@crawlee/linkedom 4.0.0-beta.77 → 4.0.0-beta.79
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.
|
@@ -1,10 +1,11 @@
|
|
|
1
|
-
import type { BasicCrawlingContext, EnqueueLinksOptions, ErrorHandler, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpCrawlingContext, InternalHttpHook, IRequestManager, RequestHandler, RouterHandler, RouterRoutes, RouteSchemas, RoutesFromSchemas, SkippedRequestCallback } from '@crawlee/http';
|
|
1
|
+
import type { BasicCrawlingContext, CrawlingContext, EnqueueLinksOptions, ErrorHandler, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpCrawlingContext, InternalHttpHook, IRequestManager, RequestHandler, RouterHandler, RouterRoutes, RouteSchemas, RoutesFromSchemas, SkippedRequestCallback } from '@crawlee/http';
|
|
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
5
|
import * as cheerio from 'cheerio';
|
|
6
6
|
export type LinkeDOMErrorHandler<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
|
|
7
|
-
JSONData extends Dictionary = any
|
|
7
|
+
JSONData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
|
|
8
|
+
ContextExtension = Dictionary<never>> = ErrorHandler<CrawlingContext, LinkeDOMCrawlingContext<UserData, JSONData> & ContextExtension>;
|
|
8
9
|
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
|
|
9
10
|
JSONData extends Dictionary = any> extends HttpCrawlerOptions<LinkeDOMCrawlingContext<UserData, JSONData>, ContextExtension, ExtendedContext> {
|
|
10
11
|
}
|
|
@@ -122,7 +123,7 @@ export declare class LinkeDOMCrawler<ContextExtension = Dictionary<never>, Exten
|
|
|
122
123
|
private static parser;
|
|
123
124
|
constructor(options: LinkeDOMCrawlerOptions<ContextExtension, ExtendedContext>);
|
|
124
125
|
// @ts-ignore optional peer dependency or compatibility with es2022
|
|
125
|
-
protected buildContextPipeline(): import("@crawlee/http").ContextPipeline<
|
|
126
|
+
protected buildContextPipeline(): import("@crawlee/http").ContextPipeline<CrawlingContext<Dictionary>, InternalHttpCrawlingContext<any, any> & {
|
|
126
127
|
readonly window: Window;
|
|
127
128
|
readonly body: string;
|
|
128
129
|
readonly document: Document;
|
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.79",
|
|
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"
|
|
@@ -49,9 +49,9 @@
|
|
|
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.
|
|
54
|
-
"@crawlee/utils": "4.0.0-beta.
|
|
52
|
+
"@crawlee/http": "4.0.0-beta.79",
|
|
53
|
+
"@crawlee/types": "4.0.0-beta.79",
|
|
54
|
+
"@crawlee/utils": "4.0.0-beta.79",
|
|
55
55
|
"cheerio": "^1.0.0",
|
|
56
56
|
"linkedom": "^0.18.10",
|
|
57
57
|
"ow": "^2.0.0",
|
|
@@ -64,5 +64,5 @@
|
|
|
64
64
|
}
|
|
65
65
|
}
|
|
66
66
|
},
|
|
67
|
-
"gitHead": "
|
|
67
|
+
"gitHead": "e897f0881c8142a1fd32f315263751296b4f1a22"
|
|
68
68
|
}
|