added new FAQ on exe dependency

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index d6748981bf4c3634c7619282c6efd7e24dbcb539..6442888d88eb3d097d92ee792b1fcbb7b343a230 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -404,7 +404,7 @@ class YoutubeIE(InfoExtractor):
                        url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
                        url_data = [parse_qs(uds) for uds in url_data_strs]
                        url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
-                       url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+                       url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
 
                        format_limit = self._downloader.params.get('format_limit', None)
                        available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
@@ -1473,7 +1473,7 @@ class YoutubePlaylistIE(InfoExtractor):
 
        _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
-       _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=(PL)?%s&'
+       _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=.*?%s'
        _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
        IE_NAME = u'youtube:playlist'
 
@@ -2959,7 +2959,6 @@ class MTVIE(InfoExtractor):
                return [info]
 
 
-
 class YoukuIE(InfoExtractor):
 
        _VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
@@ -3080,3 +3079,68 @@ class YoukuIE(InfoExtractor):
                        files_info.append(info)
 
                return files_info
+
+
+class XNXXIE(InfoExtractor):
+       """Information extractor for xnxx.com"""
+
+       _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
+       IE_NAME = u'xnxx'
+       VIDEO_URL_RE = r'flv_url=(.*?)&amp;'
+       VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
+       VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
+
+       def report_webpage(self, video_id):
+               """Report information extraction"""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction"""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group(1).decode('utf-8')
+
+               self.report_webpage(video_id)
+
+               # Get webpage content
+               try:
+                       webpage = urllib2.urlopen(url).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
+                       return
+
+               result = re.search(self.VIDEO_URL_RE, webpage)
+               if result is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = urllib.unquote(result.group(1).decode('utf-8'))
+
+               result = re.search(self.VIDEO_TITLE_RE, webpage)
+               if result is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = result.group(1).decode('utf-8')
+
+               result = re.search(self.VIDEO_THUMB_RE, webpage)
+               if result is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = result.group(1).decode('utf-8')
+
+               info = {'id': video_id,
+                               'url': video_url,
+                               'uploader': None,
+                               'upload_date': None,
+                               'title': video_title,
+                               'ext': 'flv',
+                               'format': 'flv',
+                               'thumbnail': video_thumbnail,
+                               'description': None,
+                               'player_url': None}
+
+               return [info]