@crawlee/linkedom 3.15.4-beta.38 → 3.15.4-beta.39
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.
|
@@ -85,8 +85,8 @@ JSONData extends Dictionary = any> = RequestHandler<LinkeDOMCrawlingContext<User
|
|
|
85
85
|
* ]
|
|
86
86
|
* ```
|
|
87
87
|
*
|
|
88
|
-
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`
|
|
89
|
-
* 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),
|
|
90
90
|
* and skips pages with other content types. If you want the crawler to process other content types,
|
|
91
91
|
* use the {@link LinkeDOMCrawlerOptions.additionalMimeTypes} constructor option.
|
|
92
92
|
* Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
|
|
@@ -49,8 +49,8 @@ const utilities_1 = require("@apify/utilities");
|
|
|
49
49
|
* ]
|
|
50
50
|
* ```
|
|
51
51
|
*
|
|
52
|
-
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`
|
|
53
|
-
* and `application/
|
|
52
|
+
* By default, `LinkeDOMCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
|
|
53
|
+
* and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
|
|
54
54
|
* and skips pages with other content types. If you want the crawler to process other content types,
|
|
55
55
|
* use the {@link LinkeDOMCrawlerOptions.additionalMimeTypes} constructor option.
|
|
56
56
|
* Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@crawlee/linkedom",
|
|
3
|
-
"version": "3.15.4-beta.
|
|
3
|
+
"version": "3.15.4-beta.39",
|
|
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": ">=16.0.0"
|
|
@@ -55,8 +55,8 @@
|
|
|
55
55
|
"dependencies": {
|
|
56
56
|
"@apify/timeout": "^0.3.0",
|
|
57
57
|
"@apify/utilities": "^2.7.10",
|
|
58
|
-
"@crawlee/http": "3.15.4-beta.
|
|
59
|
-
"@crawlee/types": "3.15.4-beta.
|
|
58
|
+
"@crawlee/http": "3.15.4-beta.39",
|
|
59
|
+
"@crawlee/types": "3.15.4-beta.39",
|
|
60
60
|
"linkedom": "^0.18.0",
|
|
61
61
|
"ow": "^0.28.2",
|
|
62
62
|
"tslib": "^2.4.0"
|
|
@@ -68,5 +68,5 @@
|
|
|
68
68
|
}
|
|
69
69
|
}
|
|
70
70
|
},
|
|
71
|
-
"gitHead": "
|
|
71
|
+
"gitHead": "2ea2b0447f3b3334e5ade805cd7aec4be1991c3c"
|
|
72
72
|
}
|