Merge remote-tracking branch 'FiloSottille/supports'

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index da2294a6b89b8e93bb1511babbdc282f2b46969e..ff5c47726db5c1f4d1bfb3492c747b2bb2481382 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -97,7 +97,7 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
-       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -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
@@ -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'
@@ -2995,22 +2994,15 @@ class YoukuIE(InfoExtractor):
                #return ''.join(mixed)
                return mixed
 
-
        def _get_file_id(self, fileId, seed):
                mixed = self._get_file_ID_mix_string(seed)
                ids = fileId.split('*')
                realId = []
                for ch in ids:
-                       if ch is not '':
+                       if ch:
                                realId.append(mixed[int(ch)])
                return ''.join(realId)
 
-       def _gen_key(self, key1, key2):
-               pass
-
-
-
-
        def _real_extract(self, url):
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:
@@ -3019,7 +3011,6 @@ class YoukuIE(InfoExtractor):
                video_id = mobj.group('ID')
 
                info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
-               print info_url
 
                request = urllib2.Request(info_url, None, std_headers)
                try:
@@ -3076,7 +3067,7 @@ class YoukuIE(InfoExtractor):
 
                        temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
                        download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
-                       print download_url
+
                        info = {
                                'id': '%s_part%02d' % (video_id, index),
                                'url': download_url,
@@ -3088,4 +3079,68 @@ class YoukuIE(InfoExtractor):
                        files_info.append(info)
 
                return files_info
-# vim: tabstop=4 shiftwidth=4 softtabstop=4 noexpandtab
+
+
+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]