@crawlee/browser 4.0.0-beta.84 → 4.0.0-beta.86
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.
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
import type { Awaitable, BasicCrawlerOptions, BasicCrawlingContext, CrawlingContext, Dictionary, EnqueueLinksOptions, ErrorHandler, IRequestManager, LoadedRequest, Request, RequestHandler, SkippedRequestCallback } from '@crawlee/basic';
|
|
1
|
+
import type { Awaitable, BasicCrawlerOptions, BasicCrawlingContext, CrawlingContext, Dictionary, EnqueueLinksOptions, ErrorHandler, GetUserDataFromRequest, IRequestManager, LoadedRequest, Request, RequestHandler, RouterHandler, SkippedRequestCallback } from '@crawlee/basic';
|
|
2
2
|
import { BasicCrawler, ContextPipeline } from '@crawlee/basic';
|
|
3
3
|
import type { BrowserController, BrowserPlugin, BrowserPoolHooks, BrowserPoolOptions, CommonPage, CrawlerRemoteBrowserOptions, InferBrowserPluginArray, LaunchContext } from '@crawlee/browser-pool';
|
|
4
4
|
import type { BatchAddRequestsResult, IBrowserPool } from '@crawlee/types';
|
|
@@ -32,7 +32,7 @@ export interface BrowserCrawlingContext<Page extends CommonPage = CommonPage, Re
|
|
|
32
32
|
enqueueLinks: (options?: EnqueueLinksOptions) => Promise<BatchAddRequestsResult>;
|
|
33
33
|
}
|
|
34
34
|
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, Dictionary> = BrowserCrawlingContext<Page, Response, Dictionary>, ContextExtension = Dictionary<never>, ExtendedContext extends Context = Context & ContextExtension, InternalBrowserPoolOptions extends BrowserPoolOptions = BrowserPoolOptions, __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'> {
|
|
35
|
+
export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Response extends BaseResponse = BaseResponse, Context extends BrowserCrawlingContext<Page, Response, Dictionary> = BrowserCrawlingContext<Page, Response, Dictionary>, 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
36
|
launchContext?: BrowserLaunchContext<any, any>;
|
|
37
37
|
/**
|
|
38
38
|
* An existing browser pool instance to use. When provided, the crawler will use this pool directly instead of
|
|
@@ -78,7 +78,7 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
78
78
|
* The exceptions are logged to the request using the
|
|
79
79
|
* {@link Request.pushErrorMessage|`Request.pushErrorMessage()`} function.
|
|
80
80
|
*/
|
|
81
|
-
requestHandler?: RequestHandler<ExtendedContext>;
|
|
81
|
+
requestHandler?: RouterHandler<ExtendedContext, Routes> | RequestHandler<ExtendedContext>;
|
|
82
82
|
/**
|
|
83
83
|
* User-provided function that allows modifying the request object before it gets retried by the crawler.
|
|
84
84
|
* It's executed before each retry for the requests that failed less than {@link BrowserCrawlerOptions.maxRequestRetries|`maxRequestRetries`} times.
|
|
@@ -223,7 +223,7 @@ export interface BrowserCrawlerOptions<Page extends CommonPage = CommonPage, Res
|
|
|
223
223
|
*
|
|
224
224
|
* @category Crawlers
|
|
225
225
|
*/
|
|
226
|
-
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, Dictionary> = BrowserCrawlingContext<Page, Response, Dictionary>, ContextExtension = Dictionary<never>, ExtendedContext extends Context = Context & ContextExtension, GoToOptions extends Dictionary = Dictionary> extends BasicCrawler<Context, ContextExtension, ExtendedContext> {
|
|
226
|
+
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, Dictionary> = BrowserCrawlingContext<Page, Response, Dictionary>, 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> {
|
|
227
227
|
/** Backs the {@link BrowserCrawler.browserPool|`browserPool`} getter. */
|
|
228
228
|
private browserPoolDep;
|
|
229
229
|
/**
|
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.86",
|
|
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": "^0.3.2",
|
|
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.86",
|
|
52
|
+
"@crawlee/browser-pool": "4.0.0-beta.86",
|
|
53
|
+
"@crawlee/types": "4.0.0-beta.86",
|
|
54
|
+
"@crawlee/utils": "4.0.0-beta.86",
|
|
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": "c2f251426f3ccfcc6efc920e6d492be57beac43b"
|
|
79
79
|
}
|