@crawlee/linkedom 4.0.0-beta.31 → 4.0.0-beta.33
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
CHANGED
|
@@ -89,7 +89,7 @@ By default, Crawlee stores data to `./storage` in the current working directory.
|
|
|
89
89
|
We provide automated beta builds for every merged code change in Crawlee. You can find them in the npm [list of releases](https://www.npmjs.com/package/crawlee?activeTab=versions). If you want to test new features or bug fixes before we release them, feel free to install a beta build like this:
|
|
90
90
|
|
|
91
91
|
```bash
|
|
92
|
-
npm install crawlee@
|
|
92
|
+
npm install crawlee@next
|
|
93
93
|
```
|
|
94
94
|
|
|
95
95
|
If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need to specify dependency overrides in your `package.json` file so that you don't end up with multiple versions of Crawlee installed:
|
|
@@ -98,9 +98,9 @@ If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need
|
|
|
98
98
|
{
|
|
99
99
|
"overrides": {
|
|
100
100
|
"apify": {
|
|
101
|
-
"@crawlee/core": "
|
|
102
|
-
"@crawlee/types": "
|
|
103
|
-
"@crawlee/utils": "
|
|
101
|
+
"@crawlee/core": "$crawlee",
|
|
102
|
+
"@crawlee/types": "$crawlee",
|
|
103
|
+
"@crawlee/utils": "$crawlee"
|
|
104
104
|
}
|
|
105
105
|
}
|
|
106
106
|
}
|
|
@@ -2,6 +2,7 @@ import type { BasicCrawlingContext, EnqueueLinksOptions, ErrorHandler, GetUserDa
|
|
|
2
2
|
import { HttpCrawler } from '@crawlee/http';
|
|
3
3
|
import type { Dictionary } from '@crawlee/types';
|
|
4
4
|
import { type CheerioRoot, type RobotsTxtFile } from '@crawlee/utils';
|
|
5
|
+
import * as cheerio from 'cheerio';
|
|
5
6
|
export type LinkeDOMErrorHandler<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
|
|
6
7
|
JSONData extends Dictionary = any> = ErrorHandler<LinkeDOMCrawlingContext<UserData, JSONData>>;
|
|
7
8
|
export interface LinkeDOMCrawlerOptions<ContextExtension = Dictionary<never>, ExtendedContext extends LinkeDOMCrawlingContext = LinkeDOMCrawlingContext & ContextExtension, UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
|
|
@@ -84,8 +85,8 @@ JSONData extends Dictionary = any> = RequestHandler<LinkeDOMCrawlingContext<User
|
|
|
84
85
|
* ]
|
|
85
86
|
* ```
|
|
86
87
|
*
|
|
87
|
-
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`
|
|
88
|
-
* and `application/
|
|
88
|
+
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
|
|
89
|
+
* and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
|
|
89
90
|
* and skips pages with other content types. If you want the crawler to process other content types,
|
|
90
91
|
* use the {@link LinkeDOMCrawlerOptions.additionalMimeTypes} constructor option.
|
|
91
92
|
* Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
|
|
@@ -118,6 +119,16 @@ JSONData extends Dictionary = any> = RequestHandler<LinkeDOMCrawlingContext<User
|
|
|
118
119
|
export declare class LinkeDOMCrawler<ContextExtension = Dictionary<never>, ExtendedContext extends LinkeDOMCrawlingContext = LinkeDOMCrawlingContext & ContextExtension> extends HttpCrawler<LinkeDOMCrawlingContext, ContextExtension, ExtendedContext> {
|
|
119
120
|
private static parser;
|
|
120
121
|
constructor(options: LinkeDOMCrawlerOptions<ContextExtension, ExtendedContext>);
|
|
122
|
+
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
123
|
+
protected buildContextPipeline(): import("@crawlee/http").ContextPipeline<import("@crawlee/http").CrawlingContext<Dictionary>, InternalHttpCrawlingContext<any, any> & {
|
|
124
|
+
window: Window & typeof globalThis;
|
|
125
|
+
readonly body: string;
|
|
126
|
+
readonly document: Document;
|
|
127
|
+
} & {
|
|
128
|
+
enqueueLinks: (enqueueOptions?: LinkeDOMCrawlerEnqueueLinksOptions) => Promise<unknown>;
|
|
129
|
+
waitForSelector(selector: string, timeoutMs?: number): Promise<void>;
|
|
130
|
+
parseWithCheerio(selector?: string, _timeoutMs?: number): Promise<cheerio.CheerioAPI>;
|
|
131
|
+
}>;
|
|
121
132
|
private parseContent;
|
|
122
133
|
private addHelpers;
|
|
123
134
|
}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"linkedom-crawler.d.ts","sourceRoot":"","sources":["../../src/internals/linkedom-crawler.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACR,oBAAoB,EACpB,mBAAmB,EACnB,YAAY,EACZ,sBAAsB,EACtB,kBAAkB,EAClB,2BAA2B,EAC3B,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,YAAY,EACZ,sBAAsB,EACzB,MAAM,eAAe,CAAC;AACvB,OAAO,EAEH,WAAW,EAId,MAAM,eAAe,CAAC;AACvB,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AACjD,OAAO,EAAE,KAAK,WAAW,EAAE,KAAK,aAAa,EAAS,MAAM,gBAAgB,CAAC;
|
|
1
|
+
{"version":3,"file":"linkedom-crawler.d.ts","sourceRoot":"","sources":["../../src/internals/linkedom-crawler.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACR,oBAAoB,EACpB,mBAAmB,EACnB,YAAY,EACZ,sBAAsB,EACtB,kBAAkB,EAClB,2BAA2B,EAC3B,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,YAAY,EACZ,sBAAsB,EACzB,MAAM,eAAe,CAAC;AACvB,OAAO,EAEH,WAAW,EAId,MAAM,eAAe,CAAC;AACvB,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AACjD,OAAO,EAAE,KAAK,WAAW,EAAE,KAAK,aAAa,EAAS,MAAM,gBAAgB,CAAC;AAC7E,OAAO,KAAK,OAAO,MAAM,SAAS,CAAC;AAGnC,MAAM,MAAM,oBAAoB,CAC5B,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,IACjC,YAAY,CAAC,uBAAuB,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAC;AAE9D,MAAM,WAAW,sBAAsB,CACnC,gBAAgB,GAAG,UAAU,CAAC,KAAK,CAAC,EACpC,eAAe,SAAS,uBAAuB,GAAG,uBAAuB,GAAG,gBAAgB,EAC5F,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,CACnC,SAAQ,kBAAkB,CAAC,uBAAuB,CAAC,QAAQ,EAAE,QAAQ,CAAC,EAAE,gBAAgB,EAAE,eAAe,CAAC;CAAG;AAE/G,MAAM,WAAW,kCAAmC,SAAQ,IAAI,CAAC,mBAAmB,EAAE,MAAM,GAAG,cAAc,CAAC;CAAG;AAEjH,MAAM,MAAM,YAAY,CACpB,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,IACjC,gBAAgB,CAAC,uBAAuB,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAC;AAElE,MAAM,WAAW,uBAAuB,CACpC,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,CACnC,SAAQ,2BAA2B,CAAC,QAAQ,EAAE,QAAQ,CAAC;IACrD,MAAM,EAAE,MAAM,CAAC;IAMf,QAAQ,EAAE,QAAQ,CAAC;IAEnB;;;;;;;;;;;;OAYG;IACH,eAAe,CAAC,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAErE;;;;;;;;;;;OAWG;IACH,gBAAgB,CAAC,QAAQ,CAAC,EAAE,MAAM,EAAE,SAAS,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,CAAC,CAAC;CACjF;AAED,MAAM,MAAM,sBAAsB,CAC9B,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,IACjC,cAAc,CAAC,uBAAuB,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAC;AAEhE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqEG;AAEH,qBAAa,eAAe,CACxB,gBAAgB,GAAG,UAAU,CAAC,KAAK,CAAC,EACpC,eAAe,SAAS,uBAAuB,GAAG,uBAAuB,GAAG,gBAAgB,CAC9F,SAAQ,WAAW,CAAC,uBAAuB,EAAE,gBAAgB,EAAE,eAAe,CAAC;IAC7E,OAAO,CAAC,MAAM,CAAC,MAAM,CAAmB;gBAE5B,OAAO,EAAE,sBAAsB,CAAC,gBAAgB,EAAE,eAAe,CAAC;cAS3D,oBAAoB;;;2BAuBG,QAAQ;;wCAOJ,kCAAkC;kCAWxC,MAAM;oCAaJ,MAAM;;YA7ClC,YAAY;YAmBZ,UAAU;CAqC3B;AAED,UAAU,2BAA2B;IACjC,OAAO,CAAC,EAAE,mBAAmB,CAAC;IAC9B,MAAM,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,YAAY,EAAE,eAAe,CAAC;IAC9B,aAAa,CAAC,EAAE,aAAa,CAAC;IAC9B,gBAAgB,CAAC,EAAE,sBAAsB,CAAC;IAC1C,kBAAkB,EAAE,MAAM,CAAC;IAC3B,eAAe,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED,UAAU,gCAAgC;IACtC,YAAY,EAAE,oBAAoB,CAAC,cAAc,CAAC,CAAC;IACnD,OAAO,CAAC,EAAE,mBAAmB,CAAC;IAC9B,MAAM,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,kBAAkB,EAAE,MAAM,CAAC;IAC3B,eAAe,CAAC,EAAE,MAAM,CAAC;CAC5B;AASD,gBAAgB;AAChB,wBAAsB,2BAA2B,CAC7C,OAAO,EAAE,2BAA2B,GAAG,gCAAgC,oBAqC1E;AAmBD;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AACH,wBAAgB,oBAAoB,CAChC,OAAO,SAAS,uBAAuB,GAAG,uBAAuB,EACjE,QAAQ,SAAS,UAAU,GAAG,sBAAsB,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,EAC1E,MAAM,CAAC,EAAE,YAAY,CAAC,OAAO,EAAE,QAAQ,CAAC,kDAEzC"}
|
|
@@ -41,8 +41,8 @@ import { DOMParser } from 'linkedom/cached';
|
|
|
41
41
|
* ]
|
|
42
42
|
* ```
|
|
43
43
|
*
|
|
44
|
-
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`
|
|
45
|
-
* and `application/
|
|
44
|
+
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
|
|
45
|
+
* and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
|
|
46
46
|
* and skips pages with other content types. If you want the crawler to process other content types,
|
|
47
47
|
* use the {@link LinkeDOMCrawlerOptions.additionalMimeTypes} constructor option.
|
|
48
48
|
* Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
|
|
@@ -75,15 +75,20 @@ import { DOMParser } from 'linkedom/cached';
|
|
|
75
75
|
export class LinkeDOMCrawler extends HttpCrawler {
|
|
76
76
|
static parser = new DOMParser();
|
|
77
77
|
constructor(options) {
|
|
78
|
+
const { contextPipelineBuilder, ...rest } = options;
|
|
78
79
|
super({
|
|
79
|
-
...
|
|
80
|
-
contextPipelineBuilder: () => this.buildContextPipeline()
|
|
81
|
-
.compose({
|
|
82
|
-
action: async (context) => this.parseContent(context),
|
|
83
|
-
})
|
|
84
|
-
.compose({ action: async (context) => this.addHelpers(context) }),
|
|
80
|
+
...rest,
|
|
81
|
+
contextPipelineBuilder: contextPipelineBuilder ?? (() => this.buildContextPipeline()),
|
|
85
82
|
});
|
|
86
83
|
}
|
|
84
|
+
buildContextPipeline() {
|
|
85
|
+
return super
|
|
86
|
+
.buildContextPipeline()
|
|
87
|
+
.compose({
|
|
88
|
+
action: async (context) => this.parseContent(context),
|
|
89
|
+
})
|
|
90
|
+
.compose({ action: async (context) => this.addHelpers(context) });
|
|
91
|
+
}
|
|
87
92
|
async parseContent(crawlingContext) {
|
|
88
93
|
const isXml = crawlingContext.contentType.type.includes('xml');
|
|
89
94
|
const document = LinkeDOMCrawler.parser.parseFromString(crawlingContext.body.toString(), isXml ? 'text/xml' : 'text/html');
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"linkedom-crawler.js","sourceRoot":"","sources":["../../src/internals/linkedom-crawler.ts"],"names":[],"mappings":"AAaA,OAAO,EACH,YAAY,EACZ,WAAW,EACX,sCAAsC,EACtC,MAAM,EACN,cAAc,GACjB,MAAM,eAAe,CAAC;AAEvB,OAAO,EAAwC,KAAK,EAAE,MAAM,gBAAgB,CAAC;AAC7E,OAAO,KAAK,OAAO,MAAM,SAAS,CAAC;AACnC,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAoE5C;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqEG;AAEH,MAAM,OAAO,eAGX,SAAQ,WAAuE;IACrE,MAAM,CAAC,MAAM,GAAG,IAAI,SAAS,EAAE,CAAC;IAExC,YAAY,OAAkE;QAC1E,KAAK,CAAC;YACF,GAAG,
|
|
1
|
+
{"version":3,"file":"linkedom-crawler.js","sourceRoot":"","sources":["../../src/internals/linkedom-crawler.ts"],"names":[],"mappings":"AAaA,OAAO,EACH,YAAY,EACZ,WAAW,EACX,sCAAsC,EACtC,MAAM,EACN,cAAc,GACjB,MAAM,eAAe,CAAC;AAEvB,OAAO,EAAwC,KAAK,EAAE,MAAM,gBAAgB,CAAC;AAC7E,OAAO,KAAK,OAAO,MAAM,SAAS,CAAC;AACnC,OAAO,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AAoE5C;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqEG;AAEH,MAAM,OAAO,eAGX,SAAQ,WAAuE;IACrE,MAAM,CAAC,MAAM,GAAG,IAAI,SAAS,EAAE,CAAC;IAExC,YAAY,OAAkE;QAC1E,MAAM,EAAE,sBAAsB,EAAE,GAAG,IAAI,EAAE,GAAG,OAAO,CAAC;QAEpD,KAAK,CAAC;YACF,GAAG,IAAI;YACP,sBAAsB,EAAE,sBAAsB,IAAI,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC,oBAAoB,EAAE,CAAC;SACxF,CAAC,CAAC;IACP,CAAC;IAEkB,oBAAoB;QACnC,OAAO,KAAK;aACP,oBAAoB,EAAE;aACtB,OAAO,CAAC;YACL,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,IAAI,CAAC,YAAY,CAAC,OAAO,CAAC;SACxD,CAAC;aACD,OAAO,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;IAC1E,CAAC;IAEO,KAAK,CAAC,YAAY,CAAC,eAA4C;QACnE,MAAM,KAAK,GAAG,eAAe,CAAC,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;QAC/D,MAAM,QAAQ,GAAG,eAAe,CAAC,MAAM,CAAC,eAAe,CACnD,eAAe,CAAC,IAAI,CAAC,QAAQ,EAAE,EAC/B,KAAK,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,WAAW,CACnC,CAAC;QAEF,OAAO;YACH,MAAM,EAAE,QAAQ,CAAC,WAAW;YAC5B,IAAI,IAAI;gBACJ,OAAO,QAAQ,CAAC,eAAe,CAAC,SAAS,CAAC;YAC9C,CAAC;YACD,IAAI,QAAQ;gBACR,iEAAiE;gBACjE,OAAO,QAA+B,CAAC;YAC3C,CAAC;SACJ,CAAC;IACN,CAAC;IAEO,KAAK,CAAC,UAAU,CAAC,eAA+D;QACpF,OAAO;YACH,YAAY,EAAE,KAAK,EAAE,cAAmD,EAAE,EAAE;gBACxE,OAAO,2BAA2B,CAAC;oBAC/B,OAAO,EAAE,EAAE,GAAG,cAAc,EAAE,KAAK,EAAE,IAAI,CAAC,6BAA6B,CAAC,cAAc,EAAE,KAAK,CAAC,EAAE;oBAChG,MAAM,EAAE,QAAQ,CAAC,WAAW;oBAC5B,YAAY,EAAE,MAAM,IAAI,CAAC,eAAe,EAAE;oBAC1C,aAAa,EAAE,MAAM,IAAI,CAAC,sBAAsB,CAAC,eAAe,CAAC,OAAO,CAAC,GAAG,CAAC;oBAC7E,gBAAgB,EAAE,IAAI,CAAC,oBAAoB;oBAC3C,kBAAkB,EAAE,eAAe,CAAC,OAAO,CAAC,GAAG;oBAC/C,eAAe,EAAE,eAAe,CAAC,OAAO,CAAC,SAAS;iBACrD,CAAC,CAAC;YACP,CAAC;YACD,KAAK,CAAC,eAAe,CAAC,QAAgB,EAAE,SAAS,GAAG,KAAK;gBACrD,MAAM,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC;gBAE7C,IAAI,CAAC,CAAC,QAAQ,CAAC,CAAC,GAAG,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBACjC,IAAI,SAAS,EAAE,CAAC;wBACZ,MAAM,KAAK,CAAC,EAAE,CAAC,CAAC;wBAChB,MAAM,IAAI,CAAC,eAAe,CAAC,QAAQ,EAAE,IAAI,CAAC,GAAG,CAAC,SAAS,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;wBAClE,OAAO;oBACX,CAAC;oBAED,MAAM,IAAI,KAAK,CAAC,aAAa,QAAQ,cAAc,CAAC,CAAC;gBACzD,CAAC;YACL,CAAC;YACD,KAAK,CAAC,gBAAgB,CAAC,QAAiB,EAAE,UAAU,GAAG,KAAK;gBACxD,MAAM,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC;gBAE7C,IAAI,QAAQ,IAAI,CAAC,CAAC,QAAQ,CAAC,CAAC,GAAG,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBAC7C,MAAM,IAAI,KAAK,CAAC,aAAa,QAAQ,cAAc,CAAC,CAAC;gBACzD,CAAC;gBAED,OAAO,CAAC,CAAC;YACb,CAAC;SACJ,CAAC;IACN,CAAC;;AAqBL,gBAAgB;AAChB,SAAS,oBAAoB,CACzB,OAAuE;IAEvE,OAAO,CAAC,CAAE,OAA4C,CAAC,YAAY,CAAC;AACxE,CAAC;AAED,gBAAgB;AAChB,MAAM,CAAC,KAAK,UAAU,2BAA2B,CAC7C,OAAuE;IAEvE,MAAM,EAAE,OAAO,EAAE,mBAAmB,EAAE,MAAM,EAAE,kBAAkB,EAAE,eAAe,EAAE,GAAG,OAAO,CAAC;IAE9F,IAAI,CAAC,MAAM,EAAE,CAAC;QACV,MAAM,IAAI,KAAK,CAAC,wDAAwD,CAAC,CAAC;IAC9E,CAAC;IAED,MAAM,OAAO,GAAG,sCAAsC,CAAC;QACnD,eAAe,EAAE,mBAAmB,EAAE,QAAQ;QAC9C,eAAe;QACf,kBAAkB;QAClB,mBAAmB,EAAE,mBAAmB,EAAE,OAAO;KACpD,CAAC,CAAC;IAEH,MAAM,IAAI,GAAG,qBAAqB,CAC9B,MAAM,EACN,mBAAmB,EAAE,QAAQ,IAAI,GAAG,EACpC,mBAAmB,EAAE,OAAO,IAAI,eAAe,IAAI,kBAAkB,CACxE,CAAC;IAEF,IAAI,oBAAoB,CAAC,OAAO,CAAC,EAAE,CAAC;QAChC,OAAO,OAAO,CAAC,YAAY,CAAC;YACxB,IAAI;YACJ,OAAO;YACP,GAAG,mBAAmB;SACzB,CAAC,CAAC;IACP,CAAC;IAED,OAAO,YAAY,CAAC;QAChB,YAAY,EAAE,OAAO,CAAC,YAAY;QAClC,aAAa,EAAE,OAAO,CAAC,aAAa;QACpC,gBAAgB,EAAE,OAAO,CAAC,gBAAgB;QAC1C,IAAI;QACJ,OAAO;QACP,GAAG,mBAAmB;KACzB,CAAC,CAAC;AACP,CAAC;AAED;;;GAGG;AACH,SAAS,qBAAqB,CAAC,MAAc,EAAE,QAAgB,EAAE,OAAe;IAC5E,OAAO,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAC;SACxD,GAAG,CAAC,CAAC,CAAM,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC;SACvB,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,KAAK,SAAS,IAAI,IAAI,KAAK,EAAE,CAAC;SACnD,GAAG,CAAC,CAAC,IAAwB,EAAE,EAAE;QAC9B,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACrB,OAAO,SAAS,CAAC;QACrB,CAAC;QACD,OAAO,cAAc,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC;IACzC,CAAC,CAAC;SACD,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,KAAK,SAAS,IAAI,IAAI,KAAK,EAAE,CAAa,CAAC;AACzE,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AACH,MAAM,UAAU,oBAAoB,CAGlC,MAAwC;IACtC,OAAO,MAAM,CAAC,MAAM,CAAU,MAAM,CAAC,CAAC;AAC1C,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@crawlee/linkedom",
|
|
3
|
-
"version": "4.0.0-beta.
|
|
3
|
+
"version": "4.0.0-beta.33",
|
|
4
4
|
"description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.",
|
|
5
5
|
"engines": {
|
|
6
6
|
"node": ">=22.0.0"
|
|
@@ -49,8 +49,8 @@
|
|
|
49
49
|
"dependencies": {
|
|
50
50
|
"@apify/timeout": "^0.3.2",
|
|
51
51
|
"@apify/utilities": "^2.15.5",
|
|
52
|
-
"@crawlee/http": "4.0.0-beta.
|
|
53
|
-
"@crawlee/types": "4.0.0-beta.
|
|
52
|
+
"@crawlee/http": "4.0.0-beta.33",
|
|
53
|
+
"@crawlee/types": "4.0.0-beta.33",
|
|
54
54
|
"linkedom": "^0.18.10",
|
|
55
55
|
"ow": "^2.0.0",
|
|
56
56
|
"tslib": "^2.8.1"
|
|
@@ -62,5 +62,5 @@
|
|
|
62
62
|
}
|
|
63
63
|
}
|
|
64
64
|
},
|
|
65
|
-
"gitHead": "
|
|
65
|
+
"gitHead": "8e8453c225c328d5fda0db45a8d818c3cb3a5fb6"
|
|
66
66
|
}
|