浏览代码

[tf1] add support for more related web sites

remitamine 9 年之前
父节点
当前提交
db3b8b2103
共有 1 个文件被更改,包括 2 次插入2 次删除
  1. 2 2
      youtube_dl/extractor/tf1.py

+ 2 - 2
youtube_dl/extractor/tf1.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class TF1IE(InfoExtractor):
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/(?:[^/]+/)*(?P<id>.+?)\.html'
+    _VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)'
     _TESTS = [{
     _TESTS = [{
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'info_dict': {
         'info_dict': {
@@ -48,6 +48,6 @@ class TF1IE(InfoExtractor):
         video_id = self._match_id(url)
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         webpage = self._download_webpage(url, video_id)
         wat_id = self._html_search_regex(
         wat_id = self._html_search_regex(
-            r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})(?:#.*?)?\1',
+            r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})(?:.*?)?\1',
             webpage, 'wat id', group='id')
             webpage, 'wat id', group='id')
         return self.url_result('wat:%s' % wat_id, 'Wat')
         return self.url_result('wat:%s' % wat_id, 'Wat')