web-access-cli 0.1.0
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/LICENSE +21 -0
- package/README.md +270 -0
- package/README_CN.md +268 -0
- package/THIRD_PARTY_NOTICES.md +48 -0
- package/dist/cli.js +197 -0
- package/dist/cli.js.map +1 -0
- package/dist/config/config.js +463 -0
- package/dist/config/config.js.map +1 -0
- package/dist/config/edit.js +126 -0
- package/dist/config/edit.js.map +1 -0
- package/dist/core/diagnostics.js +94 -0
- package/dist/core/diagnostics.js.map +1 -0
- package/dist/core/errors.js +47 -0
- package/dist/core/errors.js.map +1 -0
- package/dist/core/router.js +320 -0
- package/dist/core/router.js.map +1 -0
- package/dist/core/schema.js +120 -0
- package/dist/core/schema.js.map +1 -0
- package/dist/core/types.js +22 -0
- package/dist/core/types.js.map +1 -0
- package/dist/providers/anysearch.js +225 -0
- package/dist/providers/anysearch.js.map +1 -0
- package/dist/providers/common.js +210 -0
- package/dist/providers/common.js.map +1 -0
- package/dist/providers/extract.js +155 -0
- package/dist/providers/extract.js.map +1 -0
- package/dist/providers/registry.js +31 -0
- package/dist/providers/registry.js.map +1 -0
- package/dist/providers/rsc.js +109 -0
- package/dist/providers/rsc.js.map +1 -0
- package/dist/providers/search.js +178 -0
- package/dist/providers/search.js.map +1 -0
- package/dist/providers/xcrawl.js +170 -0
- package/dist/providers/xcrawl.js.map +1 -0
- package/dist/transport/http.js +175 -0
- package/dist/transport/http.js.map +1 -0
- package/dist/version.js +2 -0
- package/dist/version.js.map +1 -0
- package/package.json +61 -0
- package/schemas/config.schema.json +210 -0
- package/schemas/extractRequest.schema.json +21 -0
- package/schemas/output.schema.json +435 -0
- package/schemas/searchRequest.schema.json +57 -0
|
@@ -0,0 +1,170 @@
|
|
|
1
|
+
import { redactText, WebAccessError } from "../core/errors.js";
|
|
2
|
+
import { buildEndpoint } from "../transport/http.js";
|
|
3
|
+
import { assertOk, freshnessStartDate, normalizeHits, parseJsonResponse, providerHeaders, ref, requireBaseUrl, requireCredential, searchQueryWithDomains, } from "./common.js";
|
|
4
|
+
function isRecord(value) {
|
|
5
|
+
return !!value && typeof value === "object" && !Array.isArray(value);
|
|
6
|
+
}
|
|
7
|
+
function stringField(value) {
|
|
8
|
+
return typeof value === "string" && value.trim() ? value.trim() : undefined;
|
|
9
|
+
}
|
|
10
|
+
function responseMessage(value) {
|
|
11
|
+
for (const candidate of [
|
|
12
|
+
value.message,
|
|
13
|
+
value.error,
|
|
14
|
+
isRecord(value.data) ? value.data.message : undefined,
|
|
15
|
+
isRecord(value.data) ? value.data.error : undefined,
|
|
16
|
+
]) {
|
|
17
|
+
if (typeof candidate === "string" && candidate.trim())
|
|
18
|
+
return candidate.trim().slice(0, 500);
|
|
19
|
+
if (isRecord(candidate)) {
|
|
20
|
+
const nested = stringField(candidate.message) ?? stringField(candidate.error);
|
|
21
|
+
if (nested)
|
|
22
|
+
return nested.slice(0, 500);
|
|
23
|
+
}
|
|
24
|
+
}
|
|
25
|
+
return "上游任务失败";
|
|
26
|
+
}
|
|
27
|
+
function assertCompleted(parsed, request) {
|
|
28
|
+
if (parsed.status === "completed")
|
|
29
|
+
return;
|
|
30
|
+
if (parsed.status === "failed") {
|
|
31
|
+
const message = redactText(responseMessage(parsed), [
|
|
32
|
+
request.instance.apiKey,
|
|
33
|
+
]);
|
|
34
|
+
throw new WebAccessError("provider_error", `XCrawl 任务失败: ${message}`, {
|
|
35
|
+
provider: ref(request.instance),
|
|
36
|
+
retryable: true,
|
|
37
|
+
raw: parsed,
|
|
38
|
+
});
|
|
39
|
+
}
|
|
40
|
+
throw new WebAccessError("invalid_response", "XCrawl 返回未知任务状态", {
|
|
41
|
+
provider: ref(request.instance),
|
|
42
|
+
retryable: true,
|
|
43
|
+
raw: parsed,
|
|
44
|
+
});
|
|
45
|
+
}
|
|
46
|
+
function queryWithFilters(request) {
|
|
47
|
+
const parts = [
|
|
48
|
+
searchQueryWithDomains(request.query, request.includeDomains, request.excludeDomains),
|
|
49
|
+
];
|
|
50
|
+
if (request.instance.searchFilterMode === "best_effort" && request.freshness)
|
|
51
|
+
parts.push(`after:${freshnessStartDate(request.freshness)}`);
|
|
52
|
+
return parts.join(" ");
|
|
53
|
+
}
|
|
54
|
+
function requestHeaders(request) {
|
|
55
|
+
const key = requireCredential(request.instance);
|
|
56
|
+
const headers = providerHeaders(request.instance, {
|
|
57
|
+
"Content-Type": "application/json",
|
|
58
|
+
Accept: "application/json",
|
|
59
|
+
});
|
|
60
|
+
for (const name of Object.keys(headers))
|
|
61
|
+
if (name.toLowerCase() === "authorization")
|
|
62
|
+
delete headers[name];
|
|
63
|
+
headers.Authorization = `Bearer ${key}`;
|
|
64
|
+
return headers;
|
|
65
|
+
}
|
|
66
|
+
function normalizedMarkdown(value) {
|
|
67
|
+
return value
|
|
68
|
+
.replace(/\r\n/g, "\n")
|
|
69
|
+
.replace(/[ \t]+\n/g, "\n")
|
|
70
|
+
.trim();
|
|
71
|
+
}
|
|
72
|
+
function httpUrl(value) {
|
|
73
|
+
if (typeof value !== "string")
|
|
74
|
+
return undefined;
|
|
75
|
+
try {
|
|
76
|
+
const parsed = new URL(value);
|
|
77
|
+
return parsed.protocol === "http:" || parsed.protocol === "https:"
|
|
78
|
+
? parsed.toString()
|
|
79
|
+
: undefined;
|
|
80
|
+
}
|
|
81
|
+
catch {
|
|
82
|
+
return undefined;
|
|
83
|
+
}
|
|
84
|
+
}
|
|
85
|
+
const xcrawl = {
|
|
86
|
+
type: "xcrawl",
|
|
87
|
+
capabilities: ["search", "extract"],
|
|
88
|
+
isConfigured: (instance) => !!instance.apiKey && !!instance.baseUrl,
|
|
89
|
+
async search(request) {
|
|
90
|
+
if (request.freshness &&
|
|
91
|
+
(request.instance.searchFilterMode ?? "strict") === "strict")
|
|
92
|
+
throw new WebAccessError("provider_unavailable", "XCrawl 严格模式不支持 freshness", { provider: ref(request.instance), retryable: true });
|
|
93
|
+
const response = await request.transport.request(buildEndpoint(requireBaseUrl(request.instance), "v1/search"), {
|
|
94
|
+
method: "POST",
|
|
95
|
+
headers: requestHeaders(request),
|
|
96
|
+
body: JSON.stringify({
|
|
97
|
+
query: queryWithFilters(request),
|
|
98
|
+
limit: request.includeDomains.length || request.excludeDomains.length
|
|
99
|
+
? 20
|
|
100
|
+
: request.limit,
|
|
101
|
+
}),
|
|
102
|
+
signal: request.signal,
|
|
103
|
+
maxResponseBytes: request.maxResponseBytes,
|
|
104
|
+
});
|
|
105
|
+
assertOk(response, request.instance);
|
|
106
|
+
const parsed = parseJsonResponse(response, request.instance);
|
|
107
|
+
assertCompleted(parsed, request);
|
|
108
|
+
if (!isRecord(parsed.data) || !Array.isArray(parsed.data.data))
|
|
109
|
+
throw new WebAccessError("invalid_response", "XCrawl Search 返回缺少 data.data", {
|
|
110
|
+
provider: ref(request.instance),
|
|
111
|
+
retryable: true,
|
|
112
|
+
raw: parsed,
|
|
113
|
+
});
|
|
114
|
+
return {
|
|
115
|
+
data: {
|
|
116
|
+
results: normalizeHits(parsed.data.data, request.limit, request.includeDomains, request.excludeDomains),
|
|
117
|
+
},
|
|
118
|
+
raw: parsed,
|
|
119
|
+
};
|
|
120
|
+
},
|
|
121
|
+
async extract(request) {
|
|
122
|
+
const response = await request.transport.request(buildEndpoint(requireBaseUrl(request.instance), "v1/scrape"), {
|
|
123
|
+
method: "POST",
|
|
124
|
+
headers: requestHeaders(request),
|
|
125
|
+
body: JSON.stringify({
|
|
126
|
+
url: request.url,
|
|
127
|
+
mode: "sync",
|
|
128
|
+
output: { formats: ["markdown"] },
|
|
129
|
+
}),
|
|
130
|
+
signal: request.signal,
|
|
131
|
+
maxResponseBytes: request.maxResponseBytes,
|
|
132
|
+
});
|
|
133
|
+
assertOk(response, request.instance);
|
|
134
|
+
const parsed = parseJsonResponse(response, request.instance);
|
|
135
|
+
assertCompleted(parsed, request);
|
|
136
|
+
if (!isRecord(parsed.data))
|
|
137
|
+
throw new WebAccessError("invalid_response", "XCrawl Scrape 返回缺少 data", {
|
|
138
|
+
provider: ref(request.instance),
|
|
139
|
+
retryable: true,
|
|
140
|
+
raw: parsed,
|
|
141
|
+
});
|
|
142
|
+
const content = stringField(parsed.data.markdown);
|
|
143
|
+
if (!content)
|
|
144
|
+
throw new WebAccessError("no_usable_content", "XCrawl Scrape 没有返回 Markdown 正文", {
|
|
145
|
+
provider: ref(request.instance),
|
|
146
|
+
retryable: true,
|
|
147
|
+
raw: parsed,
|
|
148
|
+
});
|
|
149
|
+
const markdown = normalizedMarkdown(content);
|
|
150
|
+
const metadata = isRecord(parsed.data.metadata)
|
|
151
|
+
? parsed.data.metadata
|
|
152
|
+
: undefined;
|
|
153
|
+
const title = stringField(metadata?.title) ??
|
|
154
|
+
/^#\s+(.+)$/m.exec(markdown)?.[1]?.trim() ??
|
|
155
|
+
"";
|
|
156
|
+
return {
|
|
157
|
+
data: {
|
|
158
|
+
document: {
|
|
159
|
+
sourceUrl: httpUrl(metadata?.final_url) ?? httpUrl(parsed.url) ?? request.url,
|
|
160
|
+
title,
|
|
161
|
+
content: markdown,
|
|
162
|
+
contentType: "text/markdown",
|
|
163
|
+
},
|
|
164
|
+
},
|
|
165
|
+
raw: parsed,
|
|
166
|
+
};
|
|
167
|
+
},
|
|
168
|
+
};
|
|
169
|
+
export const XCRAWL_ADAPTER = xcrawl;
|
|
170
|
+
//# sourceMappingURL=xcrawl.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"xcrawl.js","sourceRoot":"","sources":["../../src/providers/xcrawl.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAS/D,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AACrD,OAAO,EACN,QAAQ,EACR,kBAAkB,EAClB,aAAa,EACb,iBAAiB,EACjB,eAAe,EACf,GAAG,EACH,cAAc,EACd,iBAAiB,EACjB,sBAAsB,GACtB,MAAM,aAAa,CAAC;AAErB,SAAS,QAAQ,CAAC,KAAc;IAC/B,OAAO,CAAC,CAAC,KAAK,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;AACtE,CAAC;AAED,SAAS,WAAW,CAAC,KAAc;IAClC,OAAO,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC;AAC7E,CAAC;AAED,SAAS,eAAe,CAAC,KAA8B;IACtD,KAAK,MAAM,SAAS,IAAI;QACvB,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,KAAK;QACX,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS;QACrD,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS;KACnD,EAAE,CAAC;QACH,IAAI,OAAO,SAAS,KAAK,QAAQ,IAAI,SAAS,CAAC,IAAI,EAAE;YACpD,OAAO,SAAS,CAAC,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;QACvC,IAAI,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;YACzB,MAAM,MAAM,GACX,WAAW,CAAC,SAAS,CAAC,OAAO,CAAC,IAAI,WAAW,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;YAChE,IAAI,MAAM;gBAAE,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;QACzC,CAAC;IACF,CAAC;IACD,OAAO,QAAQ,CAAC;AACjB,CAAC;AAED,SAAS,eAAe,CACvB,MAA+B,EAC/B,OAAqD;IAErD,IAAI,MAAM,CAAC,MAAM,KAAK,WAAW;QAAE,OAAO;IAC1C,IAAI,MAAM,CAAC,MAAM,KAAK,QAAQ,EAAE,CAAC;QAChC,MAAM,OAAO,GAAG,UAAU,CAAC,eAAe,CAAC,MAAM,CAAC,EAAE;YACnD,OAAO,CAAC,QAAQ,CAAC,MAAM;SACvB,CAAC,CAAC;QACH,MAAM,IAAI,cAAc,CAAC,gBAAgB,EAAE,gBAAgB,OAAO,EAAE,EAAE;YACrE,QAAQ,EAAE,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC;YAC/B,SAAS,EAAE,IAAI;YACf,GAAG,EAAE,MAAM;SACX,CAAC,CAAC;IACJ,CAAC;IACD,MAAM,IAAI,cAAc,CAAC,kBAAkB,EAAE,iBAAiB,EAAE;QAC/D,QAAQ,EAAE,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC;QAC/B,SAAS,EAAE,IAAI;QACf,GAAG,EAAE,MAAM;KACX,CAAC,CAAC;AACJ,CAAC;AAED,SAAS,gBAAgB,CAAC,OAA6B;IACtD,MAAM,KAAK,GAAG;QACb,sBAAsB,CACrB,OAAO,CAAC,KAAK,EACb,OAAO,CAAC,cAAc,EACtB,OAAO,CAAC,cAAc,CACtB;KACD,CAAC;IACF,IAAI,OAAO,CAAC,QAAQ,CAAC,gBAAgB,KAAK,aAAa,IAAI,OAAO,CAAC,SAAS;QAC3E,KAAK,CAAC,IAAI,CAAC,SAAS,kBAAkB,CAAC,OAAO,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC;IAC9D,OAAO,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AACxB,CAAC;AAED,SAAS,cAAc,CACtB,OAAqD;IAErD,MAAM,GAAG,GAAG,iBAAiB,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;IAChD,MAAM,OAAO,GAAG,eAAe,CAAC,OAAO,CAAC,QAAQ,EAAE;QACjD,cAAc,EAAE,kBAAkB;QAClC,MAAM,EAAE,kBAAkB;KAC1B,CAAC,CAAC;IACH,KAAK,MAAM,IAAI,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC;QACtC,IAAI,IAAI,CAAC,WAAW,EAAE,KAAK,eAAe;YAAE,OAAO,OAAO,CAAC,IAAI,CAAC,CAAC;IAClE,OAAO,CAAC,aAAa,GAAG,UAAU,GAAG,EAAE,CAAC;IACxC,OAAO,OAAO,CAAC;AAChB,CAAC;AAED,SAAS,kBAAkB,CAAC,KAAa;IACxC,OAAO,KAAK;SACV,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC;SACtB,OAAO,CAAC,WAAW,EAAE,IAAI,CAAC;SAC1B,IAAI,EAAE,CAAC;AACV,CAAC;AAED,SAAS,OAAO,CAAC,KAAc;IAC9B,IAAI,OAAO,KAAK,KAAK,QAAQ;QAAE,OAAO,SAAS,CAAC;IAChD,IAAI,CAAC;QACJ,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC;QAC9B,OAAO,MAAM,CAAC,QAAQ,KAAK,OAAO,IAAI,MAAM,CAAC,QAAQ,KAAK,QAAQ;YACjE,CAAC,CAAC,MAAM,CAAC,QAAQ,EAAE;YACnB,CAAC,CAAC,SAAS,CAAC;IACd,CAAC;IAAC,MAAM,CAAC;QACR,OAAO,SAAS,CAAC;IAClB,CAAC;AACF,CAAC;AAED,MAAM,MAAM,GAAoB;IAC/B,IAAI,EAAE,QAAQ;IACd,YAAY,EAAE,CAAC,QAAQ,EAAE,SAAS,CAAC;IACnC,YAAY,EAAE,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,IAAI,CAAC,CAAC,QAAQ,CAAC,OAAO;IACnE,KAAK,CAAC,MAAM,CAAC,OAAO;QACnB,IACC,OAAO,CAAC,SAAS;YACjB,CAAC,OAAO,CAAC,QAAQ,CAAC,gBAAgB,IAAI,QAAQ,CAAC,KAAK,QAAQ;YAE5D,MAAM,IAAI,cAAc,CACvB,sBAAsB,EACtB,0BAA0B,EAC1B,EAAE,QAAQ,EAAE,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,SAAS,EAAE,IAAI,EAAE,CACpD,CAAC;QACH,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAC,SAAS,CAAC,OAAO,CAC/C,aAAa,CAAC,cAAc,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,WAAW,CAAC,EAC5D;YACC,MAAM,EAAE,MAAM;YACd,OAAO,EAAE,cAAc,CAAC,OAAO,CAAC;YAChC,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC;gBACpB,KAAK,EAAE,gBAAgB,CAAC,OAAO,CAAC;gBAChC,KAAK,EACJ,OAAO,CAAC,cAAc,CAAC,MAAM,IAAI,OAAO,CAAC,cAAc,CAAC,MAAM;oBAC7D,CAAC,CAAC,EAAE;oBACJ,CAAC,CAAC,OAAO,CAAC,KAAK;aACjB,CAAC;YACF,MAAM,EAAE,OAAO,CAAC,MAAM;YACtB,gBAAgB,EAAE,OAAO,CAAC,gBAAgB;SAC1C,CACD,CAAC;QACF,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QACrC,MAAM,MAAM,GAAG,iBAAiB,CAAC,QAAQ,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAC7D,eAAe,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;QACjC,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC;YAC7D,MAAM,IAAI,cAAc,CACvB,kBAAkB,EAClB,8BAA8B,EAC9B;gBACC,QAAQ,EAAE,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC;gBAC/B,SAAS,EAAE,IAAI;gBACf,GAAG,EAAE,MAAM;aACX,CACD,CAAC;QACH,OAAO;YACN,IAAI,EAAE;gBACL,OAAO,EAAE,aAAa,CACrB,MAAM,CAAC,IAAI,CAAC,IAAI,EAChB,OAAO,CAAC,KAAK,EACb,OAAO,CAAC,cAAc,EACtB,OAAO,CAAC,cAAc,CACtB;aACD;YACD,GAAG,EAAE,MAAM;SACX,CAAC;IACH,CAAC;IACD,KAAK,CAAC,OAAO,CAAC,OAAO;QACpB,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAC,SAAS,CAAC,OAAO,CAC/C,aAAa,CAAC,cAAc,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,WAAW,CAAC,EAC5D;YACC,MAAM,EAAE,MAAM;YACd,OAAO,EAAE,cAAc,CAAC,OAAO,CAAC;YAChC,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC;gBACpB,GAAG,EAAE,OAAO,CAAC,GAAG;gBAChB,IAAI,EAAE,MAAM;gBACZ,MAAM,EAAE,EAAE,OAAO,EAAE,CAAC,UAAU,CAAC,EAAE;aACjC,CAAC;YACF,MAAM,EAAE,OAAO,CAAC,MAAM;YACtB,gBAAgB,EAAE,OAAO,CAAC,gBAAgB;SAC1C,CACD,CAAC;QACF,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QACrC,MAAM,MAAM,GAAG,iBAAiB,CAAC,QAAQ,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAC7D,eAAe,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;QACjC,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,CAAC;YACzB,MAAM,IAAI,cAAc,CACvB,kBAAkB,EAClB,yBAAyB,EACzB;gBACC,QAAQ,EAAE,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC;gBAC/B,SAAS,EAAE,IAAI;gBACf,GAAG,EAAE,MAAM;aACX,CACD,CAAC;QACH,MAAM,OAAO,GAAG,WAAW,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;QAClD,IAAI,CAAC,OAAO;YACX,MAAM,IAAI,cAAc,CACvB,mBAAmB,EACnB,gCAAgC,EAChC;gBACC,QAAQ,EAAE,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC;gBAC/B,SAAS,EAAE,IAAI;gBACf,GAAG,EAAE,MAAM;aACX,CACD,CAAC;QACH,MAAM,QAAQ,GAAG,kBAAkB,CAAC,OAAO,CAAC,CAAC;QAC7C,MAAM,QAAQ,GAAG,QAAQ,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC;YAC9C,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ;YACtB,CAAC,CAAC,SAAS,CAAC;QACb,MAAM,KAAK,GACV,WAAW,CAAC,QAAQ,EAAE,KAAK,CAAC;YAC5B,aAAa,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE;YACzC,EAAE,CAAC;QACJ,OAAO;YACN,IAAI,EAAE;gBACL,QAAQ,EAAE;oBACT,SAAS,EACR,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,IAAI,OAAO,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,OAAO,CAAC,GAAG;oBACnE,KAAK;oBACL,OAAO,EAAE,QAAQ;oBACjB,WAAW,EAAE,eAAe;iBAC5B;aACD;YACD,GAAG,EAAE,MAAM;SACX,CAAC;IACH,CAAC;CACD,CAAC;AAEF,MAAM,CAAC,MAAM,cAAc,GAAG,MAAM,CAAC"}
|
|
@@ -0,0 +1,175 @@
|
|
|
1
|
+
import { EnvHttpProxyAgent, fetch as undiciFetch, } from "undici";
|
|
2
|
+
import { WebAccessError } from "../core/errors.js";
|
|
3
|
+
const REDIRECT_STATUSES = new Set([301, 302, 303, 307, 308]);
|
|
4
|
+
const SENSITIVE_HEADERS = new Set([
|
|
5
|
+
"authorization",
|
|
6
|
+
"cookie",
|
|
7
|
+
"proxy-authorization",
|
|
8
|
+
"x-api-key",
|
|
9
|
+
"x-subscription-token",
|
|
10
|
+
"x-auth-token",
|
|
11
|
+
"x-access-token",
|
|
12
|
+
]);
|
|
13
|
+
function isAbortLike(error, signal) {
|
|
14
|
+
if (signal.aborted)
|
|
15
|
+
return true;
|
|
16
|
+
if (!(error instanceof Error))
|
|
17
|
+
return false;
|
|
18
|
+
return (error.name === "AbortError" ||
|
|
19
|
+
error.name === "TimeoutError" ||
|
|
20
|
+
/aborted|timed out|timeout/i.test(error.message));
|
|
21
|
+
}
|
|
22
|
+
function stripSensitiveHeaders(headers) {
|
|
23
|
+
return Object.fromEntries(Object.entries(headers).filter(([name]) => !SENSITIVE_HEADERS.has(name.toLowerCase())));
|
|
24
|
+
}
|
|
25
|
+
function decodeBody(buffer, headers) {
|
|
26
|
+
const contentType = headers.get("content-type") ?? "";
|
|
27
|
+
const charset = contentType.match(/charset\s*=\s*["']?([^;"'\s]+)/i)?.[1] ?? "utf-8";
|
|
28
|
+
try {
|
|
29
|
+
return new TextDecoder(charset).decode(buffer);
|
|
30
|
+
}
|
|
31
|
+
catch {
|
|
32
|
+
return new TextDecoder("utf-8").decode(buffer);
|
|
33
|
+
}
|
|
34
|
+
}
|
|
35
|
+
async function readBody(response, maxBytes, signal) {
|
|
36
|
+
const reader = response.body?.getReader();
|
|
37
|
+
if (!reader) {
|
|
38
|
+
const buffer = new Uint8Array(await response.arrayBuffer());
|
|
39
|
+
if (buffer.byteLength > maxBytes)
|
|
40
|
+
throw new WebAccessError("response_too_large", `响应超过 ${maxBytes} 字节`, { retryable: true });
|
|
41
|
+
return decodeBody(buffer, response.headers);
|
|
42
|
+
}
|
|
43
|
+
const chunks = [];
|
|
44
|
+
let size = 0;
|
|
45
|
+
try {
|
|
46
|
+
while (true) {
|
|
47
|
+
if (signal.aborted)
|
|
48
|
+
throw new WebAccessError("aborted", "请求已取消");
|
|
49
|
+
const { done, value } = await reader.read();
|
|
50
|
+
if (done)
|
|
51
|
+
break;
|
|
52
|
+
if (!value)
|
|
53
|
+
continue;
|
|
54
|
+
size += value.byteLength;
|
|
55
|
+
if (size > maxBytes) {
|
|
56
|
+
await reader.cancel();
|
|
57
|
+
throw new WebAccessError("response_too_large", `响应超过 ${maxBytes} 字节`, { retryable: true });
|
|
58
|
+
}
|
|
59
|
+
chunks.push(value);
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
finally {
|
|
63
|
+
reader.releaseLock();
|
|
64
|
+
}
|
|
65
|
+
const buffer = new Uint8Array(size);
|
|
66
|
+
let offset = 0;
|
|
67
|
+
for (const chunk of chunks) {
|
|
68
|
+
buffer.set(chunk, offset);
|
|
69
|
+
offset += chunk.byteLength;
|
|
70
|
+
}
|
|
71
|
+
return decodeBody(buffer, response.headers);
|
|
72
|
+
}
|
|
73
|
+
export function jsonBody(text, provider) {
|
|
74
|
+
try {
|
|
75
|
+
const value = JSON.parse(text);
|
|
76
|
+
if (!value || typeof value !== "object" || Array.isArray(value)) {
|
|
77
|
+
throw new Error("响应 JSON 根节点不是对象");
|
|
78
|
+
}
|
|
79
|
+
return value;
|
|
80
|
+
}
|
|
81
|
+
catch (error) {
|
|
82
|
+
throw new WebAccessError("invalid_response", `${provider} 返回了无效 JSON: ${error instanceof Error ? error.message : String(error)}`);
|
|
83
|
+
}
|
|
84
|
+
}
|
|
85
|
+
export function buildEndpoint(baseUrl, path) {
|
|
86
|
+
const base = baseUrl.endsWith("/") ? baseUrl : `${baseUrl}/`;
|
|
87
|
+
return new URL(path.replace(/^\//, ""), base).toString();
|
|
88
|
+
}
|
|
89
|
+
export class DefaultHttpTransport {
|
|
90
|
+
dispatcher = new EnvHttpProxyAgent();
|
|
91
|
+
async request(rawUrl, options) {
|
|
92
|
+
let current = typeof rawUrl === "string" ? new URL(rawUrl) : new URL(rawUrl.toString());
|
|
93
|
+
if (current.protocol !== "http:" && current.protocol !== "https:")
|
|
94
|
+
throw new WebAccessError("invalid_input", "只能请求 HTTP(S) URL");
|
|
95
|
+
let method = (options.method ?? "GET").toUpperCase();
|
|
96
|
+
let body = options.body;
|
|
97
|
+
let headers = { ...(options.headers ?? {}) };
|
|
98
|
+
const maxRedirects = options.maxRedirects ?? 5;
|
|
99
|
+
for (let redirectCount = 0; redirectCount <= maxRedirects; redirectCount++) {
|
|
100
|
+
let response;
|
|
101
|
+
try {
|
|
102
|
+
response = await undiciFetch(current, {
|
|
103
|
+
method,
|
|
104
|
+
...(body !== undefined ? { body } : {}),
|
|
105
|
+
headers,
|
|
106
|
+
signal: options.signal,
|
|
107
|
+
dispatcher: this.dispatcher,
|
|
108
|
+
});
|
|
109
|
+
}
|
|
110
|
+
catch (error) {
|
|
111
|
+
if (isAbortLike(error, options.signal)) {
|
|
112
|
+
throw new WebAccessError(options.signal.aborted ? "aborted" : "timeout", "HTTP 请求超时或已取消", { retryable: options.signal.aborted === false });
|
|
113
|
+
}
|
|
114
|
+
throw new WebAccessError("network_error", error instanceof Error ? error.message : String(error), { retryable: true });
|
|
115
|
+
}
|
|
116
|
+
if (!REDIRECT_STATUSES.has(response.status)) {
|
|
117
|
+
const text = await readBody(response, options.maxResponseBytes, options.signal);
|
|
118
|
+
return {
|
|
119
|
+
status: response.status,
|
|
120
|
+
statusText: response.statusText,
|
|
121
|
+
url: response.url || current.toString(),
|
|
122
|
+
headers: response.headers,
|
|
123
|
+
body: text,
|
|
124
|
+
};
|
|
125
|
+
}
|
|
126
|
+
const location = response.headers.get("location");
|
|
127
|
+
if (!location) {
|
|
128
|
+
const text = await readBody(response, options.maxResponseBytes, options.signal);
|
|
129
|
+
return {
|
|
130
|
+
status: response.status,
|
|
131
|
+
statusText: response.statusText,
|
|
132
|
+
url: response.url || current.toString(),
|
|
133
|
+
headers: response.headers,
|
|
134
|
+
body: text,
|
|
135
|
+
};
|
|
136
|
+
}
|
|
137
|
+
await response.body?.cancel();
|
|
138
|
+
if (redirectCount === maxRedirects) {
|
|
139
|
+
throw new WebAccessError("provider_error", `重定向次数超过 ${maxRedirects}`, { retryable: true, httpStatus: response.status });
|
|
140
|
+
}
|
|
141
|
+
const next = new URL(location, current);
|
|
142
|
+
if (next.protocol !== "http:" && next.protocol !== "https:")
|
|
143
|
+
throw new WebAccessError("provider_error", "重定向目标不是 HTTP(S) URL", { retryable: false });
|
|
144
|
+
if (next.origin !== current.origin)
|
|
145
|
+
headers = stripSensitiveHeaders(headers);
|
|
146
|
+
if (response.status === 303 ||
|
|
147
|
+
((response.status === 301 || response.status === 302) &&
|
|
148
|
+
method === "POST")) {
|
|
149
|
+
method = "GET";
|
|
150
|
+
body = undefined;
|
|
151
|
+
delete headers["Content-Type"];
|
|
152
|
+
delete headers["content-type"];
|
|
153
|
+
}
|
|
154
|
+
current = next;
|
|
155
|
+
}
|
|
156
|
+
throw new WebAccessError("provider_error", "HTTP 重定向失败", {
|
|
157
|
+
retryable: true,
|
|
158
|
+
});
|
|
159
|
+
}
|
|
160
|
+
}
|
|
161
|
+
export function createAbortSignal(parent, timeoutMs) {
|
|
162
|
+
const timeout = AbortSignal.timeout(Math.max(1, timeoutMs));
|
|
163
|
+
return parent ? AbortSignal.any([parent, timeout]) : timeout;
|
|
164
|
+
}
|
|
165
|
+
export function mergeHeaders(...sources) {
|
|
166
|
+
const result = {};
|
|
167
|
+
for (const source of sources) {
|
|
168
|
+
if (!source)
|
|
169
|
+
continue;
|
|
170
|
+
for (const [name, value] of Object.entries(source))
|
|
171
|
+
result[name] = value;
|
|
172
|
+
}
|
|
173
|
+
return result;
|
|
174
|
+
}
|
|
175
|
+
//# sourceMappingURL=http.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"http.js","sourceRoot":"","sources":["../../src/transport/http.ts"],"names":[],"mappings":"AAAA,OAAO,EACN,iBAAiB,EAEjB,KAAK,IAAI,WAAW,GACpB,MAAM,QAAQ,CAAC;AAChB,OAAO,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAEnD,MAAM,iBAAiB,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC;AAC7D,MAAM,iBAAiB,GAAG,IAAI,GAAG,CAAC;IACjC,eAAe;IACf,QAAQ;IACR,qBAAqB;IACrB,WAAW;IACX,sBAAsB;IACtB,cAAc;IACd,gBAAgB;CAChB,CAAC,CAAC;AA0BH,SAAS,WAAW,CAAC,KAAc,EAAE,MAAmB;IACvD,IAAI,MAAM,CAAC,OAAO;QAAE,OAAO,IAAI,CAAC;IAChC,IAAI,CAAC,CAAC,KAAK,YAAY,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IAC5C,OAAO,CACN,KAAK,CAAC,IAAI,KAAK,YAAY;QAC3B,KAAK,CAAC,IAAI,KAAK,cAAc;QAC7B,4BAA4B,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,CAChD,CAAC;AACH,CAAC;AAED,SAAS,qBAAqB,CAC7B,OAA+B;IAE/B,OAAO,MAAM,CAAC,WAAW,CACxB,MAAM,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,MAAM,CAC7B,CAAC,CAAC,IAAI,CAAC,EAAE,EAAE,CAAC,CAAC,iBAAiB,CAAC,GAAG,CAAC,IAAI,CAAC,WAAW,EAAE,CAAC,CACtD,CACD,CAAC;AACH,CAAC;AAED,SAAS,UAAU,CAAC,MAAkB,EAAE,OAAsB;IAC7D,MAAM,WAAW,GAAG,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC;IACtD,MAAM,OAAO,GACZ,WAAW,CAAC,KAAK,CAAC,iCAAiC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,OAAO,CAAC;IACtE,IAAI,CAAC;QACJ,OAAO,IAAI,WAAW,CAAC,OAAO,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;IAChD,CAAC;IAAC,MAAM,CAAC;QACR,OAAO,IAAI,WAAW,CAAC,OAAO,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;IAChD,CAAC;AACF,CAAC;AAED,KAAK,UAAU,QAAQ,CACtB,QAIC,EACD,QAAgB,EAChB,MAAmB;IAEnB,MAAM,MAAM,GACX,QAAQ,CAAC,IAOT,EAAE,SAAS,EAAE,CAAC;IACf,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,MAAM,MAAM,GAAG,IAAI,UAAU,CAAC,MAAM,QAAQ,CAAC,WAAW,EAAE,CAAC,CAAC;QAC5D,IAAI,MAAM,CAAC,UAAU,GAAG,QAAQ;YAC/B,MAAM,IAAI,cAAc,CACvB,oBAAoB,EACpB,QAAQ,QAAQ,KAAK,EACrB,EAAE,SAAS,EAAE,IAAI,EAAE,CACnB,CAAC;QACH,OAAO,UAAU,CAAC,MAAM,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC;IAC7C,CAAC;IACD,MAAM,MAAM,GAAiB,EAAE,CAAC;IAChC,IAAI,IAAI,GAAG,CAAC,CAAC;IACb,IAAI,CAAC;QACJ,OAAO,IAAI,EAAE,CAAC;YACb,IAAI,MAAM,CAAC,OAAO;gBAAE,MAAM,IAAI,cAAc,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;YACjE,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,GAAG,MAAM,MAAM,CAAC,IAAI,EAAE,CAAC;YAC5C,IAAI,IAAI;gBAAE,MAAM;YAChB,IAAI,CAAC,KAAK;gBAAE,SAAS;YACrB,IAAI,IAAI,KAAK,CAAC,UAAU,CAAC;YACzB,IAAI,IAAI,GAAG,QAAQ,EAAE,CAAC;gBACrB,MAAM,MAAM,CAAC,MAAM,EAAE,CAAC;gBACtB,MAAM,IAAI,cAAc,CACvB,oBAAoB,EACpB,QAAQ,QAAQ,KAAK,EACrB,EAAE,SAAS,EAAE,IAAI,EAAE,CACnB,CAAC;YACH,CAAC;YACD,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QACpB,CAAC;IACF,CAAC;YAAS,CAAC;QACV,MAAM,CAAC,WAAW,EAAE,CAAC;IACtB,CAAC;IACD,MAAM,MAAM,GAAG,IAAI,UAAU,CAAC,IAAI,CAAC,CAAC;IACpC,IAAI,MAAM,GAAG,CAAC,CAAC;IACf,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,MAAM,CAAC,GAAG,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;QAC1B,MAAM,IAAI,KAAK,CAAC,UAAU,CAAC;IAC5B,CAAC;IACD,OAAO,UAAU,CAAC,MAAM,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC;AAC7C,CAAC;AAED,MAAM,UAAU,QAAQ,CACvB,IAAY,EACZ,QAAgB;IAEhB,IAAI,CAAC;QACJ,MAAM,KAAK,GAAY,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACxC,IAAI,CAAC,KAAK,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;YACjE,MAAM,IAAI,KAAK,CAAC,iBAAiB,CAAC,CAAC;QACpC,CAAC;QACD,OAAO,KAAgC,CAAC;IACzC,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QAChB,MAAM,IAAI,cAAc,CACvB,kBAAkB,EAClB,GAAG,QAAQ,gBAAgB,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CACnF,CAAC;IACH,CAAC;AACF,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,OAAe,EAAE,IAAY;IAC1D,MAAM,IAAI,GAAG,OAAO,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,OAAO,GAAG,CAAC;IAC7D,OAAO,IAAI,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,EAAE,IAAI,CAAC,CAAC,QAAQ,EAAE,CAAC;AAC1D,CAAC;AAED,MAAM,OAAO,oBAAoB;IACf,UAAU,GAAG,IAAI,iBAAiB,EAAE,CAAC;IAEtD,KAAK,CAAC,OAAO,CACZ,MAAoB,EACpB,OAA2B;QAE3B,IAAI,OAAO,GACV,OAAO,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,MAAM,CAAC,QAAQ,EAAE,CAAC,CAAC;QAC3E,IAAI,OAAO,CAAC,QAAQ,KAAK,OAAO,IAAI,OAAO,CAAC,QAAQ,KAAK,QAAQ;YAChE,MAAM,IAAI,cAAc,CAAC,eAAe,EAAE,kBAAkB,CAAC,CAAC;QAC/D,IAAI,MAAM,GAAG,CAAC,OAAO,CAAC,MAAM,IAAI,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC;QACrD,IAAI,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC;QACxB,IAAI,OAAO,GAAG,EAAE,GAAG,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC,EAAE,CAAC;QAC7C,MAAM,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,CAAC,CAAC;QAE/C,KACC,IAAI,aAAa,GAAG,CAAC,EACrB,aAAa,IAAI,YAAY,EAC7B,aAAa,EAAE,EACd,CAAC;YACF,IAAI,QAAiD,CAAC;YACtD,IAAI,CAAC;gBACJ,QAAQ,GAAG,MAAM,WAAW,CAAC,OAAO,EAAE;oBACrC,MAAM;oBACN,GAAG,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBACvC,OAAO;oBACP,MAAM,EAAE,OAAO,CAAC,MAAM;oBACtB,UAAU,EAAE,IAAI,CAAC,UAAU;iBAClB,CAAC,CAAC;YACb,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBAChB,IAAI,WAAW,CAAC,KAAK,EAAE,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC;oBACxC,MAAM,IAAI,cAAc,CACvB,OAAO,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,SAAS,EAC9C,eAAe,EACf,EAAE,SAAS,EAAE,OAAO,CAAC,MAAM,CAAC,OAAO,KAAK,KAAK,EAAE,CAC/C,CAAC;gBACH,CAAC;gBACD,MAAM,IAAI,cAAc,CACvB,eAAe,EACf,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EACtD,EAAE,SAAS,EAAE,IAAI,EAAE,CACnB,CAAC;YACH,CAAC;YAED,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;gBAC7C,MAAM,IAAI,GAAG,MAAM,QAAQ,CAC1B,QAAQ,EACR,OAAO,CAAC,gBAAgB,EACxB,OAAO,CAAC,MAAM,CACd,CAAC;gBACF,OAAO;oBACN,MAAM,EAAE,QAAQ,CAAC,MAAM;oBACvB,UAAU,EAAE,QAAQ,CAAC,UAAU;oBAC/B,GAAG,EAAE,QAAQ,CAAC,GAAG,IAAI,OAAO,CAAC,QAAQ,EAAE;oBACvC,OAAO,EAAE,QAAQ,CAAC,OAAO;oBACzB,IAAI,EAAE,IAAI;iBACV,CAAC;YACH,CAAC;YAED,MAAM,QAAQ,GAAG,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;YAClD,IAAI,CAAC,QAAQ,EAAE,CAAC;gBACf,MAAM,IAAI,GAAG,MAAM,QAAQ,CAC1B,QAAQ,EACR,OAAO,CAAC,gBAAgB,EACxB,OAAO,CAAC,MAAM,CACd,CAAC;gBACF,OAAO;oBACN,MAAM,EAAE,QAAQ,CAAC,MAAM;oBACvB,UAAU,EAAE,QAAQ,CAAC,UAAU;oBAC/B,GAAG,EAAE,QAAQ,CAAC,GAAG,IAAI,OAAO,CAAC,QAAQ,EAAE;oBACvC,OAAO,EAAE,QAAQ,CAAC,OAAO;oBACzB,IAAI,EAAE,IAAI;iBACV,CAAC;YACH,CAAC;YACD,MAAM,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,CAAC;YAC9B,IAAI,aAAa,KAAK,YAAY,EAAE,CAAC;gBACpC,MAAM,IAAI,cAAc,CACvB,gBAAgB,EAChB,WAAW,YAAY,EAAE,EACzB,EAAE,SAAS,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,MAAM,EAAE,CAChD,CAAC;YACH,CAAC;YACD,MAAM,IAAI,GAAG,IAAI,GAAG,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;YACxC,IAAI,IAAI,CAAC,QAAQ,KAAK,OAAO,IAAI,IAAI,CAAC,QAAQ,KAAK,QAAQ;gBAC1D,MAAM,IAAI,cAAc,CACvB,gBAAgB,EAChB,qBAAqB,EACrB,EAAE,SAAS,EAAE,KAAK,EAAE,CACpB,CAAC;YACH,IAAI,IAAI,CAAC,MAAM,KAAK,OAAO,CAAC,MAAM;gBACjC,OAAO,GAAG,qBAAqB,CAAC,OAAO,CAAC,CAAC;YAC1C,IACC,QAAQ,CAAC,MAAM,KAAK,GAAG;gBACvB,CAAC,CAAC,QAAQ,CAAC,MAAM,KAAK,GAAG,IAAI,QAAQ,CAAC,MAAM,KAAK,GAAG,CAAC;oBACpD,MAAM,KAAK,MAAM,CAAC,EAClB,CAAC;gBACF,MAAM,GAAG,KAAK,CAAC;gBACf,IAAI,GAAG,SAAS,CAAC;gBACjB,OAAO,OAAO,CAAC,cAAc,CAAC,CAAC;gBAC/B,OAAO,OAAO,CAAC,cAAc,CAAC,CAAC;YAChC,CAAC;YACD,OAAO,GAAG,IAAI,CAAC;QAChB,CAAC;QACD,MAAM,IAAI,cAAc,CAAC,gBAAgB,EAAE,YAAY,EAAE;YACxD,SAAS,EAAE,IAAI;SACf,CAAC,CAAC;IACJ,CAAC;CACD;AAED,MAAM,UAAU,iBAAiB,CAChC,MAA+B,EAC/B,SAAiB;IAEjB,MAAM,OAAO,GAAG,WAAW,CAAC,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;IAC5D,OAAO,MAAM,CAAC,CAAC,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC;AAC9D,CAAC;AAED,MAAM,UAAU,YAAY,CAC3B,GAAG,OAAkD;IAErD,MAAM,MAAM,GAA2B,EAAE,CAAC;IAC1C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC9B,IAAI,CAAC,MAAM;YAAE,SAAS;QACtB,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,MAAM,CAAC;YAAE,MAAM,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC;IAC1E,CAAC;IACD,OAAO,MAAM,CAAC;AACf,CAAC"}
|
package/dist/version.js
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"version.js","sourceRoot":"","sources":["../src/version.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,OAAO,GAAG,OAAO,CAAC"}
|
package/package.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "web-access-cli",
|
|
3
|
+
"version": "0.1.0",
|
|
4
|
+
"description": "Agent-neutral web search and content extraction CLI",
|
|
5
|
+
"license": "MIT",
|
|
6
|
+
"repository": {
|
|
7
|
+
"type": "git",
|
|
8
|
+
"url": "git+https://github.com/Juexe/web-access-cli.git"
|
|
9
|
+
},
|
|
10
|
+
"homepage": "https://github.com/Juexe/web-access-cli#readme",
|
|
11
|
+
"bugs": {
|
|
12
|
+
"url": "https://github.com/Juexe/web-access-cli/issues"
|
|
13
|
+
},
|
|
14
|
+
"keywords": [
|
|
15
|
+
"cli",
|
|
16
|
+
"web-search",
|
|
17
|
+
"content-extraction",
|
|
18
|
+
"agent"
|
|
19
|
+
],
|
|
20
|
+
"type": "module",
|
|
21
|
+
"bin": {
|
|
22
|
+
"web-access": "./dist/cli.js"
|
|
23
|
+
},
|
|
24
|
+
"files": [
|
|
25
|
+
"dist",
|
|
26
|
+
"schemas",
|
|
27
|
+
"README.md",
|
|
28
|
+
"README_CN.md",
|
|
29
|
+
"LICENSE",
|
|
30
|
+
"THIRD_PARTY_NOTICES.md"
|
|
31
|
+
],
|
|
32
|
+
"engines": {
|
|
33
|
+
"node": ">=22.19.0"
|
|
34
|
+
},
|
|
35
|
+
"packageManager": "pnpm@11.16.0",
|
|
36
|
+
"scripts": {
|
|
37
|
+
"build": "tsc -p tsconfig.build.json && node scripts/write-schemas.mjs",
|
|
38
|
+
"typecheck": "tsc -p tsconfig.json --noEmit",
|
|
39
|
+
"test": "tsx --test test/**/*.test.ts",
|
|
40
|
+
"lint": "biome check .",
|
|
41
|
+
"format": "biome format --write .",
|
|
42
|
+
"check": "pnpm lint && pnpm typecheck && pnpm test && pnpm build",
|
|
43
|
+
"pack:check": "pnpm build && pnpm pack --pack-destination .artifacts"
|
|
44
|
+
},
|
|
45
|
+
"dependencies": {
|
|
46
|
+
"@mozilla/readability": "^0.6.0",
|
|
47
|
+
"commander": "^15.0.0",
|
|
48
|
+
"linkedom": "^0.18.12",
|
|
49
|
+
"open": "^11.0.0",
|
|
50
|
+
"turndown": "^7.2.0",
|
|
51
|
+
"typebox": "^1.3.11",
|
|
52
|
+
"undici": "^8.10.0"
|
|
53
|
+
},
|
|
54
|
+
"devDependencies": {
|
|
55
|
+
"@biomejs/biome": "^2.5.7",
|
|
56
|
+
"@types/node": "^24.0.0",
|
|
57
|
+
"@types/turndown": "^5.0.6",
|
|
58
|
+
"tsx": "^4.20.0",
|
|
59
|
+
"typescript": "^5.9.0"
|
|
60
|
+
}
|
|
61
|
+
}
|
|
@@ -0,0 +1,210 @@
|
|
|
1
|
+
{
|
|
2
|
+
"type": "object",
|
|
3
|
+
"properties": {
|
|
4
|
+
"$schema": {
|
|
5
|
+
"type": "string",
|
|
6
|
+
"format": "uri-reference"
|
|
7
|
+
},
|
|
8
|
+
"providers": {
|
|
9
|
+
"type": "array",
|
|
10
|
+
"items": {
|
|
11
|
+
"anyOf": [
|
|
12
|
+
{
|
|
13
|
+
"type": "object",
|
|
14
|
+
"required": [
|
|
15
|
+
"id",
|
|
16
|
+
"type"
|
|
17
|
+
],
|
|
18
|
+
"properties": {
|
|
19
|
+
"id": {
|
|
20
|
+
"type": "string",
|
|
21
|
+
"pattern": "^[a-z][a-z0-9_-]{0,63}$"
|
|
22
|
+
},
|
|
23
|
+
"apiKey": {
|
|
24
|
+
"type": "string"
|
|
25
|
+
},
|
|
26
|
+
"apiKeyEnv": {
|
|
27
|
+
"type": "string",
|
|
28
|
+
"pattern": "^[A-Za-z_][A-Za-z0-9_]*$"
|
|
29
|
+
},
|
|
30
|
+
"baseUrl": {
|
|
31
|
+
"type": "string",
|
|
32
|
+
"format": "uri"
|
|
33
|
+
},
|
|
34
|
+
"baseUrlEnv": {
|
|
35
|
+
"type": "string",
|
|
36
|
+
"pattern": "^[A-Za-z_][A-Za-z0-9_]*$"
|
|
37
|
+
},
|
|
38
|
+
"headers": {
|
|
39
|
+
"type": "object",
|
|
40
|
+
"patternProperties": {
|
|
41
|
+
"^[^\\r\\n]+$": {
|
|
42
|
+
"type": "string",
|
|
43
|
+
"pattern": "^[^\\r\\n]*$"
|
|
44
|
+
}
|
|
45
|
+
},
|
|
46
|
+
"additionalProperties": false
|
|
47
|
+
},
|
|
48
|
+
"type": {
|
|
49
|
+
"anyOf": [
|
|
50
|
+
{
|
|
51
|
+
"type": "string",
|
|
52
|
+
"const": "tavily"
|
|
53
|
+
},
|
|
54
|
+
{
|
|
55
|
+
"type": "string",
|
|
56
|
+
"const": "exa"
|
|
57
|
+
},
|
|
58
|
+
{
|
|
59
|
+
"type": "string",
|
|
60
|
+
"const": "brave"
|
|
61
|
+
},
|
|
62
|
+
{
|
|
63
|
+
"type": "string",
|
|
64
|
+
"const": "searxng"
|
|
65
|
+
},
|
|
66
|
+
{
|
|
67
|
+
"type": "string",
|
|
68
|
+
"const": "firecrawl"
|
|
69
|
+
},
|
|
70
|
+
{
|
|
71
|
+
"type": "string",
|
|
72
|
+
"const": "jina"
|
|
73
|
+
},
|
|
74
|
+
{
|
|
75
|
+
"type": "string",
|
|
76
|
+
"const": "http"
|
|
77
|
+
}
|
|
78
|
+
]
|
|
79
|
+
}
|
|
80
|
+
},
|
|
81
|
+
"additionalProperties": false
|
|
82
|
+
},
|
|
83
|
+
{
|
|
84
|
+
"type": "object",
|
|
85
|
+
"required": [
|
|
86
|
+
"id",
|
|
87
|
+
"type"
|
|
88
|
+
],
|
|
89
|
+
"properties": {
|
|
90
|
+
"id": {
|
|
91
|
+
"type": "string",
|
|
92
|
+
"pattern": "^[a-z][a-z0-9_-]{0,63}$"
|
|
93
|
+
},
|
|
94
|
+
"apiKey": {
|
|
95
|
+
"type": "string"
|
|
96
|
+
},
|
|
97
|
+
"apiKeyEnv": {
|
|
98
|
+
"type": "string",
|
|
99
|
+
"pattern": "^[A-Za-z_][A-Za-z0-9_]*$"
|
|
100
|
+
},
|
|
101
|
+
"baseUrl": {
|
|
102
|
+
"type": "string",
|
|
103
|
+
"format": "uri"
|
|
104
|
+
},
|
|
105
|
+
"baseUrlEnv": {
|
|
106
|
+
"type": "string",
|
|
107
|
+
"pattern": "^[A-Za-z_][A-Za-z0-9_]*$"
|
|
108
|
+
},
|
|
109
|
+
"headers": {
|
|
110
|
+
"type": "object",
|
|
111
|
+
"patternProperties": {
|
|
112
|
+
"^[^\\r\\n]+$": {
|
|
113
|
+
"type": "string",
|
|
114
|
+
"pattern": "^[^\\r\\n]*$"
|
|
115
|
+
}
|
|
116
|
+
},
|
|
117
|
+
"additionalProperties": false
|
|
118
|
+
},
|
|
119
|
+
"type": {
|
|
120
|
+
"anyOf": [
|
|
121
|
+
{
|
|
122
|
+
"type": "string",
|
|
123
|
+
"const": "anysearch"
|
|
124
|
+
},
|
|
125
|
+
{
|
|
126
|
+
"type": "string",
|
|
127
|
+
"const": "xcrawl"
|
|
128
|
+
}
|
|
129
|
+
]
|
|
130
|
+
},
|
|
131
|
+
"searchFilterMode": {
|
|
132
|
+
"anyOf": [
|
|
133
|
+
{
|
|
134
|
+
"type": "string",
|
|
135
|
+
"const": "strict"
|
|
136
|
+
},
|
|
137
|
+
{
|
|
138
|
+
"type": "string",
|
|
139
|
+
"const": "best_effort"
|
|
140
|
+
}
|
|
141
|
+
]
|
|
142
|
+
}
|
|
143
|
+
},
|
|
144
|
+
"additionalProperties": false
|
|
145
|
+
}
|
|
146
|
+
]
|
|
147
|
+
}
|
|
148
|
+
},
|
|
149
|
+
"search": {
|
|
150
|
+
"type": "object",
|
|
151
|
+
"properties": {
|
|
152
|
+
"providers": {
|
|
153
|
+
"type": "array",
|
|
154
|
+
"items": {
|
|
155
|
+
"type": "string",
|
|
156
|
+
"pattern": "^[a-z][a-z0-9_-]{0,63}$"
|
|
157
|
+
}
|
|
158
|
+
},
|
|
159
|
+
"limit": {
|
|
160
|
+
"type": "integer",
|
|
161
|
+
"minimum": 1,
|
|
162
|
+
"maximum": 20
|
|
163
|
+
},
|
|
164
|
+
"timeoutMs": {
|
|
165
|
+
"type": "integer",
|
|
166
|
+
"minimum": 1
|
|
167
|
+
},
|
|
168
|
+
"attemptTimeoutMs": {
|
|
169
|
+
"type": "integer",
|
|
170
|
+
"minimum": 1
|
|
171
|
+
},
|
|
172
|
+
"maxResponseBytes": {
|
|
173
|
+
"type": "integer",
|
|
174
|
+
"minimum": 1
|
|
175
|
+
}
|
|
176
|
+
},
|
|
177
|
+
"additionalProperties": false
|
|
178
|
+
},
|
|
179
|
+
"extract": {
|
|
180
|
+
"type": "object",
|
|
181
|
+
"properties": {
|
|
182
|
+
"providers": {
|
|
183
|
+
"type": "array",
|
|
184
|
+
"items": {
|
|
185
|
+
"type": "string",
|
|
186
|
+
"pattern": "^[a-z][a-z0-9_-]{0,63}$"
|
|
187
|
+
}
|
|
188
|
+
},
|
|
189
|
+
"timeoutMs": {
|
|
190
|
+
"type": "integer",
|
|
191
|
+
"minimum": 1
|
|
192
|
+
},
|
|
193
|
+
"attemptTimeoutMs": {
|
|
194
|
+
"type": "integer",
|
|
195
|
+
"minimum": 1
|
|
196
|
+
},
|
|
197
|
+
"maxResponseBytes": {
|
|
198
|
+
"type": "integer",
|
|
199
|
+
"minimum": 1
|
|
200
|
+
},
|
|
201
|
+
"minContentCharacters": {
|
|
202
|
+
"type": "integer",
|
|
203
|
+
"minimum": 1
|
|
204
|
+
}
|
|
205
|
+
},
|
|
206
|
+
"additionalProperties": false
|
|
207
|
+
}
|
|
208
|
+
},
|
|
209
|
+
"additionalProperties": false
|
|
210
|
+
}
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
{
|
|
2
|
+
"type": "object",
|
|
3
|
+
"required": [
|
|
4
|
+
"url",
|
|
5
|
+
"provider"
|
|
6
|
+
],
|
|
7
|
+
"properties": {
|
|
8
|
+
"url": {
|
|
9
|
+
"type": "string",
|
|
10
|
+
"format": "uri"
|
|
11
|
+
},
|
|
12
|
+
"provider": {
|
|
13
|
+
"type": "string",
|
|
14
|
+
"minLength": 1
|
|
15
|
+
},
|
|
16
|
+
"timeoutMs": {
|
|
17
|
+
"type": "integer",
|
|
18
|
+
"minimum": 1
|
|
19
|
+
}
|
|
20
|
+
}
|
|
21
|
+
}
|