@crawlee/linkedom 3.15.4-beta.8 → 3.16.0

package/README.md

@@ -89,7 +89,7 @@ By default, Crawlee stores data to `./storage` in the current working directory.
 We provide automated beta builds for every merged code change in Crawlee. You can find them in the npm [list of releases](https://www.npmjs.com/package/crawlee?activeTab=versions). If you want to test new features or bug fixes before we release them, feel free to install a beta build like this:
 
 ```bash
-npm install crawlee@3.12.3-beta.13
+npm install crawlee@next
 ```
 
 If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need to specify dependency overrides in your `package.json` file so that you don't end up with multiple versions of Crawlee installed:
@@ -98,9 +98,9 @@ If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need
 {
     "overrides": {
        "apify": {
-           "@crawlee/core": "3.12.3-beta.13",
-           "@crawlee/types": "3.12.3-beta.13",
-           "@crawlee/utils": "3.12.3-beta.13"
+           "@crawlee/core": "$crawlee",
+           "@crawlee/types": "$crawlee",
+           "@crawlee/utils": "$crawlee"
        }
     }
 }

package/internals/linkedom-crawler.d.ts

@@ -85,8 +85,8 @@ JSONData extends Dictionary = any> = RequestHandler<LinkeDOMCrawlingContext<User
  * ]
  * ```
  *
- * By default, `LinkeDOMCrawler` only processes web pages with the `text/html`
- * and `application/xhtml+xml` MIME content types (as reported by the `Content-Type` HTTP header),
+ * By default, `LinkeDOMCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
+ * and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
  * and skips pages with other content types. If you want the crawler to process other content types,
  * use the {@link LinkeDOMCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.

package/internals/linkedom-crawler.js

@@ -49,8 +49,8 @@ const utilities_1 = require("@apify/utilities");
  * ]
  * ```
  *
- * By default, `LinkeDOMCrawler` only processes web pages with the `text/html`
- * and `application/xhtml+xml` MIME content types (as reported by the `Content-Type` HTTP header),
+ * By default, `LinkeDOMCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
+ * and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
  * and skips pages with other content types. If you want the crawler to process other content types,
  * use the {@link LinkeDOMCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/linkedom",
-    "version": "3.15.4-beta.8",
+    "version": "3.16.0",
     "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.",
     "engines": {
         "node": ">=16.0.0"
@@ -55,8 +55,8 @@
     "dependencies": {
         "@apify/timeout": "^0.3.0",
         "@apify/utilities": "^2.7.10",
-        "@crawlee/http": "3.15.4-beta.8",
-        "@crawlee/types": "3.15.4-beta.8",
+        "@crawlee/http": "3.16.0",
+        "@crawlee/types": "3.16.0",
         "linkedom": "^0.18.0",
         "ow": "^0.28.2",
         "tslib": "^2.4.0"
@@ -68,5 +68,5 @@
             }
         }
     },
-    "gitHead": "e5a61207a0be4c77e1f198984104ddb7a2cff583"
+    "gitHead": "e6451749f838744d539c81bf9d969c1cfcc9e86b"
 }