ag-webscrape 0.0.13 → 0.0.15
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/dist/WebScraper.d.ts.map +1 -1
- package/dist/WebScraper.js +10 -10
- package/dist/WebScraper.js.map +1 -1
- package/package.json +2 -2
package/dist/WebScraper.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"WebScraper.d.ts","sourceRoot":"","sources":["../src/WebScraper.ts"],"names":[],"mappings":"AAKA,MAAM,WAAW,eAAe;IAC9B,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACjC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB;AAED,MAAM,WAAW,cAAc;IAC7B,GAAG,EAAE,MAAM,CAAC;IACZ,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,OAAO,GAAG,QAAQ,CAAC;IAC3B,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,UAAU,CAAC,EAAE,OAAO,CAAC;IACrB,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,qBAAa,UAAU;IACrB,OAAO,CAAC,SAAS,CAAS;IAC1B,OAAO,CAAC,cAAc,CAAkB;gBAE5B,OAAO,GAAE,eAAoB;YAc3B,aAAa;
|
|
1
|
+
{"version":3,"file":"WebScraper.d.ts","sourceRoot":"","sources":["../src/WebScraper.ts"],"names":[],"mappings":"AAKA,MAAM,WAAW,eAAe;IAC9B,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACjC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB;AAED,MAAM,WAAW,cAAc;IAC7B,GAAG,EAAE,MAAM,CAAC;IACZ,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,OAAO,GAAG,QAAQ,CAAC;IAC3B,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,UAAU,CAAC,EAAE,OAAO,CAAC;IACrB,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,qBAAa,UAAU;IACrB,OAAO,CAAC,SAAS,CAAS;IAC1B,OAAO,CAAC,cAAc,CAAkB;gBAE5B,OAAO,GAAE,eAAoB;YAc3B,aAAa;YAkDb,mBAAmB;IAqE3B,MAAM,CACV,GAAG,EAAE,MAAM,EACX,OAAO,GAAE,eAAoB,GAC5B,OAAO,CAAC,cAAc,CAAC;IAsDpB,cAAc,CAClB,IAAI,EAAE,MAAM,EAAE,EACd,OAAO,GAAE,eAAoB,GAC5B,OAAO,CAAC,cAAc,EAAE,CAAC;IAwBtB,OAAO,IAAI,OAAO,CAAC,IAAI,CAAC;CAG/B"}
|
package/dist/WebScraper.js
CHANGED
|
@@ -38,6 +38,7 @@ class WebScraper {
|
|
|
38
38
|
url,
|
|
39
39
|
html,
|
|
40
40
|
status: response.status,
|
|
41
|
+
error: response.status === 200 ? undefined : response.status.toString(),
|
|
41
42
|
method: 'fetch',
|
|
42
43
|
redirected: response.redirected,
|
|
43
44
|
finalUrl: response.url,
|
|
@@ -62,9 +63,8 @@ class WebScraper {
|
|
|
62
63
|
html = pageResult.html.outerHTML;
|
|
63
64
|
status = pageResult.status;
|
|
64
65
|
finalUrl = pageResult.url;
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
}
|
|
66
|
+
error =
|
|
67
|
+
status === 200 ? undefined : `HTTP ${status}: ${pageResult.statusText}`;
|
|
68
68
|
return {
|
|
69
69
|
url,
|
|
70
70
|
html,
|
|
@@ -98,7 +98,7 @@ class WebScraper {
|
|
|
98
98
|
html: '',
|
|
99
99
|
status,
|
|
100
100
|
method: 'visual',
|
|
101
|
-
error: errorMessage,
|
|
101
|
+
error: errorMessage || 'err',
|
|
102
102
|
finalUrl,
|
|
103
103
|
};
|
|
104
104
|
}
|
|
@@ -109,23 +109,23 @@ class WebScraper {
|
|
|
109
109
|
try {
|
|
110
110
|
const result = await this.fetchDirectly(url, mergedOptions);
|
|
111
111
|
if (result.status >= 200 && result.status < 300) {
|
|
112
|
+
(0, log_1.info)('fetch: OK', url);
|
|
112
113
|
return result;
|
|
113
114
|
}
|
|
114
115
|
if (result.status === 404) {
|
|
115
|
-
(0, log_1.info)(`
|
|
116
|
+
(0, log_1.info)(`fetch:${result.status}. skip:`, url);
|
|
116
117
|
return result;
|
|
117
118
|
}
|
|
118
|
-
(0, log_1.info)(`Direct fetch failed or anti-scraping detected for ${url}. Falling back to puppeteer.`, JSON.stringify(result, null, 2));
|
|
119
119
|
}
|
|
120
120
|
catch (error) {
|
|
121
121
|
lastError =
|
|
122
122
|
error instanceof Error ? error : new Error('Unknown fetch error');
|
|
123
|
-
(0, log_1.info)(`Direct fetch failed for ${url}: ${lastError.message}. Falling back to puppeteer.`);
|
|
123
|
+
(0, log_1.info)(`Direct fetch failed or anti-scraping detected for ${url}: ${lastError.message}. Falling back to puppeteer.`);
|
|
124
124
|
}
|
|
125
125
|
try {
|
|
126
|
-
const
|
|
127
|
-
(0, log_1.debug)(`Puppeteer scrape successful for ${url}.`, JSON.stringify(
|
|
128
|
-
return
|
|
126
|
+
const resultP = await this.scrapeWithpuppeteer(url, mergedOptions);
|
|
127
|
+
(0, log_1.debug)(`Puppeteer scrape successful for ${url}.`, JSON.stringify(resultP, null, 2));
|
|
128
|
+
return resultP;
|
|
129
129
|
}
|
|
130
130
|
catch (error) {
|
|
131
131
|
const puppeteerError = error instanceof Error ? error : new Error('Unknown puppeteer error');
|
package/dist/WebScraper.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"WebScraper.js","sourceRoot":"","sources":["../src/WebScraper.ts"],"names":[],"mappings":";;;AACA,2DAAsE;AAEtE,uCAAwE;AAsBxE,MAAa,UAAU;IAIrB,YAAY,UAA2B,EAAE;QACvC,IAAI,CAAC,SAAS;YACZ,iHAAiH,CAAC;QACpH,IAAI,CAAC,cAAc,GAAG;YACpB,OAAO,EAAE,KAAK;YACd,OAAO,EAAE,CAAC;YACV,cAAc,EAAE,IAAI;YACpB,GAAG,OAAO;SACX,CAAC;IACJ,CAAC;IAKO,KAAK,CAAC,aAAa,CACzB,GAAW,EACX,OAAwB;QAExB,MAAM,OAAO,GAAG;YACd,YAAY,EAAE,OAAO,CAAC,SAAS,IAAI,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE;YAC5D,MAAM,EACJ,4EAA4E;YAC9E,iBAAiB,EAAE,gBAAgB;YACnC,iBAAiB,EAAE,eAAe;YAClC,UAAU,EAAE,YAAY;YACxB,2BAA2B,EAAE,GAAG;YAChC,GAAG,OAAO,CAAC,OAAO;SACnB,CAAC;QAEF,MAAM,UAAU,GAAG,IAAI,eAAe,EAAE,CAAC;QACzC,MAAM,SAAS,GAAG,UAAU,CAC1B,GAAG,EAAE,CAAC,UAAU,CAAC,KAAK,EAAE,EACxB,OAAO,CAAC,OAAO,IAAI,IAAI,CAAC,cAAc,CAAC,OAAQ,CAChD,CAAC;QAEF,IAAI,CAAC;YACH,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;gBAChC,OAAO;gBACP,MAAM,EAAE,UAAU,CAAC,MAAM;gBACzB,QAAQ,EAAE,QAAQ;aACnB,CAAC,CAAC;YAEH,YAAY,CAAC,SAAS,CAAC,CAAC;YAExB,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;YAEnC,OAAO;gBACL,GAAG;gBACH,IAAI;gBACJ,MAAM,EAAE,QAAQ,CAAC,MAAM;gBACvB,MAAM,EAAE,OAAO;gBACf,UAAU,EAAE,QAAQ,CAAC,UAAU;gBAC/B,QAAQ,EAAE,QAAQ,CAAC,GAAG;aACvB,CAAC;QACJ,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,YAAY,CAAC,SAAS,CAAC,CAAC;YACxB,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;IAKO,KAAK,CAAC,mBAAmB,CAC/B,GAAW,EACX,OAAwB;QAExB,IAAI,IAAI,GAAG,EAAE,CAAC;QACd,IAAI,MAAM,GAAG,GAAG,CAAC;QACjB,IAAI,KAAyB,CAAC;QAC9B,IAAI,QAAQ,GAAG,GAAG,CAAC;QAEnB,IAAI,CAAC;YAEH,MAAM,UAAU,GAAe,MAAM,IAAA,cAAQ,EAAC,GAAG,EAAE;gBACjD,OAAO,EAAE,OAAO,CAAC,OAAO,IAAI,IAAI,CAAC,cAAc,CAAC,OAAO;gBACvD,iBAAiB,EAAE,OAAO,CAAC,eAAe;gBAC1C,cAAc,EAAE,OAAO,CAAC,cAAc;aACvC,CAAC,CAAC;YAGH,IAAI,GAAG,UAAU,CAAC,IAAI,CAAC,SAAS,CAAC;YACjC,MAAM,GAAG,UAAU,CAAC,MAAM,CAAC;YAC3B,QAAQ,GAAG,UAAU,CAAC,GAAG,CAAC;
|
|
1
|
+
{"version":3,"file":"WebScraper.js","sourceRoot":"","sources":["../src/WebScraper.ts"],"names":[],"mappings":";;;AACA,2DAAsE;AAEtE,uCAAwE;AAsBxE,MAAa,UAAU;IAIrB,YAAY,UAA2B,EAAE;QACvC,IAAI,CAAC,SAAS;YACZ,iHAAiH,CAAC;QACpH,IAAI,CAAC,cAAc,GAAG;YACpB,OAAO,EAAE,KAAK;YACd,OAAO,EAAE,CAAC;YACV,cAAc,EAAE,IAAI;YACpB,GAAG,OAAO;SACX,CAAC;IACJ,CAAC;IAKO,KAAK,CAAC,aAAa,CACzB,GAAW,EACX,OAAwB;QAExB,MAAM,OAAO,GAAG;YACd,YAAY,EAAE,OAAO,CAAC,SAAS,IAAI,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE;YAC5D,MAAM,EACJ,4EAA4E;YAC9E,iBAAiB,EAAE,gBAAgB;YACnC,iBAAiB,EAAE,eAAe;YAClC,UAAU,EAAE,YAAY;YACxB,2BAA2B,EAAE,GAAG;YAChC,GAAG,OAAO,CAAC,OAAO;SACnB,CAAC;QAEF,MAAM,UAAU,GAAG,IAAI,eAAe,EAAE,CAAC;QACzC,MAAM,SAAS,GAAG,UAAU,CAC1B,GAAG,EAAE,CAAC,UAAU,CAAC,KAAK,EAAE,EACxB,OAAO,CAAC,OAAO,IAAI,IAAI,CAAC,cAAc,CAAC,OAAQ,CAChD,CAAC;QAEF,IAAI,CAAC;YACH,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;gBAChC,OAAO;gBACP,MAAM,EAAE,UAAU,CAAC,MAAM;gBACzB,QAAQ,EAAE,QAAQ;aACnB,CAAC,CAAC;YAEH,YAAY,CAAC,SAAS,CAAC,CAAC;YAExB,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;YAEnC,OAAO;gBACL,GAAG;gBACH,IAAI;gBACJ,MAAM,EAAE,QAAQ,CAAC,MAAM;gBACvB,KAAK,EAAE,QAAQ,CAAC,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,QAAQ,EAAE;gBACvE,MAAM,EAAE,OAAO;gBACf,UAAU,EAAE,QAAQ,CAAC,UAAU;gBAC/B,QAAQ,EAAE,QAAQ,CAAC,GAAG;aACvB,CAAC;QACJ,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,YAAY,CAAC,SAAS,CAAC,CAAC;YACxB,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;IAKO,KAAK,CAAC,mBAAmB,CAC/B,GAAW,EACX,OAAwB;QAExB,IAAI,IAAI,GAAG,EAAE,CAAC;QACd,IAAI,MAAM,GAAG,GAAG,CAAC;QACjB,IAAI,KAAyB,CAAC;QAC9B,IAAI,QAAQ,GAAG,GAAG,CAAC;QAEnB,IAAI,CAAC;YAEH,MAAM,UAAU,GAAe,MAAM,IAAA,cAAQ,EAAC,GAAG,EAAE;gBACjD,OAAO,EAAE,OAAO,CAAC,OAAO,IAAI,IAAI,CAAC,cAAc,CAAC,OAAO;gBACvD,iBAAiB,EAAE,OAAO,CAAC,eAAe;gBAC1C,cAAc,EAAE,OAAO,CAAC,cAAc;aACvC,CAAC,CAAC;YAGH,IAAI,GAAG,UAAU,CAAC,IAAI,CAAC,SAAS,CAAC;YACjC,MAAM,GAAG,UAAU,CAAC,MAAM,CAAC;YAC3B,QAAQ,GAAG,UAAU,CAAC,GAAG,CAAC;YAE1B,KAAK;gBACH,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,MAAM,KAAK,UAAU,CAAC,UAAU,EAAE,CAAC;YAE1E,OAAO;gBACL,GAAG;gBACH,IAAI;gBACJ,MAAM;gBACN,MAAM,EAAE,QAAQ;gBAChB,KAAK;gBACL,QAAQ;aACT,CAAC;QACJ,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,MAAM,YAAY,GAAG,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,CAAC;YAG1E,IAAI,YAAY,CAAC,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;gBACrC,MAAM,GAAG,GAAG,CAAC;YACf,CAAC;iBAAM,IACL,YAAY,CAAC,QAAQ,CAAC,KAAK,CAAC;gBAC5B,YAAY,CAAC,QAAQ,CAAC,WAAW,CAAC,EAClC,CAAC;gBACD,MAAM,GAAG,GAAG,CAAC;YACf,CAAC;iBAAM,IACL,YAAY,CAAC,QAAQ,CAAC,KAAK,CAAC;gBAC5B,YAAY,CAAC,QAAQ,CAAC,WAAW,CAAC,EAClC,CAAC;gBACD,MAAM,GAAG,GAAG,CAAC;YACf,CAAC;iBAAM,IAAI,YAAY,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;gBACxC,MAAM,GAAG,GAAG,CAAC;YACf,CAAC;iBAAM,CAAC;gBACN,MAAM,GAAG,CAAC,CAAC;YACb,CAAC;YAED,OAAO;gBACL,GAAG;gBACH,IAAI,EAAE,EAAE;gBACR,MAAM;gBACN,MAAM,EAAE,QAAQ;gBAChB,KAAK,EAAE,YAAY,IAAI,KAAK;gBAC5B,QAAQ;aACT,CAAC;QACJ,CAAC;IACH,CAAC;IAKD,KAAK,CAAC,MAAM,CACV,GAAW,EACX,UAA2B,EAAE;QAE7B,MAAM,aAAa,GAAG,EAAE,GAAG,IAAI,CAAC,cAAc,EAAE,GAAG,OAAO,EAAE,CAAC;QAC7D,IAAI,SAAS,GAAiB,IAAI,CAAC;QAGnC,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,aAAa,CAAC,GAAG,EAAE,aAAa,CAAC,CAAC;YAG5D,IAAI,MAAM,CAAC,MAAM,IAAI,GAAG,IAAI,MAAM,CAAC,MAAM,GAAG,GAAG,EAAE,CAAC;gBAChD,IAAA,UAAI,EAAC,WAAW,EAAE,GAAG,CAAC,CAAC;gBACvB,OAAO,MAAM,CAAC;YAChB,CAAC;YAGD,IAAI,MAAM,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;gBAC1B,IAAA,UAAI,EAAC,SAAS,MAAM,CAAC,MAAM,SAAS,EAAE,GAAG,CAAC,CAAC;gBAC3C,OAAO,MAAM,CAAC;YAChB,CAAC;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,SAAS;gBACP,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,qBAAqB,CAAC,CAAC;YACpE,IAAA,UAAI,EACF,qDAAqD,GAAG,KAAK,SAAS,CAAC,OAAO,8BAA8B,CAC7G,CAAC;QACJ,CAAC;QAGD,IAAI,CAAC;YACH,MAAM,OAAO,GAAG,MAAM,IAAI,CAAC,mBAAmB,CAAC,GAAG,EAAE,aAAa,CAAC,CAAC;YACnE,IAAA,WAAK,EACH,mCAAmC,GAAG,GAAG,EACzC,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CACjC,CAAC;YACF,OAAO,OAAO,CAAC;QACjB,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,MAAM,cAAc,GAClB,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,yBAAyB,CAAC,CAAC;YAExE,MAAM,CAAC,GAAG,+BAA+B,SAAS,EAAE,OAAO,IAAI,SAAS,gBAAgB,cAAc,CAAC,OAAO,SAAU,KAAe,CAAC,OAAO,EAAE,CAAC;YAClJ,IAAA,UAAI,EAAC,CAAC,CAAC,CAAC;YACR,OAAO;gBACL,GAAG;gBACH,IAAI,EAAE,EAAE;gBACR,MAAM,EAAE,CAAC;gBACT,MAAM,EAAE,QAAQ;gBAChB,KAAK,EAAE,CAAC;aACT,CAAC;QACJ,CAAC;IACH,CAAC;IAKD,KAAK,CAAC,cAAc,CAClB,IAAc,EACd,UAA2B,EAAE;QAE7B,MAAM,OAAO,GAAqB,EAAE,CAAC;QAErC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,IAAI,CAAC;gBACH,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,MAAM,CAAC,GAAG,EAAE,OAAO,CAAC,CAAC;gBAC/C,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;YACvB,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,OAAO,CAAC,IAAI,CAAC;oBACX,GAAG;oBACH,IAAI,EAAE,EAAE;oBACR,MAAM,EAAE,CAAC;oBACT,MAAM,EAAE,OAAO;oBACf,KAAK,EAAE,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe;iBAChE,CAAC,CAAC;YACL,CAAC;QACH,CAAC;QAED,OAAO,OAAO,CAAC;IACjB,CAAC;IAKD,KAAK,CAAC,OAAO;QACX,MAAM,IAAA,kBAAY,GAAE,CAAC;IACvB,CAAC;CACF;AAhOD,gCAgOC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ag-webscrape",
|
|
3
|
-
"version": "0.0.
|
|
3
|
+
"version": "0.0.15",
|
|
4
4
|
"author": "admin@gec.dev",
|
|
5
5
|
"description": "TypeScript web scraper with Playwright fallback for anti-scraping protection",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -15,7 +15,7 @@
|
|
|
15
15
|
"license": "MIT",
|
|
16
16
|
"dependencies": {
|
|
17
17
|
"@sparticuz/chromium": "^138.0.2",
|
|
18
|
-
"ag-common": "^0.0.
|
|
18
|
+
"ag-common": "^0.0.759",
|
|
19
19
|
"node-html-parser": "^7.0.1",
|
|
20
20
|
"puppeteer": "^24.15.0",
|
|
21
21
|
"puppeteer-core": "^24.15.0"
|