Adding HTTPS support for YouTube playlists and users; Escaping dots.

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 53d4548..7a47365 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -15,7 +15,7 @@ __author__  = (
        )
 
 __license__ = 'Public Domain'
-__version__ = '2011.09.18b'
+__version__ = '2011.09.18c'
 
 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
 
@@ -1088,7 +1088,7 @@ class YoutubeIE(InfoExtractor):
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
        _NETRC_MACHINE = 'youtube'
        # Listed in order of quality
-       _available_formats = ['38', '37', '22', '45', '35', '43', '34', '18', '6', '5', '17', '13']
+       _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',
@@ -1097,6 +1097,7 @@ class YoutubeIE(InfoExtractor):
                '37': 'mp4',
                '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
                '43': 'webm',
+               '44': 'webm',
                '45': 'webm',
        }
        IE_NAME = u'youtube'
@@ -2431,7 +2432,7 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 
-       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+       _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([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 = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
@@ -2505,7 +2506,7 @@ class YoutubePlaylistIE(InfoExtractor):
 class YoutubeUserIE(InfoExtractor):
        """Information Extractor for YouTube users."""
 
-       _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+       _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
        _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
        _GDATA_PAGE_SIZE = 50
        _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
@@ -2593,7 +2594,7 @@ class YoutubeUserIE(InfoExtractor):
 class DepositFilesIE(InfoExtractor):
        """Information extractor for depositfiles.com"""
 
-       _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
+       _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
        IE_NAME = u'DepositFiles'
 
        def __init__(self, downloader=None):
@@ -2670,7 +2671,7 @@ class DepositFilesIE(InfoExtractor):
 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 
-       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
        _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
        _NETRC_MACHINE = 'facebook'
        _available_formats = ['highqual', 'lowqual']
@@ -3175,7 +3176,7 @@ class ComedyCentralIE(InfoExtractor):
 class EscapistIE(InfoExtractor):
        """Information extractor for The Escapist """
 
-       _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+       _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
        IE_NAME = u'escapist'
 
        def report_extraction(self, showName):
@@ -3350,12 +3351,14 @@ class FFmpegExtractAudioPP(PostProcessor):
 
                more_opts = []
                if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
-                       if filecodec == 'aac' or filecodec == 'mp3':
+                       if filecodec in ['aac', 'mp3', 'vorbis']:
                                # Lossless if possible
                                acodec = 'copy'
                                extension = filecodec
                                if filecodec == 'aac':
                                        more_opts = ['-f', 'adts']
+                               if filecodec == 'vorbis':
+                                       extension = 'ogg'
                        else:
                                # MP3 otherwise.
                                acodec = 'libmp3lame'
@@ -3365,13 +3368,15 @@ class FFmpegExtractAudioPP(PostProcessor):
                                        more_opts += ['-ab', self._preferredquality]
                else:
                        # We convert the audio (lossy)
-                       acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
+                       acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
                        extension = self._preferredcodec
                        more_opts = []
                        if self._preferredquality is not None:
                                more_opts += ['-ab', self._preferredquality]
                        if self._preferredcodec == 'aac':
                                more_opts += ['-f', 'adts']
+                       if self._preferredcodec == 'vorbis':
+                               extension = 'ogg'
 
                (prefix, ext) = os.path.splitext(path)
                new_path = prefix + '.' + extension
@@ -3582,7 +3587,7 @@ def parseOpts():
                        action='store_false', dest='continue_dl',
                        help='do not resume partially downloaded files (restart from beginning)')
        filesystem.add_option('--cookies',
-                       dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+                       dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
        filesystem.add_option('--no-part',
                        action='store_true', dest='nopart', help='do not use .part files', default=False)
        filesystem.add_option('--no-mtime',
@@ -3599,7 +3604,7 @@ def parseOpts():
        postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
                        help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
        postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-                       help='"best", "aac" or "mp3"; best by default')
+                       help='"best", "aac", "vorbis" or "mp3"; best by default')
        postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
                        help='ffmpeg audio bitrate specification, 128k by default')
        postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
@@ -3733,7 +3738,7 @@ def main():
        except (TypeError, ValueError), err:
                parser.error(u'invalid playlist end number specified')
        if opts.extractaudio:
-               if opts.audioformat not in ['best', 'aac', 'mp3']:
+               if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
                        parser.error(u'invalid audio format specified')
 
        # File downloader