Proper support for changing User-Agents from IEs

[yt-dlp.git] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index b8311ca5c119acc15ae8c2cf4c7e341f2b83b643..9712480228a7c57e17d0ab80528a50806bb722c1 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -2209,6 +2209,7 @@ def _real_extract(self, url):
             cchar = '?'
         json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
         request = compat_urllib_request.Request(json_url)
+        request.add_header('User-Agent', 'iTunes/10.6.1')
         self.report_extraction(mobj.group(1))
         info = None
         try:
@@ -2229,8 +2230,7 @@ def _real_extract(self, url):
                     'urlhandle': urlh
                 }
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
-            return
+            raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
         if info is None: # Regular URL
             try:
                 json_code_bytes = urlh.read()
@@ -2263,13 +2263,13 @@ def _real_extract(self, url):
                     'format': data['media']['mimeType'],
                     'thumbnail': data['thumbnailUrl'],
                     'description': data['description'],
-                    'player_url': data['embedUrl']
+                    'player_url': data['embedUrl'],
+                    'user_agent': 'iTunes/10.6.1',
                 }
             except (ValueError,KeyError) as err:
                 self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
                 return
 
-        std_headers['User-Agent'] = 'iTunes/10.6.1'
         return [info]
 
 
@@ -3896,9 +3896,6 @@ class YouJizzIE(InfoExtractor):
     """Information extractor for youjizz.com."""
     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
 
-    def __init__(self, downloader=None):
-        InfoExtractor.__init__(self, downloader)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
@@ -3911,19 +3908,15 @@ def _real_extract(self, url):
         webpage = self._download_webpage(url, video_id)
 
         # Get the video title
-        VIDEO_TITLE_RE = r'<title>(?P<title>.*)</title>'
-        result = re.search(VIDEO_TITLE_RE, webpage)
+        result = re.search(r'<title>(?P<title>.*)</title>', webpage)
         if result is None:
-            self._downloader.trouble(u'ERROR: unable to extract video title')
-            return
+            raise ExtractorError(u'ERROR: unable to extract video title')
         video_title = result.group('title').strip()
 
         # Get the embed page
-        EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)'
-        result = re.search(EMBED_PAGE_RE, webpage)
+        result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
         if result is None:
-            self._downloader.trouble(u'ERROR: unable to extract embed page')
-            return
+            raise ExtractorError(u'ERROR: unable to extract embed page')
 
         embed_page_url = result.group(0).strip()
         video_id = result.group('videoid')
@@ -3931,22 +3924,16 @@ def _real_extract(self, url):
         webpage = self._download_webpage(embed_page_url, video_id)
 
         # Get the video URL
-        SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);'
-        result = re.search(SOURCE_RE, webpage)
+        result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
         if result is None:
-            self._downloader.trouble(u'ERROR: unable to extract video url')
-            return
+            raise ExtractorError(u'ERROR: unable to extract video url')
         video_url = result.group('source')
 
         info = {'id': video_id,
                 'url': video_url,
-                'uploader': None,
-                'upload_date': None,
                 'title': video_title,
                 'ext': 'flv',
                 'format': 'flv',
-                'thumbnail': None,
-                'description': None,
                 'player_url': embed_page_url}
 
         return [info]