method("asset_types", method!(CrawlConfig::asset_types, 0))?;
|
|
4541
|
+
class.define_method("max_asset_size", method!(CrawlConfig::max_asset_size, 0))?;
|
|
4542
|
+
class.define_method("browser", method!(CrawlConfig::browser, 0))?;
|
|
4543
|
+
class.define_method("proxy", method!(CrawlConfig::proxy, 0))?;
|
|
4544
|
+
class.define_method("user_agents", method!(CrawlConfig::user_agents, 0))?;
|
|
4545
|
+
class.define_method("capture_screenshot", method!(CrawlConfig::capture_screenshot, 0))?;
|
|
4546
|
+
class.define_method("download_documents", method!(CrawlConfig::download_documents, 0))?;
|
|
4547
|
+
class.define_method("document_max_size", method!(CrawlConfig::document_max_size, 0))?;
|
|
4548
|
+
class.define_method("document_mime_types", method!(CrawlConfig::document_mime_types, 0))?;
|
|
4549
|
+
class.define_method("warc_output", method!(CrawlConfig::warc_output, 0))?;
|
|
4550
|
+
class.define_method("browser_profile", method!(CrawlConfig::browser_profile, 0))?;
|
|
4551
|
+
class.define_method("save_browser_profile", method!(CrawlConfig::save_browser_profile, 0))?;
|
|
4552
|
+
|
|
4553
|
+
let class = module.define_class("DownloadedDocument", ruby.class_object())?;
|
|
4554
|
+
class.define_singleton_method("new", function!(DownloadedDocument::new, 7))?;
|
|
4555
|
+
class.define_method("url", method!(DownloadedDocument::url, 0))?;
|
|
4556
|
+
class.define_method("mime_type", method!(DownloadedDocument::mime_type, 0))?;
|
|
4557
|
+
class.define_method("content", method!(DownloadedDocument::content, 0))?;
|
|
4558
|
+
class.define_method("size", method!(DownloadedDocument::size, 0))?;
|
|
4559
|
+
class.define_method("filename", method!(DownloadedDocument::filename, 0))?;
|
|
4560
|
+
class.define_method("content_hash", method!(DownloadedDocument::content_hash, 0))?;
|
|
4561
|
+
class.define_method("headers", method!(DownloadedDocument::headers, 0))?;
|
|
4562
|
+
|
|
4563
|
+
let class = module.define_class("InteractionResult", ruby.class_object())?;
|
|
4564
|
+
class.define_singleton_method("new", function!(InteractionResult::new, 4))?;
|
|
4565
|
+
class.define_method("action_results", method!(InteractionResult::action_results, 0))?;
|
|
4566
|
+
class.define_method("final_html", method!(InteractionResult::final_html, 0))?;
|
|
4567
|
+
class.define_method("final_url", method!(InteractionResult::final_url, 0))?;
|
|
4568
|
+
class.define_method("screenshot", method!(InteractionResult::screenshot, 0))?;
|
|
4569
|
+
|
|
4570
|
+
let class = module.define_class("ActionResult", ruby.class_object())?;
|
|
4571
|
+
class.define_singleton_method("new", function!(ActionResult::new, 5))?;
|
|
4572
|
+
class.define_method("action_index", method!(ActionResult::action_index, 0))?;
|
|
4573
|
+
class.define_method("action_type", method!(ActionResult::action_type, 0))?;
|
|
4574
|
+
class.define_method("success", method!(ActionResult::success, 0))?;
|
|
4575
|
+
class.define_method("data", method!(ActionResult::data, 0))?;
|
|
4576
|
+
class.define_method("error", method!(ActionResult::error, 0))?;
|
|
4577
|
+
|
|
4578
|
+
let class = module.define_class("ScrapeResult", ruby.class_object())?;
|
|
4579
|
+
class.define_singleton_method("new", function!(ScrapeResult::new, 1))?;
|
|
4580
|
+
class.define_method("status_code", method!(ScrapeResult::status_code, 0))?;
|
|
4581
|
+
class.define_method("content_type", method!(ScrapeResult::content_type, 0))?;
|
|
4582
|
+
class.define_method("html", method!(ScrapeResult::html, 0))?;
|
|
4583
|
+
class.define_method("body_size", method!(ScrapeResult::body_size, 0))?;
|
|
4584
|
+
class.define_method("metadata", method!(ScrapeResult::metadata, 0))?;
|
|
4585
|
+
class.define_method("links", method!(ScrapeResult::links, 0))?;
|
|
4586
|
+
class.define_method("images", method!(ScrapeResult::images, 0))?;
|
|
4587
|
+
class.define_method("feeds", method!(ScrapeResult::feeds, 0))?;
|
|
4588
|
+
class.define_method("json_ld", method!(ScrapeResult::json_ld, 0))?;
|
|
4589
|
+
class.define_method("is_allowed", method!(ScrapeResult::is_allowed, 0))?;
|
|
4590
|
+
class.define_method("crawl_delay", method!(ScrapeResult::crawl_delay, 0))?;
|
|
4591
|
+
class.define_method("noindex_detected", method!(ScrapeResult::noindex_detected, 0))?;
|
|
4592
|
+
class.define_method("nofollow_detected", method!(ScrapeResult::nofollow_detected, 0))?;
|
|
4593
|
+
class.define_method("x_robots_tag", method!(ScrapeResult::x_robots_tag, 0))?;
|
|
4594
|
+
class.define_method("is_pdf", method!(ScrapeResult::is_pdf, 0))?;
|
|
4595
|
+
class.define_method("was_skipped", method!(ScrapeResult::was_skipped, 0))?;
|
|
4596
|
+
class.define_method("detected_charset", method!(ScrapeResult::detected_charset, 0))?;
|
|
4597
|
+
class.define_method("main_content_only", method!(ScrapeResult::main_content_only, 0))?;
|
|
4598
|
+
class.define_method("auth_header_sent", method!(ScrapeResult::auth_header_sent, 0))?;
|
|
4599
|
+
class.define_method("response_meta", method!(ScrapeResult::response_meta, 0))?;
|
|
4600
|
+
class.define_method("assets", method!(ScrapeResult::assets, 0))?;
|
|
4601
|
+
class.define_method("js_render_hint", method!(ScrapeResult::js_render_hint, 0))?;
|
|
4602
|
+
class.define_method("browser_used", method!(ScrapeResult::browser_used, 0))?;
|
|
4603
|
+
class.define_method("markdown", method!(ScrapeResult::markdown, 0))?;
|
|
4604
|
+
class.define_method("extracted_data", method!(ScrapeResult::extracted_data, 0))?;
|
|
4605
|
+
class.define_method("extraction_meta", method!(ScrapeResult::extraction_meta, 0))?;
|
|
4606
|
+
class.define_method("screenshot", method!(ScrapeResult::screenshot, 0))?;
|
|
4607
|
+
class.define_method("downloaded_document", method!(ScrapeResult::downloaded_document, 0))?;
|
|
4608
|
+
|
|
4609
|
+
let class = module.define_class("CrawlPageResult", ruby.class_object())?;
|
|
4610
|
+
class.define_singleton_method("new", function!(CrawlPageResult::new, 1))?;
|
|
4611
|
+
class.define_method("url", method!(CrawlPageResult::url, 0))?;
|
|
4612
|
+
class.define_method("normalized_url", method!(CrawlPageResult::normalized_url, 0))?;
|
|
4613
|
+
class.define_method("status_code", method!(CrawlPageResult::status_code, 0))?;
|
|
4614
|
+
class.define_method("content_type", method!(CrawlPageResult::content_type, 0))?;
|
|
4615
|
+
class.define_method("html", method!(CrawlPageResult::html, 0))?;
|
|
4616
|
+
class.define_method("body_size", method!(CrawlPageResult::body_size, 0))?;
|
|
4617
|
+
class.define_method("metadata", method!(CrawlPageResult::metadata, 0))?;
|
|
4618
|
+
class.define_method("links", method!(CrawlPageResult::links, 0))?;
|
|
4619
|
+
class.define_method("images", method!(CrawlPageResult::images, 0))?;
|
|
4620
|
+
class.define_method("feeds", method!(CrawlPageResult::feeds, 0))?;
|
|
4621
|
+
class.define_method("json_ld", method!(CrawlPageResult::json_ld, 0))?;
|
|
4622
|
+
class.define_method("depth", method!(CrawlPageResult::depth, 0))?;
|
|
4623
|
+
class.define_method("stayed_on_domain", method!(CrawlPageResult::stayed_on_domain, 0))?;
|
|
4624
|
+
class.define_method("was_skipped", method!(CrawlPageResult::was_skipped, 0))?;
|
|
4625
|
+
class.define_method("is_pdf", method!(CrawlPageResult::is_pdf, 0))?;
|
|
4626
|
+
class.define_method("detected_charset", method!(CrawlPageResult::detected_charset, 0))?;
|
|
4627
|
+
class.define_method("markdown", method!(CrawlPageResult::markdown, 0))?;
|
|
4628
|
+
class.define_method("extracted_data", method!(CrawlPageResult::extracted_data, 0))?;
|
|
4629
|
+
class.define_method("extraction_meta", method!(CrawlPageResult::extraction_meta, 0))?;
|
|
4630
|
+
class.define_method("downloaded_document", method!(CrawlPageResult::downloaded_document, 0))?;
|
|
4631
|
+
|
|
4632
|
+
let class = module.define_class("CrawlResult", ruby.class_object())?;
|
|
4633
|
+
class.define_singleton_method("new", function!(CrawlResult::new, 7))?;
|
|
4634
|
+
class.define_method("pages", method!(CrawlResult::pages, 0))?;
|
|
4635
|
+
class.define_method("final_url", method!(CrawlResult::final_url, 0))?;
|
|
4636
|
+
class.define_method("redirect_count", method!(CrawlResult::redirect_count, 0))?;
|
|
4637
|
+
class.define_method("was_skipped", method!(CrawlResult::was_skipped, 0))?;
|
|
4638
|
+
class.define_method("error", method!(CrawlResult::error, 0))?;
|
|
4639
|
+
class.define_method("cookies", method!(CrawlResult::cookies, 0))?;
|
|
4640
|
+
class.define_method("normalized_urls", method!(CrawlResult::normalized_urls, 0))?;
|
|
4641
|
+
|
|
4642
|
+
let class = module.define_class("SitemapUrl", ruby.class_object())?;
|
|
4643
|
+
class.define_singleton_method("new", function!(SitemapUrl::new, 4))?;
|
|
4644
|
+
class.define_method("url", method!(SitemapUrl::url, 0))?;
|
|
4645
|
+
class.define_method("lastmod", method!(SitemapUrl::lastmod, 0))?;
|
|
4646
|
+
class.define_method("changefreq", method!(SitemapUrl::changefreq, 0))?;
|
|
4647
|
+
class.define_method("priority", method!(SitemapUrl::priority, 0))?;
|
|
4648
|
+
|
|
4649
|
+
let class = module.define_class("MapResult", ruby.class_object())?;
|
|
4650
|
+
class.define_singleton_method("new", function!(MapResult::new, 1))?;
|
|
4651
|
+
class.define_method("urls", method!(MapResult::urls, 0))?;
|
|
4652
|
+
|
|
4653
|
+
let class = module.define_class("MarkdownResult", ruby.class_object())?;
|
|
4654
|
+
class.define_singleton_method("new", function!(MarkdownResult::new, 6))?;
|
|
4655
|
+
class.define_method("content", method!(MarkdownResult::content, 0))?;
|
|
4656
|
+
class.define_method("document_structure", method!(MarkdownResult::document_structure, 0))?;
|
|
4657
|
+
class.define_method("tables", method!(MarkdownResult::tables, 0))?;
|
|
4658
|
+
class.define_method("warnings", method!(MarkdownResult::warnings, 0))?;
|
|
4659
|
+
class.define_method("citations", method!(MarkdownResult::citations, 0))?;
|
|
4660
|
+
class.define_method("fit_content", method!(MarkdownResult::fit_content, 0))?;
|
|
4661
|
+
|
|
4662
|
+
let class = module.define_class("CachedPage", ruby.class_object())?;
|
|
4663
|
+
class.define_singleton_method("new", function!(CachedPage::new, 7))?;
|
|
4664
|
+
class.define_method("url", method!(CachedPage::url, 0))?;
|
|
4665
|
+
class.define_method("status_code", method!(CachedPage::status_code, 0))?;
|
|
4666
|
+
class.define_method("content_type", method!(CachedPage::content_type, 0))?;
|
|
4667
|
+
class.define_method("body", method!(CachedPage::body, 0))?;
|
|
4668
|
+
class.define_method("etag", method!(CachedPage::etag, 0))?;
|
|
4669
|
+
class.define_method("last_modified", method!(CachedPage::last_modified, 0))?;
|
|
4670
|
+
class.define_method("cached_at", method!(CachedPage::cached_at, 0))?;
|
|
4671
|
+
|
|
4672
|
+
let class = module.define_class("LinkInfo", ruby.class_object())?;
|
|
4673
|
+
class.define_singleton_method("new", function!(LinkInfo::new, 5))?;
|
|
4674
|
+
class.define_method("url", method!(LinkInfo::url, 0))?;
|
|
4675
|
+
class.define_method("text", method!(LinkInfo::text, 0))?;
|
|
4676
|
+
class.define_method("link_type", method!(LinkInfo::link_type, 0))?;
|
|
4677
|
+
class.define_method("rel", method!(LinkInfo::rel, 0))?;
|
|
4678
|
+
class.define_method("nofollow", method!(LinkInfo::nofollow, 0))?;
|
|
4679
|
+
|
|
4680
|
+
let class = module.define_class("ImageInfo", ruby.class_object())?;
|
|
4681
|
+
class.define_singleton_method("new", function!(ImageInfo::new, 5))?;
|
|
4682
|
+
class.define_method("url", method!(ImageInfo::url, 0))?;
|
|
4683
|
+
class.define_method("alt", method!(ImageInfo::alt, 0))?;
|
|
4684
|
+
class.define_method("width", method!(ImageInfo::width, 0))?;
|
|
4685
|
+
class.define_method("height", method!(ImageInfo::height, 0))?;
|
|
4686
|
+
class.define_method("source", method!(ImageInfo::source, 0))?;
|
|
4687
|
+
|
|
4688
|
+
let class = module.define_class("FeedInfo", ruby.class_object())?;
|
|
4689
|
+
class.define_singleton_method("new", function!(FeedInfo::new, 3))?;
|
|
4690
|
+
class.define_method("url", method!(FeedInfo::url, 0))?;
|
|
4691
|
+
class.define_method("title", method!(FeedInfo::title, 0))?;
|
|
4692
|
+
class.define_method("feed_type", method!(FeedInfo::feed_type, 0))?;
|
|
4693
|
+
|
|
4694
|
+
let class = module.define_class("JsonLdEntry", ruby.class_object())?;
|
|
4695
|
+
class.define_singleton_method("new", function!(JsonLdEntry::new, 3))?;
|
|
4696
|
+
class.define_method("schema_type", method!(JsonLdEntry::schema_type, 0))?;
|
|
4697
|
+
class.define_method("name", method!(JsonLdEntry::name, 0))?;
|
|
4698
|
+
class.define_method("raw", method!(JsonLdEntry::raw, 0))?;
|
|
4699
|
+
|
|
4700
|
+
let class = module.define_class("CookieInfo", ruby.class_object())?;
|
|
4701
|
+
class.define_singleton_method("new", function!(CookieInfo::new, 4))?;
|
|
4702
|
+
class.define_method("name", method!(CookieInfo::name, 0))?;
|
|
4703
|
+
class.define_method("value", method!(CookieInfo::value, 0))?;
|
|
4704
|
+
class.define_method("domain", method!(CookieInfo::domain, 0))?;
|
|
4705
|
+
class.define_method("path", method!(CookieInfo::path, 0))?;
|
|
4706
|
+
|
|
4707
|
+
let class = module.define_class("DownloadedAsset", ruby.class_object())?;
|
|
4708
|
+
class.define_singleton_method("new", function!(DownloadedAsset::new, 6))?;
|
|
4709
|
+
class.define_method("url", method!(DownloadedAsset::url, 0))?;
|
|
4710
|
+
class.define_method("content_hash", method!(DownloadedAsset::content_hash, 0))?;
|
|
4711
|
+
class.define_method("mime_type", method!(DownloadedAsset::mime_type, 0))?;
|
|
4712
|
+
class.define_method("size", method!(DownloadedAsset::size, 0))?;
|
|
4713
|
+
class.define_method("asset_category", method!(DownloadedAsset::asset_category, 0))?;
|
|
4714
|
+
class.define_method("html_tag", method!(DownloadedAsset::html_tag, 0))?;
|
|
4715
|
+
|
|
4716
|
+
let class = module.define_class("ArticleMetadata", ruby.class_object())?;
|
|
4717
|
+
class.define_singleton_method("new", function!(ArticleMetadata::new, 5))?;
|
|
4718
|
+
class.define_method("published_time", method!(ArticleMetadata::published_time, 0))?;
|
|
4719
|
+
class.define_method("modified_time", method!(ArticleMetadata::modified_time, 0))?;
|
|
4720
|
+
class.define_method("author", method!(ArticleMetadata::author, 0))?;
|
|
4721
|
+
class.define_method("section", method!(ArticleMetadata::section, 0))?;
|
|
4722
|
+
class.define_method("tags", method!(ArticleMetadata::tags, 0))?;
|
|
4723
|
+
|
|
4724
|
+
let class = module.define_class("HreflangEntry", ruby.class_object())?;
|
|
4725
|
+
class.define_singleton_method("new", function!(HreflangEntry::new, 2))?;
|
|
4726
|
+
class.define_method("lang", method!(HreflangEntry::lang, 0))?;
|
|
4727
|
+
class.define_method("url", method!(HreflangEntry::url, 0))?;
|
|
4728
|
+
|
|
4729
|
+
let class = module.define_class("FaviconInfo", ruby.class_object())?;
|
|
4730
|
+
class.define_singleton_method("new", function!(FaviconInfo::new, 4))?;
|
|
4731
|
+
class.define_method("url", method!(FaviconInfo::url, 0))?;
|
|
4732
|
+
class.define_method("rel", method!(FaviconInfo::rel, 0))?;
|
|
4733
|
+
class.define_method("sizes", method!(FaviconInfo::sizes, 0))?;
|
|
4734
|
+
class.define_method("mime_type", method!(FaviconInfo::mime_type, 0))?;
|
|
4735
|
+
|
|
4736
|
+
let class = module.define_class("HeadingInfo", ruby.class_object())?;
|
|
4737
|
+
class.define_singleton_method("new", function!(HeadingInfo::new, 2))?;
|
|
4738
|
+
class.define_method("level", method!(HeadingInfo::level, 0))?;
|
|
4739
|
+
class.define_method("text", method!(HeadingInfo::text, 0))?;
|
|
4740
|
+
|
|
4741
|
+
let class = module.define_class("ResponseMeta", ruby.class_object())?;
|
|
4742
|
+
class.define_singleton_method("new", function!(ResponseMeta::new, 7))?;
|
|
4743
|
+
class.define_method("etag", method!(ResponseMeta::etag, 0))?;
|
|
4744
|
+
class.define_method("last_modified", method!(ResponseMeta::last_modified, 0))?;
|
|
4745
|
+
class.define_method("cache_control", method!(ResponseMeta::cache_control, 0))?;
|
|
4746
|
+
class.define_method("server", method!(ResponseMeta::server, 0))?;
|
|
4747
|
+
class.define_method("x_powered_by", method!(ResponseMeta::x_powered_by, 0))?;
|
|
4748
|
+
class.define_method("content_language", method!(ResponseMeta::content_language, 0))?;
|
|
4749
|
+
class.define_method("content_encoding", method!(ResponseMeta::content_encoding, 0))?;
|
|
4750
|
+
|
|
4751
|
+
let class = module.define_class("PageMetadata", ruby.class_object())?;
|
|
4752
|
+
class.define_singleton_method("new", function!(PageMetadata::new, 1))?;
|
|
4753
|
+
class.define_method("title", method!(PageMetadata::title, 0))?;
|
|
4754
|
+
class.define_method("description", method!(PageMetadata::description, 0))?;
|
|
4755
|
+
class.define_method("canonical_url", method!(PageMetadata::canonical_url, 0))?;
|
|
4756
|
+
class.define_method("keywords", method!(PageMetadata::keywords, 0))?;
|
|
4757
|
+
class.define_method("author", method!(PageMetadata::author, 0))?;
|
|
4758
|
+
class.define_method("viewport", method!(PageMetadata::viewport, 0))?;
|
|
4759
|
+
class.define_method("theme_color", method!(PageMetadata::theme_color, 0))?;
|
|
4760
|
+
class.define_method("generator", method!(PageMetadata::generator, 0))?;
|
|
4761
|
+
class.define_method("robots", method!(PageMetadata::robots, 0))?;
|
|
4762
|
+
class.define_method("html_lang", method!(PageMetadata::html_lang, 0))?;
|
|
4763
|
+
class.define_method("html_dir", method!(PageMetadata::html_dir, 0))?;
|
|
4764
|
+
class.define_method("og_title", method!(PageMetadata::og_title, 0))?;
|
|
4765
|
+
class.define_method("og_type", method!(PageMetadata::og_type, 0))?;
|
|
4766
|
+
class.define_method("og_image", method!(PageMetadata::og_image, 0))?;
|
|
4767
|
+
class.define_method("og_description", method!(PageMetadata::og_description, 0))?;
|
|
4768
|
+
class.define_method("og_url", method!(PageMetadata::og_url, 0))?;
|
|
4769
|
+
class.define_method("og_site_name", method!(PageMetadata::og_site_name, 0))?;
|
|
4770
|
+
class.define_method("og_locale", method!(PageMetadata::og_locale, 0))?;
|
|
4771
|
+
class.define_method("og_video", method!(PageMetadata::og_video, 0))?;
|
|
4772
|
+
class.define_method("og_audio", method!(PageMetadata::og_audio, 0))?;
|
|
4773
|
+
class.define_method("og_locale_alternates", method!(PageMetadata::og_locale_alternates, 0))?;
|
|
4774
|
+
class.define_method("twitter_card", method!(PageMetadata::twitter_card, 0))?;
|
|
4775
|
+
class.define_method("twitter_title", method!(PageMetadata::twitter_title, 0))?;
|
|
4776
|
+
class.define_method("twitter_description", method!(PageMetadata::twitter_description, 0))?;
|
|
4777
|
+
class.define_method("twitter_image", method!(PageMetadata::twitter_image, 0))?;
|
|
4778
|
+
class.define_method("twitter_site", method!(PageMetadata::twitter_site, 0))?;
|
|
4779
|
+
class.define_method("twitter_creator", method!(PageMetadata::twitter_creator, 0))?;
|
|
4780
|
+
class.define_method("dc_title", method!(PageMetadata::dc_title, 0))?;
|
|
4781
|
+
class.define_method("dc_creator", method!(PageMetadata::dc_creator, 0))?;
|
|
4782
|
+
class.define_method("dc_subject", method!(PageMetadata::dc_subject, 0))?;
|
|
4783
|
+
class.define_method("dc_description", method!(PageMetadata::dc_description, 0))?;
|
|
4784
|
+
class.define_method("dc_publisher", method!(PageMetadata::dc_publisher, 0))?;
|
|
4785
|
+
class.define_method("dc_date", method!(PageMetadata::dc_date, 0))?;
|
|
4786
|
+
class.define_method("dc_type", method!(PageMetadata::dc_type, 0))?;
|
|
4787
|
+
class.define_method("dc_format", method!(PageMetadata::dc_format, 0))?;
|
|
4788
|
+
class.define_method("dc_identifier", method!(PageMetadata::dc_identifier, 0))?;
|
|
4789
|
+
class.define_method("dc_language", method!(PageMetadata::dc_language, 0))?;
|
|
4790
|
+
class.define_method("dc_rights", method!(PageMetadata::dc_rights, 0))?;
|
|
4791
|
+
class.define_method("article", method!(PageMetadata::article, 0))?;
|
|
4792
|
+
class.define_method("hreflangs", method!(PageMetadata::hreflangs, 0))?;
|
|
4793
|
+
class.define_method("favicons", method!(PageMetadata::favicons, 0))?;
|
|
4794
|
+
class.define_method("headings", method!(PageMetadata::headings, 0))?;
|
|
4795
|
+
class.define_method("word_count", method!(PageMetadata::word_count, 0))?;
|
|
4796
|
+
|
|
4797
|
+
let class = module.define_class("CitationResult", ruby.class_object())?;
|
|
4798
|
+
class.define_singleton_method("new", function!(CitationResult::new, 2))?;
|
|
4799
|
+
class.define_method("content", method!(CitationResult::content, 0))?;
|
|
4800
|
+
class.define_method("references", method!(CitationResult::references, 0))?;
|
|
4801
|
+
|
|
4802
|
+
let class = module.define_class("CitationReference", ruby.class_object())?;
|
|
4803
|
+
class.define_singleton_method("new", function!(CitationReference::new, 3))?;
|
|
4804
|
+
class.define_method("index", method!(CitationReference::index, 0))?;
|
|
4805
|
+
class.define_method("url", method!(CitationReference::url, 0))?;
|
|
4806
|
+
class.define_method("text", method!(CitationReference::text, 0))?;
|
|
4807
|
+
|
|
4808
|
+
let _class = module.define_class("CrawlEngineHandle", ruby.class_object())?;
|
|
4809
|
+
|
|
4810
|
+
let class = module.define_class("BatchScrapeResult", ruby.class_object())?;
|
|
4811
|
+
class.define_singleton_method("new", function!(BatchScrapeResult::new, 3))?;
|
|
4812
|
+
class.define_method("url", method!(BatchScrapeResult::url, 0))?;
|
|
4813
|
+
class.define_method("result", method!(BatchScrapeResult::result, 0))?;
|
|
4814
|
+
class.define_method("error", method!(BatchScrapeResult::error, 0))?;
|
|
4815
|
+
|
|
4816
|
+
let class = module.define_class("BatchCrawlResult", ruby.class_object())?;
|
|
4817
|
+
class.define_singleton_method("new", function!(BatchCrawlResult::new, 3))?;
|
|
4818
|
+
class.define_method("url", method!(BatchCrawlResult::url, 0))?;
|
|
4819
|
+
class.define_method("result", method!(BatchCrawlResult::result, 0))?;
|
|
4820
|
+
class.define_method("error", method!(BatchCrawlResult::error, 0))?;
|
|
4821
|
+
|
|
4822
|
+
module.define_module_function("create_engine", function!(create_engine, 1))?;
|
|
4823
|
+
module.define_module_function("scrape", function!(scrape, 2))?;
|
|
4824
|
+
module.define_module_function("scrape_async", function!(scrape_async, 2))?;
|
|
4825
|
+
module.define_module_function("crawl", function!(crawl, 2))?;
|
|
4826
|
+
module.define_module_function("crawl_async", function!(crawl_async, 2))?;
|
|
4827
|
+
module.define_module_function("map_urls", function!(map_urls, 2))?;
|
|
4828
|
+
module.define_module_function("map_urls_async", function!(map_urls_async, 2))?;
|
|
4829
|
+
module.define_module_function("batch_scrape", function!(batch_scrape, 2))?;
|
|
4830
|
+
module.define_module_function("batch_scrape_async", function!(batch_scrape_async, 2))?;
|
|
4831
|
+
module.define_module_function("batch_crawl", function!(batch_crawl, 2))?;
|
|
4832
|
+
module.define_module_function("batch_crawl_async", function!(batch_crawl_async, 2))?;
|
|
4833
|
+
|
|
4834
|
+
Ok(())
|
|
4835
|
+
}
|