]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/fox9.py
Import Upstream version 2020.01.24
[youtubedl] / youtube_dl / extractor / fox9.py
index 17dfffa7b70867adaa5a8995e4e24e03ed18df4d..91f8f7b8a1a2727783305dfd15137978d61d121f 100644 (file)
@@ -1,13 +1,23 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .anvato import AnvatoIE
+from .common import InfoExtractor
 
 
-class FOX9IE(AnvatoIE):
-    _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
-    _TESTS = [{
-        'url': 'http://www.fox9.com/news/215123287-story',
+class FOX9IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(
+            'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id,
+            'Anvato', video_id)
+
+
+class FOX9NewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P<id>[^/?&#]+)'
+    _TEST = {
+        'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota',
         'md5': 'd6e1b2572c3bab8a849c9103615dd243',
         'info_dict': {
             'id': '314473',
@@ -21,22 +31,11 @@ class FOX9IE(AnvatoIE):
             'categories': ['News', 'Sports'],
             'tags': ['news', 'video'],
         },
-    }, {
-        'url': 'http://www.fox9.com/news/investigators/214070684-story',
-        'only_matching': True,
-    }]
+    }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        video_id = self._parse_json(
-            self._search_regex(
-                r"this\.videosJson\s*=\s*'(\[.+?\])';",
-                webpage, 'anvato playlist'),
-            video_id)[0]['video']
-
-        return self._get_anvato_videos(
-            'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
-            video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        anvato_id = self._search_regex(
+            r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id')
+        return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9')