@crawlee/playwright 4.0.0-beta.149 → 4.0.0-beta.150
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.
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { URL } from 'node:url';
|
|
2
|
-
import { applyRequestTransform, constructUrlPatternObjects, createRequestOptions, filterRequestOptionsByPatterns, urlPatternSchema, Request as CrawleeRequest, serviceLocator, } from '@crawlee/browser';
|
|
2
|
+
import { applyRequestTransform, constructUrlPatternObjects, createRequestOptions, createSkippedRequestArgs, filterRequestOptionsByPatterns, urlPatternSchema, Request as CrawleeRequest, serviceLocator, } from '@crawlee/browser';
|
|
3
3
|
import { parseArgument, schemas } from '@crawlee/utils/internal';
|
|
4
4
|
import { z } from 'zod';
|
|
5
5
|
const STARTING_Z_INDEX = 2147400000;
|
|
@@ -65,6 +65,7 @@ export async function enqueueLinksByClickingElements(options) {
|
|
|
65
65
|
const { page, requestManager, selector, clickOptions, include, exclude, transformRequestFunction, waitForPageIdleSecs, maxWaitForPageIdleSecs, forefront, onSkippedRequest, } = parsedOptions;
|
|
66
66
|
const waitForPageIdleMillis = waitForPageIdleSecs * 1000;
|
|
67
67
|
const maxWaitForPageIdleMillis = maxWaitForPageIdleSecs * 1000;
|
|
68
|
+
const hasOnSkippedRequest = onSkippedRequest !== undefined;
|
|
68
69
|
const urlExcludePatternObjects = exclude?.length ? constructUrlPatternObjects(exclude) : [];
|
|
69
70
|
const urlPatternObjects = include?.length ? constructUrlPatternObjects(include) : [];
|
|
70
71
|
const interceptedRequests = await clickElementsAndInterceptNavigationRequests({
|
|
@@ -76,15 +77,15 @@ export async function enqueueLinksByClickingElements(options) {
|
|
|
76
77
|
});
|
|
77
78
|
const requestOptions = createRequestOptions(interceptedRequests, parsedOptions);
|
|
78
79
|
const skippedByFilters = [];
|
|
79
|
-
let filteredOptions = filterRequestOptionsByPatterns(requestOptions, urlPatternObjects.length > 0 ? urlPatternObjects : undefined, urlExcludePatternObjects, undefined, (
|
|
80
|
+
let filteredOptions = filterRequestOptionsByPatterns(requestOptions, urlPatternObjects.length > 0 ? urlPatternObjects : undefined, urlExcludePatternObjects, undefined, hasOnSkippedRequest ? (opts) => skippedByFilters.push(opts) : undefined);
|
|
80
81
|
if (onSkippedRequest && skippedByFilters.length > 0) {
|
|
81
|
-
await Promise.all(skippedByFilters.map(async (
|
|
82
|
+
await Promise.all(skippedByFilters.map(async (opts) => onSkippedRequest(createSkippedRequestArgs(opts, 'filters'))));
|
|
82
83
|
}
|
|
83
84
|
if (transformRequestFunction) {
|
|
84
85
|
const skippedByTransform = [];
|
|
85
|
-
filteredOptions = applyRequestTransform(filteredOptions, transformRequestFunction, (r) => skippedByTransform.push(r));
|
|
86
|
+
filteredOptions = applyRequestTransform(filteredOptions, transformRequestFunction, hasOnSkippedRequest ? (r) => skippedByTransform.push(r) : undefined);
|
|
86
87
|
if (onSkippedRequest && skippedByTransform.length > 0) {
|
|
87
|
-
await Promise.all(skippedByTransform.map(async (r) => onSkippedRequest(
|
|
88
|
+
await Promise.all(skippedByTransform.map(async (r) => onSkippedRequest(createSkippedRequestArgs(r, 'transform'))));
|
|
88
89
|
}
|
|
89
90
|
}
|
|
90
91
|
const requests = filteredOptions.map((opts) => new CrawleeRequest(opts));
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@crawlee/playwright",
|
|
3
|
-
"version": "4.0.0-beta.
|
|
3
|
+
"version": "4.0.0-beta.150",
|
|
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"
|
|
@@ -49,13 +49,13 @@
|
|
|
49
49
|
"dependencies": {
|
|
50
50
|
"@apify/datastructures": "^2.0.3",
|
|
51
51
|
"@apify/timeout": "^0.4.4",
|
|
52
|
-
"@crawlee/basic": "4.0.0-beta.
|
|
53
|
-
"@crawlee/browser": "4.0.0-beta.
|
|
54
|
-
"@crawlee/browser-pool": "4.0.0-beta.
|
|
55
|
-
"@crawlee/cheerio": "4.0.0-beta.
|
|
56
|
-
"@crawlee/core": "4.0.0-beta.
|
|
57
|
-
"@crawlee/types": "4.0.0-beta.
|
|
58
|
-
"@crawlee/utils": "4.0.0-beta.
|
|
52
|
+
"@crawlee/basic": "4.0.0-beta.150",
|
|
53
|
+
"@crawlee/browser": "4.0.0-beta.150",
|
|
54
|
+
"@crawlee/browser-pool": "4.0.0-beta.150",
|
|
55
|
+
"@crawlee/cheerio": "4.0.0-beta.150",
|
|
56
|
+
"@crawlee/core": "4.0.0-beta.150",
|
|
57
|
+
"@crawlee/types": "4.0.0-beta.150",
|
|
58
|
+
"@crawlee/utils": "4.0.0-beta.150",
|
|
59
59
|
"cheerio": "^1.0.0",
|
|
60
60
|
"jquery": "^3.7.1",
|
|
61
61
|
"ml-logistic-regression": "^2.0.0",
|
|
@@ -80,5 +80,5 @@
|
|
|
80
80
|
}
|
|
81
81
|
}
|
|
82
82
|
},
|
|
83
|
-
"gitHead": "
|
|
83
|
+
"gitHead": "ef7e9fb2e2fcaa0f74e60a30fa8ae61c60c64626"
|
|
84
84
|
}
|