浏览代码

[generic] Add support for xfileshare embeds (closes #15879)

Sergey M․ 7 年之前
父节点
当前提交
178ee88319
共有 2 个文件被更改,包括 15 次插入0 次删除
  1. 6 0
      youtube_dl/extractor/generic.py
  2. 9 0
      youtube_dl/extractor/xfileshare.py

+ 6 - 0
youtube_dl/extractor/generic.py

@@ -104,6 +104,7 @@ from .mediasite import MediasiteIE
 from .springboardplatform import SpringboardPlatformIE
 from .springboardplatform import SpringboardPlatformIE
 from .yapfiles import YapFilesIE
 from .yapfiles import YapFilesIE
 from .vice import ViceIE
 from .vice import ViceIE
+from .xfileshare import XFileShareIE
 
 
 
 
 class GenericIE(InfoExtractor):
 class GenericIE(InfoExtractor):
@@ -2971,6 +2972,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
             return self.playlist_from_matches(
                 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
                 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
 
 
+        xfileshare_urls = XFileShareIE._extract_urls(webpage)
+        if xfileshare_urls:
+            return self.playlist_from_matches(
+                xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
+
         def merge_dicts(dict1, dict2):
         def merge_dicts(dict1, dict2):
             merged = {}
             merged = {}
             for k, v in dict1.items():
             for k, v in dict1.items():

+ 9 - 0
youtube_dl/extractor/xfileshare.py

@@ -118,6 +118,15 @@ class XFileShareIE(InfoExtractor):
         'only_matching': True
         'only_matching': True
     }]
     }]
 
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1'
+                % '|'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
+                webpage)]
+
     def _real_extract(self, url):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         video_id = mobj.group('id')