@crawlee/browser 4.0.0-beta.103 → 4.0.0-beta.104
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.
|
@@ -8,7 +8,8 @@ import type { BrowserLaunchContext } from './browser-launcher.js';
|
|
|
8
8
|
interface BaseResponse {
|
|
9
9
|
status(): number;
|
|
10
10
|
}
|
|
11
|
-
export interface BrowserCrawlingContext<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, UserData extends Dictionary =
|
|
11
|
+
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
|
|
12
|
+
GoToOptions extends Dictionary = Dictionary> extends CrawlingContext<UserData> {
|
|
12
13
|
/**
|
|
13
14
|
* The browser page object where the web page is loaded and rendered.
|
|
14
15
|
*/
|
|
@@ -32,7 +33,7 @@ export interface BrowserCrawlingContext<Page extends CommonPage = CommonPage, Re
|
|
|
32
33
|
enqueueLinks: (options?: EnqueueLinksOptions) => Promise<BatchAddRequestsResult>;
|
|
33
34
|
}
|
|
34
35
|
export type BrowserHook<Context = BrowserCrawlingContext, ContextExtension = {}> = (crawlingContext: Context & ContextExtension) => Awaitable<void | Partial<Context>>;
|
|
35
|
-
export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, Context extends BrowserCrawlingContext<Page, Response
|
|
36
|
+
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, InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, Routes extends Record<keyof Routes, Dictionary> = Record<string, GetUserDataFromRequest<Context['request']>>, __BrowserPlugins extends BrowserPlugin[] = InferBrowserPluginArray<InternalBrowserPoolOptions['browserPlugins']>, __BrowserControllerReturn extends BrowserController = ReturnType<__BrowserPlugins[number]['createController']>, __LaunchContextReturn extends LaunchContext = ReturnType<__BrowserPlugins[number]['createLaunchContext']>> extends Omit<BasicCrawlerOptions<Context, ContextExtension, ExtendedContext>, 'requestHandler' | 'failedRequestHandler' | 'errorHandler'> {
|
|
36
37
|
launchContext?: BrowserLaunchContext<any, any>;
|
|
37
38
|
/**
|
|
38
39
|
* An existing browser pool instance to use. When provided, the crawler will use this pool directly instead of
|
|
@@ -225,7 +226,7 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
225
226
|
*
|
|
226
227
|
* @category Crawlers
|
|
227
228
|
*/
|
|
228
|
-
export declare abstract class BrowserCrawler<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, LaunchOptions extends Dictionary | undefined = Dictionary, Context extends BrowserCrawlingContext<Page, Response
|
|
229
|
+
export declare abstract class BrowserCrawler<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, 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']>>, GoToOptions extends Dictionary = Dictionary> extends BasicCrawler<Context, ContextExtension, ExtendedContext, Routes> {
|
|
229
230
|
/** Backs the {@link BrowserCrawler.browserPool|`browserPool`} getter. */
|
|
230
231
|
private browserPoolDep;
|
|
231
232
|
/**
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@crawlee/browser",
|
|
3
|
-
"version": "4.0.0-beta.
|
|
3
|
+
"version": "4.0.0-beta.104",
|
|
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"
|
|
@@ -48,10 +48,10 @@
|
|
|
48
48
|
},
|
|
49
49
|
"dependencies": {
|
|
50
50
|
"@apify/timeout": "^0.4.4",
|
|
51
|
-
"@crawlee/basic": "4.0.0-beta.
|
|
52
|
-
"@crawlee/browser-pool": "4.0.0-beta.
|
|
53
|
-
"@crawlee/types": "4.0.0-beta.
|
|
54
|
-
"@crawlee/utils": "4.0.0-beta.
|
|
51
|
+
"@crawlee/basic": "4.0.0-beta.104",
|
|
52
|
+
"@crawlee/browser-pool": "4.0.0-beta.104",
|
|
53
|
+
"@crawlee/types": "4.0.0-beta.104",
|
|
54
|
+
"@crawlee/utils": "4.0.0-beta.104",
|
|
55
55
|
"ow": "^2.0.0",
|
|
56
56
|
"tslib": "^2.8.1",
|
|
57
57
|
"type-fest": "^4.41.0"
|
|
@@ -75,5 +75,5 @@
|
|
|
75
75
|
}
|
|
76
76
|
}
|
|
77
77
|
},
|
|
78
|
-
"gitHead": "
|
|
78
|
+
"gitHead": "1c761e689e56ac06b67fc4f1dc091f693e024d12"
|
|
79
79
|
}
|