@crawlee/browser 4.0.0-beta.19 → 4.0.0-beta.191
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.
- package/README.md +14 -14
- package/index.d.ts +0 -1
- package/index.js +0 -1
- package/internals/browser-crawler.d.ts +262 -171
- package/internals/browser-crawler.js +286 -244
- package/internals/browser-launcher.d.ts +70 -23
- package/internals/browser-launcher.js +73 -23
- package/package.json +10 -10
- package/index.d.ts.map +0 -1
- package/index.js.map +0 -1
- package/internals/browser-crawler.d.ts.map +0 -1
- package/internals/browser-crawler.js.map +0 -1
- package/internals/browser-launcher.d.ts.map +0 -1
- package/internals/browser-launcher.js.map +0 -1
|
@@ -1,19 +1,32 @@
|
|
|
1
|
-
import type {
|
|
2
|
-
import { BasicCrawler,
|
|
3
|
-
import type {
|
|
4
|
-
import {
|
|
5
|
-
import
|
|
6
|
-
import type { RobotsTxtFile } from '@crawlee/utils';
|
|
7
|
-
import type { ReadonlyDeep } from 'type-fest';
|
|
1
|
+
import type { AddRequestsBatchedResult, BasicCrawlerOptions, CrawlingContext, EnqueueLinksOptions, ErrorHandler, ExtractLinksOptions, GetUserDataFromRequest, LoadedRequest, CrawlingRequest, RequestHandler, RouterHandler } from '@crawlee/basic';
|
|
2
|
+
import { BasicCrawler, ContextPipeline } from '@crawlee/basic';
|
|
3
|
+
import type { CommonPage, CrawlerRemoteBrowserOptions } from '@crawlee/browser-pool';
|
|
4
|
+
import type { Awaitable, Dictionary, IBrowserPool } from '@crawlee/types';
|
|
5
|
+
import { z } from 'zod';
|
|
8
6
|
import type { BrowserLaunchContext } from './browser-launcher.js';
|
|
9
7
|
interface BaseResponse {
|
|
10
8
|
status(): number;
|
|
9
|
+
/** Optional because only Playwright and Puppeteer responses are guaranteed to carry it. */
|
|
10
|
+
headers?(): Record<string, string>;
|
|
11
11
|
}
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
12
|
+
/**
|
|
13
|
+
* The type of a browser pool the crawler builds (and therefore owns) for itself. It's an {@link IBrowserPool} that
|
|
14
|
+
* additionally exposes the lifecycle hooks a crawler only ever calls on a pool it created — which is why
|
|
15
|
+
* {@link IBrowserPool} itself intentionally omits them: `releaseAllBrowsers()` at the end of every run, and
|
|
16
|
+
* `destroy()` once the crawler itself is destroyed.
|
|
17
|
+
*/
|
|
18
|
+
export type OwnedBrowserPool<Page> = IBrowserPool<Page> & {
|
|
19
|
+
releaseAllBrowsers: () => Promise<void>;
|
|
20
|
+
destroy: () => Promise<void>;
|
|
21
|
+
};
|
|
22
|
+
/**
|
|
23
|
+
* Rejects options that exist only to configure the browser pool the crawler would have built for itself.
|
|
24
|
+
* Accepting them alongside a pre-built `browserPool` and quietly ignoring them is how `browserPoolOptions` grew
|
|
25
|
+
* into a second, half-working way of configuring the same pool.
|
|
26
|
+
*/
|
|
27
|
+
export declare function assertBrowserPoolNotConfigured(crawlerName: string, ignoredOptions: Dictionary): void;
|
|
28
|
+
export interface BrowserCrawlingContext<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
|
|
29
|
+
GoToOptions extends Dictionary = Dictionary> extends CrawlingContext<UserData> {
|
|
17
30
|
/**
|
|
18
31
|
* The browser page object where the web page is loaded and rendered.
|
|
19
32
|
*/
|
|
@@ -21,19 +34,55 @@ export interface BrowserCrawlingContext<Page extends CommonPage = CommonPage, Re
|
|
|
21
34
|
/**
|
|
22
35
|
* The request object that was successfully loaded and navigated to, including the {@link Request.loadedUrl|`loadedUrl`} property.
|
|
23
36
|
*/
|
|
24
|
-
request: LoadedRequest<
|
|
37
|
+
request: LoadedRequest<CrawlingRequest<UserData>>;
|
|
25
38
|
/**
|
|
26
39
|
* The HTTP response object returned by the browser's navigation.
|
|
27
40
|
*/
|
|
28
41
|
response: Response;
|
|
42
|
+
/**
|
|
43
|
+
* Options object passed to the underlying `page.goto()` call. `preNavigationHooks` can mutate this
|
|
44
|
+
* object (or return `{ gotoOptions: ... }`) to influence the navigation.
|
|
45
|
+
*/
|
|
46
|
+
gotoOptions: GoToOptions;
|
|
47
|
+
/**
|
|
48
|
+
* Extracts URLs from the current page, without adding them to the request queue.
|
|
49
|
+
*/
|
|
50
|
+
extractLinks: (options?: ExtractLinksOptions) => Promise<string[]>;
|
|
29
51
|
/**
|
|
30
52
|
* Helper function for extracting URLs from the current page and adding them to the request queue.
|
|
31
53
|
*/
|
|
32
|
-
enqueueLinks: (options?: EnqueueLinksOptions) => Promise<
|
|
54
|
+
enqueueLinks: (options?: EnqueueLinksOptions) => Promise<AddRequestsBatchedResult>;
|
|
33
55
|
}
|
|
34
|
-
export type BrowserHook<Context = BrowserCrawlingContext,
|
|
35
|
-
export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse,
|
|
56
|
+
export type BrowserHook<Context = BrowserCrawlingContext, ContextExtension = {}> = (crawlingContext: Context & ContextExtension) => Awaitable<void | Partial<Context>>;
|
|
57
|
+
export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, Context extends BrowserCrawlingContext<Page, Response> = BrowserCrawlingContext<Page, Response>, ContextExtension = Dictionary<never>, ExtendedContext extends Context = Context & ContextExtension, Routes extends Record<keyof Routes, Dictionary> = Record<string, GetUserDataFromRequest<Context['request']>>, StatisticStateExtension extends object = {}> extends Omit<BasicCrawlerOptions<Context, ContextExtension, ExtendedContext, Routes, StatisticStateExtension>, 'requestHandler' | 'failedRequestHandler' | 'errorHandler'> {
|
|
36
58
|
launchContext?: BrowserLaunchContext<any, any>;
|
|
59
|
+
/**
|
|
60
|
+
* The browser pool the crawler should serve its pages from. This is the single way to run a pool with
|
|
61
|
+
* non-default options: build one with the factory that matches your crawler
|
|
62
|
+
* ({@link playwrightBrowserPool}, {@link puppeteerBrowserPool}, {@link stagehandBrowserPool}) - it
|
|
63
|
+
* accepts every {@link BrowserPoolOptions|`BrowserPool` option} and supplies the correct browser plugin
|
|
64
|
+
* itself, so the pool can never mismatch the crawler.
|
|
65
|
+
*
|
|
66
|
+
* A pool passed in this way is borrowed, not owned: the crawler will not tear it down, which is what makes it
|
|
67
|
+
* shareable across crawlers. Since the crawler then builds nothing itself, the options that configure its own
|
|
68
|
+
* pool (`launchContext`, `headless`, `remoteBrowser`) are rejected rather than silently ignored.
|
|
69
|
+
*
|
|
70
|
+
* When omitted, the crawler builds - and tears down - a default pool for its own browser.
|
|
71
|
+
*/
|
|
72
|
+
browserPool?: IBrowserPool<Page>;
|
|
73
|
+
/**
|
|
74
|
+
* Connect to a remote browser service (Browserbase, Browserless, Steel, …) instead of launching locally.
|
|
75
|
+
*
|
|
76
|
+
* The crawler builds a {@link RemoteBrowserPool} around its own browser plugin, so the connection is
|
|
77
|
+
* always for the right browser — there is no plugin to construct and no way to mismatch the pool with the
|
|
78
|
+
* crawler. Supply the connection details only: a static `endpoint` URL, a function returning one per launch,
|
|
79
|
+
* or a {@link RemoteBrowserProvider}.
|
|
80
|
+
*
|
|
81
|
+
* Cannot be combined with `browserPool`. To tune the pool wrapping the remote connection, or to share it
|
|
82
|
+
* across crawlers, build it with the remote factory for your crawler ({@link remotePlaywrightBrowserPool},
|
|
83
|
+
* {@link remotePuppeteerBrowserPool}, {@link remoteStagehandBrowserPool}) and pass it as `browserPool`.
|
|
84
|
+
*/
|
|
85
|
+
remoteBrowser?: CrawlerRemoteBrowserOptions;
|
|
37
86
|
/**
|
|
38
87
|
* Function that is called to process each request.
|
|
39
88
|
*
|
|
@@ -44,7 +93,6 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
44
93
|
* - {@link BrowserCrawlingContext.page|`page`} is an instance of the
|
|
45
94
|
* Puppeteer [Page](https://pptr.dev/api/puppeteer.page) or
|
|
46
95
|
* Playwright [Page](https://playwright.dev/docs/api/class-page);
|
|
47
|
-
* - {@link BrowserCrawlingContext.browserController|`browserController`} is an instance of the {@link BrowserController};
|
|
48
96
|
* - {@link BrowserCrawlingContext.response|`response`} is an instance of the
|
|
49
97
|
* Puppeteer [Response](https://pptr.dev/api/puppeteer.httpresponse) or
|
|
50
98
|
* Playwright [Response](https://playwright.dev/docs/api/class-response),
|
|
@@ -59,9 +107,9 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
59
107
|
* To make this work, we should **always**
|
|
60
108
|
* let our function throw exceptions rather than catch them.
|
|
61
109
|
* The exceptions are logged to the request using the
|
|
62
|
-
* {@link
|
|
110
|
+
* {@link CrawlingRequest.pushErrorMessage|`request.pushErrorMessage()`} function.
|
|
63
111
|
*/
|
|
64
|
-
requestHandler?: RequestHandler<ExtendedContext>;
|
|
112
|
+
requestHandler?: RouterHandler<ExtendedContext, Routes> | RequestHandler<ExtendedContext>;
|
|
65
113
|
/**
|
|
66
114
|
* User-provided function that allows modifying the request object before it gets retried by the crawler.
|
|
67
115
|
* It's executed before each retry for the requests that failed less than {@link BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
|
|
@@ -83,22 +131,16 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
83
131
|
* represents the last error thrown during processing of the request.
|
|
84
132
|
*/
|
|
85
133
|
failedRequestHandler?: ErrorHandler<CrawlingContext, ExtendedContext>;
|
|
86
|
-
/**
|
|
87
|
-
* Custom options passed to the underlying {@link BrowserPool} constructor.
|
|
88
|
-
* We can tweak those to fine-tune browser management.
|
|
89
|
-
*/
|
|
90
|
-
browserPoolOptions?: Partial<BrowserPoolOptions> & Partial<BrowserPoolHooks<__BrowserControllerReturn, __LaunchContextReturn>>;
|
|
91
134
|
/**
|
|
92
135
|
* Async functions that are sequentially evaluated before the navigation. Good for setting additional cookies
|
|
93
|
-
* or browser properties before navigation. The function
|
|
94
|
-
*
|
|
136
|
+
* or browser properties before navigation. The function receives the `crawlingContext`; the options object
|
|
137
|
+
* forwarded to `page.goto()` is available as `crawlingContext.gotoOptions` and can be mutated in place.
|
|
95
138
|
*
|
|
96
139
|
* **Example:**
|
|
97
140
|
*
|
|
98
141
|
* ```js
|
|
99
142
|
* preNavigationHooks: [
|
|
100
|
-
* async (
|
|
101
|
-
* const { page } = crawlingContext;
|
|
143
|
+
* async ({ page, gotoOptions }) => {
|
|
102
144
|
* await page.evaluate((attr) => { window.foo = attr; }, 'bar');
|
|
103
145
|
* gotoOptions.timeout = 60_000;
|
|
104
146
|
* gotoOptions.waitUntil = 'domcontentloaded';
|
|
@@ -106,14 +148,22 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
106
148
|
* ]
|
|
107
149
|
* ```
|
|
108
150
|
*
|
|
109
|
-
*
|
|
110
|
-
*
|
|
151
|
+
* A hook may optionally return a partial object whose properties are merged into the crawling context,
|
|
152
|
+
* allowing the hook to override context members for subsequent hooks and pipeline stages.
|
|
153
|
+
*
|
|
154
|
+
* The context is built up in the following order: base context (`request`, `session`, helpers, ...) ->
|
|
155
|
+
* `extendContext` -> `preNavigationHooks` -> navigation -> `postNavigationHooks` -> `requestHandler`.
|
|
156
|
+
* This means the members added by `extendContext` are already available here, but navigation-dependent
|
|
157
|
+
* members (e.g. `page`, `response`) are not.
|
|
111
158
|
*/
|
|
112
|
-
preNavigationHooks?: BrowserHook<Context>[];
|
|
159
|
+
preNavigationHooks?: BrowserHook<Context, ContextExtension>[];
|
|
113
160
|
/**
|
|
114
161
|
* Async functions that are sequentially evaluated after the navigation. Good for checking if the navigation was successful.
|
|
115
162
|
* The function accepts `crawlingContext` as the only parameter.
|
|
116
163
|
*
|
|
164
|
+
* A hook may optionally return a partial object whose properties are merged into the crawling context.
|
|
165
|
+
* This is useful for overriding context members (e.g. `response`) after solving a challenge.
|
|
166
|
+
*
|
|
117
167
|
* **Example:**
|
|
118
168
|
*
|
|
119
169
|
* ```js
|
|
@@ -124,24 +174,27 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
124
174
|
* await solveCaptcha(page);
|
|
125
175
|
* }
|
|
126
176
|
* },
|
|
177
|
+
* async (crawlingContext) => {
|
|
178
|
+
* if (await needsRevalidation(crawlingContext)) {
|
|
179
|
+
* return { response: await crawlingContext.page.reload() };
|
|
180
|
+
* }
|
|
181
|
+
* },
|
|
127
182
|
* ]
|
|
128
183
|
* ```
|
|
129
184
|
*/
|
|
130
|
-
postNavigationHooks?: BrowserHook<Context>[];
|
|
185
|
+
postNavigationHooks?: BrowserHook<Context, ContextExtension>[];
|
|
131
186
|
/**
|
|
132
|
-
* Timeout
|
|
187
|
+
* Timeout for the whole navigation phase, in seconds. A single window shared by the `preNavigationHooks`,
|
|
188
|
+
* the page navigation, and the `postNavigationHooks` - so a slow hook eats into the same budget the
|
|
189
|
+
* navigation uses. Separate from the
|
|
190
|
+
* {@link BasicCrawlerOptions.requestHandlerTimeoutSecs|`requestHandlerTimeoutSecs`}, which times only the
|
|
191
|
+
* request handler.
|
|
133
192
|
*/
|
|
134
193
|
navigationTimeoutSecs?: number;
|
|
135
194
|
/**
|
|
136
|
-
* Defines whether the cookies should be persisted for sessions.
|
|
137
|
-
* This can only be used when `useSessionPool` is set to `true`.
|
|
138
|
-
*/
|
|
139
|
-
persistCookiesPerSession?: boolean;
|
|
140
|
-
/**
|
|
141
|
-
* Whether to run browser in headless mode. Defaults to `true`.
|
|
142
|
-
* Can be also set via {@link Configuration}.
|
|
195
|
+
* Defines whether the cookies should be persisted for sessions. Enabled by default.
|
|
143
196
|
*/
|
|
144
|
-
|
|
197
|
+
saveResponseCookies?: boolean;
|
|
145
198
|
/**
|
|
146
199
|
* Whether to ignore custom elements (and their #shadow-roots) when processing the page content via `parseWithCheerio` helper.
|
|
147
200
|
* By default, they are expanded automatically. Use this option to disable this behavior.
|
|
@@ -165,174 +218,213 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
165
218
|
* If the target website doesn't need JavaScript, we should consider using the {@link CheerioCrawler},
|
|
166
219
|
* which downloads the pages using raw HTTP requests and is about 10x faster.
|
|
167
220
|
*
|
|
168
|
-
* The source URLs are represented by the {@link Request} objects that are fed from the
|
|
169
|
-
*
|
|
170
|
-
* constructor
|
|
221
|
+
* The source URLs are represented by the {@link Request} objects that are fed from the
|
|
222
|
+
* {@link IRequestManager|request manager} provided via the {@link BrowserCrawlerOptions.requestManager|`requestManager`}
|
|
223
|
+
* constructor option (a {@link RequestQueue} is itself a request manager). If no `requestManager` is provided,
|
|
171
224
|
* the crawler will open the default request queue either when the {@link BrowserCrawler.addRequests|`crawler.addRequests()`} function is called,
|
|
172
225
|
* or if `requests` parameter (representing the initial requests) of the {@link BrowserCrawler.run|`crawler.run()`} function is provided.
|
|
173
226
|
*
|
|
174
|
-
*
|
|
175
|
-
*
|
|
176
|
-
*
|
|
227
|
+
* To read from a read-only source such as a {@link RequestList} while still being able to enqueue new requests,
|
|
228
|
+
* combine it with a queue into a {@link RequestManagerTandem} via {@link IRequestLoader.toTandem|`requestLoader.toTandem()`}
|
|
229
|
+
* and pass the result as `requestManager`.
|
|
230
|
+
*
|
|
231
|
+
* > The {@link BrowserCrawlerOptions.requestList|`requestList`} and {@link BrowserCrawlerOptions.requestQueue|`requestQueue`}
|
|
232
|
+
* > options are deprecated; they are still accepted and folded into a single `requestManager` for back-compat.
|
|
177
233
|
*
|
|
178
234
|
* The crawler finishes when there are no more {@link Request} objects to crawl.
|
|
179
235
|
*
|
|
180
236
|
* `BrowserCrawler` opens a new browser page (i.e. tab or window) for each {@link Request} object to crawl
|
|
181
237
|
* and then calls the function provided by user as the {@link BrowserCrawlerOptions.requestHandler|`requestHandler`} option.
|
|
182
238
|
*
|
|
183
|
-
* New pages are only opened when there is enough free CPU and memory available,
|
|
184
|
-
*
|
|
185
|
-
*
|
|
186
|
-
*
|
|
187
|
-
*
|
|
188
|
-
* {@link AutoscaledPoolOptions.maxConcurrency|`maxConcurrency`} options of the
|
|
189
|
-
* underlying {@link AutoscaledPool} constructor are available directly in the `BrowserCrawler` constructor.
|
|
239
|
+
* New pages are only opened when there is enough free CPU and memory available, as judged by the crawler's
|
|
240
|
+
* {@link ConcurrencySystem}.
|
|
241
|
+
* Concurrency is tuned via the `minConcurrency`, `maxConcurrency` and `maxRequestsPerMinute` options of the
|
|
242
|
+
* `BrowserCrawler` constructor, or, for finer control, by injecting a pre-configured
|
|
243
|
+
* {@link ConcurrencySystem|`concurrencySystem`}.
|
|
190
244
|
*
|
|
191
245
|
* > *NOTE:* the pool of browser instances is internally managed by the {@link BrowserPool} class.
|
|
192
246
|
*
|
|
193
247
|
* @category Crawlers
|
|
194
248
|
*/
|
|
195
|
-
export declare abstract class BrowserCrawler<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse,
|
|
196
|
-
|
|
249
|
+
export declare abstract class BrowserCrawler<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, LaunchOptions extends Dictionary | undefined = Dictionary, Context extends BrowserCrawlingContext<Page, Response> = BrowserCrawlingContext<Page, Response>, ContextExtension = Dictionary<never>, ExtendedContext extends Context = Context & ContextExtension, Routes extends Record<keyof Routes, Dictionary> = Record<string, GetUserDataFromRequest<Context['request']>>, StatisticStateExtension extends object = {}, GoToOptions extends Dictionary = Dictionary> extends BasicCrawler<Context, ContextExtension, ExtendedContext, Routes, StatisticStateExtension> {
|
|
250
|
+
#private;
|
|
197
251
|
/**
|
|
198
|
-
* A reference to the underlying
|
|
252
|
+
* A reference to the underlying browser pool that manages the crawler's browsers. Typed as
|
|
253
|
+
* {@link IBrowserPool} so custom implementations can be plugged in via the `browserPool` constructor option.
|
|
199
254
|
*/
|
|
200
|
-
browserPool:
|
|
255
|
+
get browserPool(): IBrowserPool<Page>;
|
|
201
256
|
launchContext: BrowserLaunchContext<LaunchOptions, unknown>;
|
|
202
257
|
protected readonly ignoreShadowRoots: boolean;
|
|
203
258
|
protected readonly ignoreIframes: boolean;
|
|
204
|
-
|
|
205
|
-
|
|
206
|
-
|
|
207
|
-
protected persistCookiesPerSession: boolean;
|
|
259
|
+
/**
|
|
260
|
+
* @internal
|
|
261
|
+
*/
|
|
208
262
|
protected static optionsShape: {
|
|
209
|
-
|
|
210
|
-
|
|
211
|
-
|
|
212
|
-
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
|
|
218
|
-
|
|
219
|
-
|
|
220
|
-
|
|
221
|
-
|
|
222
|
-
|
|
223
|
-
|
|
224
|
-
|
|
225
|
-
|
|
226
|
-
|
|
227
|
-
|
|
228
|
-
|
|
229
|
-
|
|
230
|
-
|
|
231
|
-
|
|
232
|
-
|
|
233
|
-
|
|
234
|
-
|
|
235
|
-
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
240
|
-
|
|
241
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
242
|
-
|
|
243
|
-
|
|
244
|
-
|
|
245
|
-
|
|
246
|
-
|
|
247
|
-
|
|
248
|
-
|
|
249
|
-
|
|
250
|
-
|
|
251
|
-
|
|
252
|
-
|
|
253
|
-
|
|
254
|
-
|
|
255
|
-
|
|
256
|
-
|
|
257
|
-
|
|
258
|
-
|
|
259
|
-
|
|
260
|
-
|
|
261
|
-
|
|
262
|
-
|
|
263
|
-
|
|
264
|
-
|
|
265
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
266
|
-
onSkippedRequest: import("ow").Predicate<Function> & import("ow").BasePredicate<Function | undefined>;
|
|
267
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
268
|
-
httpClient: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
|
|
269
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
270
|
-
minConcurrency: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
|
|
271
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
272
|
-
maxConcurrency: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
|
|
273
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
274
|
-
maxRequestsPerMinute: import("ow").NumberPredicate & import("ow").BasePredicate<number | undefined>;
|
|
275
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
276
|
-
keepAlive: import("ow").BooleanPredicate & import("ow").BasePredicate<boolean | undefined>;
|
|
277
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
278
|
-
log: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
|
|
279
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
280
|
-
experiments: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
|
|
281
|
-
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
282
|
-
statisticsOptions: import("ow").ObjectPredicate<object> & import("ow").BasePredicate<object | undefined>;
|
|
263
|
+
contextPipelineBuilder: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
264
|
+
extendContext: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
265
|
+
requestList: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
266
|
+
requestQueue: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
267
|
+
requestManager: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
268
|
+
requestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
269
|
+
requestHandlerTimeoutSecs: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
270
|
+
errorHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
271
|
+
failedRequestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
272
|
+
maxRequestRetries: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
273
|
+
sameDomainDelaySecs: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
274
|
+
maxRequestsPerCrawl: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
275
|
+
maxCrawlDepth: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
276
|
+
taskLoopOptions: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
277
|
+
concurrencySystem: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
278
|
+
sessionPool: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
279
|
+
statusMessageLoggingInterval: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
280
|
+
statusMessageCallback: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
281
|
+
additionalHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
|
|
282
|
+
ignoreHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
|
|
283
|
+
blockedStatusCodes: z.ZodOptional<z.ZodArray<z.ZodCustom<number, number>>>;
|
|
284
|
+
retryOnBlocked: z.ZodDefault<z.ZodBoolean>;
|
|
285
|
+
respectRobotsTxtFile: z.ZodDefault<z.ZodUnion<readonly [z.ZodBoolean, z.ZodCustom<Dictionary, Dictionary>]>>;
|
|
286
|
+
transactionalStorage: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodObject<{
|
|
287
|
+
requestQueue: z.ZodOptional<z.ZodEnum<{
|
|
288
|
+
deferred: "deferred";
|
|
289
|
+
writeThrough: "writeThrough";
|
|
290
|
+
}>>;
|
|
291
|
+
}, z.core.$strict>]>>;
|
|
292
|
+
onSkippedRequest: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
293
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
294
|
+
httpClient: z.ZodOptional<z.ZodCustom<import("@crawlee/http-client").BaseHttpClient, import("@crawlee/http-client").BaseHttpClient>>;
|
|
295
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
296
|
+
configuration: z.ZodOptional<z.ZodCustom<import("@crawlee/basic").Configuration, import("@crawlee/basic").Configuration>>;
|
|
297
|
+
storageBackend: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
298
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
299
|
+
eventManager: z.ZodOptional<z.ZodCustom<import("@crawlee/basic").EventManager, import("@crawlee/basic").EventManager>>;
|
|
300
|
+
logger: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
301
|
+
minConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
302
|
+
maxConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
303
|
+
initialConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
304
|
+
maxRequestsPerMinute: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
305
|
+
keepAlive: z.ZodOptional<z.ZodBoolean>;
|
|
306
|
+
statistics: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
307
|
+
id: z.ZodOptional<z.ZodString>;
|
|
308
|
+
navigationTimeoutSecs: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
309
|
+
preNavigationHooks: z.ZodDefault<z.ZodCustom<unknown[], unknown[]>>;
|
|
310
|
+
postNavigationHooks: z.ZodDefault<z.ZodCustom<unknown[], unknown[]>>;
|
|
311
|
+
launchContext: z.ZodDefault<z.ZodCustom<Dictionary, Dictionary>>;
|
|
312
|
+
browserPool: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
313
|
+
browserPoolBuilder: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
314
|
+
remoteBrowser: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
315
|
+
saveResponseCookies: z.ZodDefault<z.ZodBoolean>;
|
|
316
|
+
proxyConfiguration: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
317
|
+
ignoreIframes: z.ZodDefault<z.ZodBoolean>;
|
|
318
|
+
ignoreShadowRoots: z.ZodDefault<z.ZodBoolean>;
|
|
283
319
|
};
|
|
320
|
+
/** @internal */
|
|
321
|
+
protected static optionsSchema: z.ZodObject<{
|
|
322
|
+
contextPipelineBuilder: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
323
|
+
extendContext: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
324
|
+
requestList: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
325
|
+
requestQueue: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
326
|
+
requestManager: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
327
|
+
requestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
328
|
+
requestHandlerTimeoutSecs: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
329
|
+
errorHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
330
|
+
failedRequestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
331
|
+
maxRequestRetries: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
332
|
+
sameDomainDelaySecs: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
333
|
+
maxRequestsPerCrawl: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
334
|
+
maxCrawlDepth: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
335
|
+
taskLoopOptions: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
336
|
+
concurrencySystem: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
337
|
+
sessionPool: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
338
|
+
statusMessageLoggingInterval: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
339
|
+
statusMessageCallback: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
340
|
+
additionalHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
|
|
341
|
+
ignoreHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
|
|
342
|
+
blockedStatusCodes: z.ZodOptional<z.ZodArray<z.ZodCustom<number, number>>>;
|
|
343
|
+
retryOnBlocked: z.ZodDefault<z.ZodBoolean>;
|
|
344
|
+
respectRobotsTxtFile: z.ZodDefault<z.ZodUnion<readonly [z.ZodBoolean, z.ZodCustom<Dictionary, Dictionary>]>>;
|
|
345
|
+
transactionalStorage: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodObject<{
|
|
346
|
+
requestQueue: z.ZodOptional<z.ZodEnum<{
|
|
347
|
+
deferred: "deferred";
|
|
348
|
+
writeThrough: "writeThrough";
|
|
349
|
+
}>>;
|
|
350
|
+
}, z.core.$strict>]>>;
|
|
351
|
+
onSkippedRequest: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
352
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
353
|
+
httpClient: z.ZodOptional<z.ZodCustom<import("@crawlee/http-client").BaseHttpClient, import("@crawlee/http-client").BaseHttpClient>>;
|
|
354
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
355
|
+
configuration: z.ZodOptional<z.ZodCustom<import("@crawlee/basic").Configuration, import("@crawlee/basic").Configuration>>;
|
|
356
|
+
storageBackend: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
357
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
358
|
+
eventManager: z.ZodOptional<z.ZodCustom<import("@crawlee/basic").EventManager, import("@crawlee/basic").EventManager>>;
|
|
359
|
+
logger: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
360
|
+
minConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
361
|
+
maxConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
362
|
+
initialConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
363
|
+
maxRequestsPerMinute: z.ZodOptional<z.ZodCustom<number, number>>;
|
|
364
|
+
keepAlive: z.ZodOptional<z.ZodBoolean>;
|
|
365
|
+
statistics: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
366
|
+
id: z.ZodOptional<z.ZodString>;
|
|
367
|
+
navigationTimeoutSecs: z.ZodDefault<z.ZodCustom<number, number>>;
|
|
368
|
+
preNavigationHooks: z.ZodDefault<z.ZodCustom<unknown[], unknown[]>>;
|
|
369
|
+
postNavigationHooks: z.ZodDefault<z.ZodCustom<unknown[], unknown[]>>;
|
|
370
|
+
launchContext: z.ZodDefault<z.ZodCustom<Dictionary, Dictionary>>;
|
|
371
|
+
browserPool: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
372
|
+
browserPoolBuilder: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
|
|
373
|
+
remoteBrowser: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
|
|
374
|
+
saveResponseCookies: z.ZodDefault<z.ZodBoolean>;
|
|
375
|
+
proxyConfiguration: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
|
|
376
|
+
ignoreIframes: z.ZodDefault<z.ZodBoolean>;
|
|
377
|
+
ignoreShadowRoots: z.ZodDefault<z.ZodBoolean>;
|
|
378
|
+
}, z.core.$strict>;
|
|
284
379
|
/**
|
|
285
380
|
* All `BrowserCrawler` parameters are passed via an options object.
|
|
286
381
|
*/
|
|
287
|
-
protected constructor(options: BrowserCrawlerOptions<Page, Response,
|
|
382
|
+
protected constructor(options: BrowserCrawlerOptions<Page, Response, Context, ContextExtension, ExtendedContext, Routes, StatisticStateExtension> & {
|
|
288
383
|
contextPipelineBuilder: () => ContextPipeline<CrawlingContext, Context>;
|
|
289
|
-
|
|
290
|
-
|
|
384
|
+
/**
|
|
385
|
+
* Builds the pool the crawler owns, used only when the user injected no `browserPool`. Supplied by the
|
|
386
|
+
* concrete crawler, which is the only place that knows which browser plugin to run - that is also why
|
|
387
|
+
* `remoteBrowser` is handed to it rather than acted upon here.
|
|
388
|
+
*/
|
|
389
|
+
browserPoolBuilder: (remoteBrowser?: CrawlerRemoteBrowserOptions) => OwnedBrowserPool<Page>;
|
|
390
|
+
});
|
|
391
|
+
protected getNavigationTimeoutMillis(): number;
|
|
392
|
+
protected buildContextPipeline(): ContextPipeline<CrawlingContext, BrowserCrawlingContext<Page, Response, Dictionary>>;
|
|
291
393
|
private containsSelectors;
|
|
292
|
-
|
|
394
|
+
private isRequestBlocked;
|
|
293
395
|
private preparePage;
|
|
294
|
-
private
|
|
396
|
+
private prepareNavigation;
|
|
397
|
+
private navigate;
|
|
398
|
+
private finalizeNavigation;
|
|
399
|
+
/**
|
|
400
|
+
* Copies cookies from the live browser page into the session cookie jar.
|
|
401
|
+
*/
|
|
402
|
+
private persistCookiesFromPage;
|
|
403
|
+
/**
|
|
404
|
+
* Runs the user request handler, then re-reads browser cookies so login flows /
|
|
405
|
+
* `page.setCookie` / XHR `Set-Cookie` updates are stored for later requests.
|
|
406
|
+
*/
|
|
407
|
+
protected runRequestHandler(crawlingContext: ExtendedContext): Promise<void>;
|
|
295
408
|
private handleBlockedRequestByContent;
|
|
296
409
|
private restoreRequestState;
|
|
297
|
-
|
|
410
|
+
private applyCookies;
|
|
298
411
|
/**
|
|
299
|
-
* Marks session bad in
|
|
412
|
+
* Marks session bad on navigation timeout, and stops in-flight page loading on any navigation error.
|
|
300
413
|
*/
|
|
301
|
-
|
|
414
|
+
private handleNavigationTimeout;
|
|
302
415
|
/**
|
|
303
416
|
* Transforms proxy-related errors to `SessionError`.
|
|
304
417
|
*/
|
|
305
|
-
|
|
306
|
-
protected abstract
|
|
418
|
+
private throwIfProxyError;
|
|
419
|
+
protected abstract navigationHandler(crawlingContext: BrowserCrawlingContext<Page, Response>, gotoOptions: GoToOptions): Promise<Context['response'] | null | undefined>;
|
|
307
420
|
private processResponse;
|
|
308
|
-
protected _extendLaunchContext(_pageId: string, launchContext: LaunchContext): Promise<void>;
|
|
309
|
-
protected _maybeAddSessionRetiredListener(_pageId: string, browserController: Context['browserController']): void;
|
|
310
421
|
/**
|
|
311
|
-
*
|
|
312
|
-
*
|
|
422
|
+
* Closes the browsers of a pool the crawler owns, so a finished run leaves none behind. The pool itself is
|
|
423
|
+
* crawler-lifetime and survives — destroying it here would hand a repeated `run()` a dead pool.
|
|
313
424
|
*/
|
|
314
425
|
teardown(): Promise<void>;
|
|
426
|
+
destroy(): Promise<void>;
|
|
315
427
|
}
|
|
316
|
-
/** @internal */
|
|
317
|
-
interface EnqueueLinksInternalOptions {
|
|
318
|
-
options?: ReadonlyDeep<Omit<EnqueueLinksOptions, 'requestQueue'>> & Pick<EnqueueLinksOptions, 'requestQueue'>;
|
|
319
|
-
page: CommonPage;
|
|
320
|
-
requestQueue: RequestProvider;
|
|
321
|
-
robotsTxtFile?: RobotsTxtFile;
|
|
322
|
-
onSkippedRequest?: SkippedRequestCallback;
|
|
323
|
-
originalRequestUrl: string;
|
|
324
|
-
finalRequestUrl?: string;
|
|
325
|
-
}
|
|
326
|
-
/** @internal */
|
|
327
|
-
interface BoundEnqueueLinksInternalOptions {
|
|
328
|
-
enqueueLinks: BasicCrawlingContext['enqueueLinks'];
|
|
329
|
-
options?: ReadonlyDeep<Omit<EnqueueLinksOptions, 'requestQueue'>> & Pick<EnqueueLinksOptions, 'requestQueue'>;
|
|
330
|
-
originalRequestUrl: string;
|
|
331
|
-
finalRequestUrl?: string;
|
|
332
|
-
page: CommonPage;
|
|
333
|
-
}
|
|
334
|
-
/** @internal */
|
|
335
|
-
export declare function browserCrawlerEnqueueLinks(options: EnqueueLinksInternalOptions | BoundEnqueueLinksInternalOptions): Promise<unknown>;
|
|
336
428
|
/**
|
|
337
429
|
* Extracts URLs from a given page.
|
|
338
430
|
* @ignore
|
|
@@ -341,4 +433,3 @@ export declare function extractUrlsFromPage(page: {
|
|
|
341
433
|
$$eval: Function;
|
|
342
434
|
}, selector: string, baseUrl: string): Promise<string[]>;
|
|
343
435
|
export {};
|
|
344
|
-
//# sourceMappingURL=browser-crawler.d.ts.map
|