Update README
[youtube-dl.git] / youtube-dl
index ae4917b..a2100aa 100755 (executable)
@@ -625,11 +625,12 @@ class FileDownloader(object):
                        return
                filetime = timeconvert(timestr)
                if filetime is None:
-                       return
+                       return filetime
                try:
                        os.utime(filename, (time.time(), filetime))
                except:
                        pass
+               return filetime
 
        def report_writedescription(self, descfn):
                """ Report that the description file is being written """
@@ -697,20 +698,23 @@ class FileDownloader(object):
        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""
                filename = self.prepare_filename(info_dict)
+               
+               # Forced printings
+               if self.params.get('forcetitle', False):
+                       print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forceurl', False):
+                       print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
+                       print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcedescription', False) and 'description' in info_dict:
+                       print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcefilename', False) and filename is not None:
+                       print filename.encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forceformat', False):
+                       print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
+
                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):
-                       # Forced printings
-                       if self.params.get('forcetitle', False):
-                               print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forceurl', False):
-                               print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
-                               print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcedescription', False) and 'description' in info_dict:
-                               print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcefilename', False) and filename is not None:
-                               print filename.encode(preferredencoding(), 'xmlcharrefreplace')
-
                        return
 
                if filename is None:
@@ -769,23 +773,25 @@ class FileDownloader(object):
                                self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
                                return
 
-               try:
-                       success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
-               except (OSError, IOError), err:
-                       raise UnavailableVideoError
-               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-                       self.trouble(u'ERROR: unable to download video data: %s' % str(err))
-                       return
-               except (ContentTooShortError, ), err:
-                       self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
-                       return
-
-               if success:
+               if not self.params.get('skip_download', False):
                        try:
-                               self.post_process(filename, info_dict)
-                       except (PostProcessingError), err:
-                               self.trouble(u'ERROR: postprocessing: %s' % str(err))
+                               success,add_data = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
+                               info_dict.update(add_data)
+                       except (OSError, IOError), err:
+                               raise UnavailableVideoError
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self.trouble(u'ERROR: unable to download video data: %s' % str(err))
                                return
+                       except (ContentTooShortError, ), err:
+                               self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+                               return
+       
+                       if success:
+                               try:
+                                       self.post_process(filename, info_dict)
+                               except (PostProcessingError), err:
+                                       self.trouble(u'ERROR: postprocessing: %s' % str(err))
+                                       return
 
        def download(self, url_list):
                """Download a given list of URLs."""
@@ -990,10 +996,11 @@ class FileDownloader(object):
                self.try_rename(tmpfilename, filename)
 
                # Update file modification time
+               filetime = None
                if self.params.get('updatetime', True):
-                       self.try_utime(filename, data.info().get('last-modified', None))
+                       filetime = self.try_utime(filename, data.info().get('last-modified', None))
 
-               return True
+               return True, {'filetime': filetime}
 
 
 class InfoExtractor(object):
@@ -1026,9 +1033,8 @@ class InfoExtractor(object):
        description:    One-line video description.
 
        Subclasses of this one should re-define the _real_initialize() and
-       _real_extract() methods, as well as the suitable() static method.
-       Probably, they should also be instantiated and added to the main
-       downloader.
+       _real_extract() methods and define a _VALID_URL regexp.
+       Probably, they should also be added to the list of extractors.
        """
 
        _ready = False
@@ -1039,10 +1045,9 @@ class InfoExtractor(object):
                self._ready = False
                self.set_downloader(downloader)
 
-       @staticmethod
-       def suitable(url):
+       def suitable(self, url):
                """Receives a URL and returns True if suitable for this IE."""
-               return False
+               return re.match(self._VALID_URL, url) is not None
 
        def initialize(self):
                """Initializes an instance (authentication, etc)."""
@@ -1088,10 +1093,7 @@ class YoutubeIE(InfoExtractor):
                '43': 'webm',
                '45': 'webm',
        }
-
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeIE._VALID_URL, url) is not None)
+       IE_NAME = u'youtube'
 
        def report_lang(self):
                """Report attempt to set language."""
@@ -1320,6 +1322,8 @@ class YoutubeIE(InfoExtractor):
                                return
                        if req_format is None:
                                video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+                       elif req_format == 'worst':
+                               video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
                        elif req_format == '-1':
                                video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
                        else:
@@ -1365,15 +1369,12 @@ class MetacafeIE(InfoExtractor):
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
        _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None
+       IE_NAME = u'metacafe'
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(MetacafeIE._VALID_URL, url) is not None)
-
        def report_disclaimer(self):
                """Report disclaimer retrieval."""
                self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
@@ -1507,14 +1508,11 @@ class DailymotionIE(InfoExtractor):
        """Information Extractor for Dailymotion"""
 
        _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+       IE_NAME = u'dailymotion'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(DailymotionIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
@@ -1601,14 +1599,11 @@ class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 
        _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+       IE_NAME = u'video.google'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(GoogleIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
@@ -1711,14 +1706,11 @@ class PhotobucketIE(InfoExtractor):
        """Information extractor for photobucket.com."""
 
        _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+       IE_NAME = u'photobucket'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(PhotobucketIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
@@ -1796,14 +1788,11 @@ class YahooIE(InfoExtractor):
        # _VPAGE_URL matches only the extractable '/watch/' URLs
        _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
        _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
+       IE_NAME = u'video.yahoo'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(YahooIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
@@ -1952,14 +1941,11 @@ class VimeoIE(InfoExtractor):
 
        # _VALID_URL matches Vimeo URLs
        _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+       IE_NAME = u'vimeo'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(VimeoIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
@@ -2066,13 +2052,12 @@ class VimeoIE(InfoExtractor):
 class GenericIE(InfoExtractor):
        """Generic last-resort information extractor."""
 
+       _VALID_URL = r'.*'
+       IE_NAME = u'generic'
+
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return True
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
@@ -2166,21 +2151,18 @@ class GenericIE(InfoExtractor):
 
 class YoutubeSearchIE(InfoExtractor):
        """Information Extractor for YouTube search queries."""
-       _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
        _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _max_youtube_results = 1000
+       IE_NAME = u'youtube:search'
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
-
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
@@ -2190,7 +2172,7 @@ class YoutubeSearchIE(InfoExtractor):
                self._youtube_ie.initialize()
 
        def _real_extract(self, query):
-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
@@ -2258,21 +2240,18 @@ class YoutubeSearchIE(InfoExtractor):
 
 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""
-       _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
        _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
        _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
        _MORE_PAGES_INDICATOR = r'<span>Next</span>'
        _google_ie = None
        _max_google_results = 1000
+       IE_NAME = u'video.google:search'
 
        def __init__(self, google_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._google_ie = google_ie
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
-
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
@@ -2282,7 +2261,7 @@ class GoogleSearchIE(InfoExtractor):
                self._google_ie.initialize()
 
        def _real_extract(self, query):
-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
@@ -2350,21 +2329,18 @@ class GoogleSearchIE(InfoExtractor):
 
 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""
-       _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
        _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
        _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
        _MORE_PAGES_INDICATOR = r'\s*Next'
        _yahoo_ie = None
        _max_yahoo_results = 1000
+       IE_NAME = u'video.yahoo:search'
 
        def __init__(self, yahoo_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._yahoo_ie = yahoo_ie
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
-
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
@@ -2374,7 +2350,7 @@ class YahooSearchIE(InfoExtractor):
                self._yahoo_ie.initialize()
 
        def _real_extract(self, query):
-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
@@ -2448,15 +2424,12 @@ class YoutubePlaylistIE(InfoExtractor):
        _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
+       IE_NAME = u'youtube:playlist'
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
-
        def report_download_page(self, playlist_id, pagenum):
                """Report attempt to download playlist page with given number."""
                self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
@@ -2526,15 +2499,12 @@ class YoutubeUserIE(InfoExtractor):
        _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
        _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
        _youtube_ie = None
+       IE_NAME = u'youtube:user'
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
-
        def report_download_page(self, username, start_index):
                """Report attempt to download user page."""
                self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
@@ -2612,14 +2582,11 @@ class DepositFilesIE(InfoExtractor):
        """Information extractor for depositfiles.com"""
 
        _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
+       IE_NAME = u'DepositFiles'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(DepositFilesIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, file_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
@@ -2699,14 +2666,11 @@ class FacebookIE(InfoExtractor):
                'highqual': 'mp4',
                'lowqual': 'mp4',
        }
+       IE_NAME = u'facebook'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
-       @staticmethod
-       def suitable(url):
-               return (re.match(FacebookIE._VALID_URL, url) is not None)
-
        def _reporter(self, message):
                """Add header and report message."""
                self._downloader.to_screen(u'[facebook] %s' % message)
@@ -2872,6 +2836,8 @@ class FacebookIE(InfoExtractor):
                                return
                        if req_format is None:
                                video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+                       elif req_format == 'worst':
+                               video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
                        elif req_format == '-1':
                                video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
                        else:
@@ -2912,10 +2878,7 @@ class BlipTVIE(InfoExtractor):
 
        _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
        _URL_EXT = r'^.*\.([a-z0-9]+)$'
-
-       @staticmethod
-       def suitable(url):
-               return (re.match(BlipTVIE._VALID_URL, url) is not None)
+       IE_NAME = u'blip.tv'
 
        def report_extraction(self, file_id):
                """Report information extraction."""
@@ -2987,14 +2950,11 @@ class MyVideoIE(InfoExtractor):
        """Information Extractor for myvideo.de."""
 
        _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+       IE_NAME = u'myvideo'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
        
-       @staticmethod
-       def suitable(url):
-               return (re.match(MyVideoIE._VALID_URL, url) is not None)
-
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
@@ -3062,11 +3022,8 @@ class MyVideoIE(InfoExtractor):
 class ComedyCentralIE(InfoExtractor):
        """Information extractor for The Daily Show and Colbert Report """
 
-       _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
-
-       @staticmethod
-       def suitable(url):
-               return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+       _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+       IE_NAME = u'comedycentral'
 
        def report_extraction(self, episode_id):
                self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
@@ -3207,10 +3164,7 @@ class EscapistIE(InfoExtractor):
        """Information extractor for The Escapist """
 
        _VALID_URL = r'^(https?://)?(www\.)escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?].*$'
-
-       @staticmethod
-       def suitable(url):
-               return (re.match(EscapistIE._VALID_URL, url) is not None)
+       IE_NAME = u'escapist'
 
        def report_extraction(self, showName):
                self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
@@ -3339,11 +3293,13 @@ class PostProcessor(object):
 
 class FFmpegExtractAudioPP(PostProcessor):
 
-       def __init__(self, downloader=None, preferredcodec=None):
+       def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
                PostProcessor.__init__(self, downloader)
                if preferredcodec is None:
                        preferredcodec = 'best'
                self._preferredcodec = preferredcodec
+               self._preferredquality = preferredquality
+               self._keepvideo = keepvideo
 
        @staticmethod
        def get_audio_codec(path):
@@ -3392,12 +3348,16 @@ class FFmpegExtractAudioPP(PostProcessor):
                                # MP3 otherwise.
                                acodec = 'libmp3lame'
                                extension = 'mp3'
-                               more_opts = ['-ab', '128k']
+                               more_opts = []
+                               if self._preferredquality is not None:
+                                       more_opts += ['-ab', self._preferredquality]
                else:
                        # We convert the audio (lossy)
                        acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
                        extension = self._preferredcodec
-                       more_opts = ['-ab', '128k']
+                       more_opts = []
+                       if self._preferredquality is not None:
+                               more_opts += ['-ab', self._preferredquality]
                        if self._preferredcodec == 'aac':
                                more_opts += ['-f', 'adts']
 
@@ -3410,11 +3370,19 @@ class FFmpegExtractAudioPP(PostProcessor):
                        self._downloader.to_stderr(u'WARNING: error running ffmpeg')
                        return None
 
-               try:
-                       os.remove(path)
-               except (IOError, OSError):
-                       self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
-                       return None
+               # Try to update the date time for extracted audio file.
+               if information.get('filetime') is not None:
+                       try:
+                               os.utime(new_path, (time.time(), information['filetime']))
+                       except:
+                               self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+
+               if not self._keepvideo:
+                       try:
+                               os.remove(path)
+                       except (IOError, OSError):
+                               self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+                               return None
 
                information['filepath'] = new_path
                return information
@@ -3522,6 +3490,9 @@ def parseOpts():
        general.add_option('--dump-user-agent',
                        action='store_true', dest='dump_user_agent',
                        help='display the current browser identification', default=False)
+       general.add_option('--list-extractors',
+                       action='store_true', dest='list_extractors',
+                       help='List all supported extractors and the URLs they would handle', default=False)
 
        selection.add_option('--playlist-start',
                        dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
@@ -3549,7 +3520,9 @@ def parseOpts():
        verbosity.add_option('-q', '--quiet',
                        action='store_true', dest='quiet', help='activates quiet mode', default=False)
        verbosity.add_option('-s', '--simulate',
-                       action='store_true', dest='simulate', help='do not download video', default=False)
+                       action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
+       verbosity.add_option('--skip-download',
+                       action='store_true', dest='skip_download', help='do not download the video', default=False)
        verbosity.add_option('-g', '--get-url',
                        action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
        verbosity.add_option('-e', '--get-title',
@@ -3563,6 +3536,9 @@ def parseOpts():
        verbosity.add_option('--get-filename',
                        action='store_true', dest='getfilename',
                        help='simulate, quiet but print output filename', default=False)
+       verbosity.add_option('--get-format',
+                       action='store_true', dest='getformat',
+                       help='simulate, quiet but print output format', default=False)
        verbosity.add_option('--no-progress',
                        action='store_true', dest='noprogress', help='do not print progress bar', default=False)
        verbosity.add_option('--console-title',
@@ -3604,6 +3580,10 @@ def parseOpts():
                        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')
+       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,
+                       help='keeps the video file on disk after the post-processing; the video is erased by default')
 
 
        parser.add_option_group(general)
@@ -3618,6 +3598,36 @@ def parseOpts():
 
        return parser, opts, args
 
+def gen_extractors():
+       """ Return a list of an instance of every supported extractor.
+       The order does matter; the first extractor matched is the one handling the URL.
+       """
+       youtube_ie = YoutubeIE()
+       google_ie = GoogleIE()
+       yahoo_ie = YahooIE()
+       return [
+               youtube_ie,
+               MetacafeIE(youtube_ie),
+               DailymotionIE(),
+               YoutubePlaylistIE(youtube_ie),
+               YoutubeUserIE(youtube_ie),
+               YoutubeSearchIE(youtube_ie),
+               google_ie,
+               GoogleSearchIE(google_ie),
+               PhotobucketIE(),
+               yahoo_ie,
+               YahooSearchIE(yahoo_ie),
+               DepositFilesIE(),
+               FacebookIE(),
+               BlipTVIE(),
+               VimeoIE(),
+               MyVideoIE(),
+               ComedyCentralIE(),
+               EscapistIE(),
+
+               GenericIE()
+       ]
+
 def main():
        parser, opts, args = parseOpts()
 
@@ -3637,12 +3647,6 @@ def main():
                print std_headers['User-Agent']
                sys.exit(0)
 
-       # General configuration
-       cookie_processor = urllib2.HTTPCookieProcessor(jar)
-       opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
-       urllib2.install_opener(opener)
-       socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
-
        # Batch file verification
        batchurls = []
        if opts.batchfile is not None:
@@ -3658,6 +3662,23 @@ def main():
                        sys.exit(u'ERROR: batch file could not be read')
        all_urls = batchurls + args
 
+       # General configuration
+       cookie_processor = urllib2.HTTPCookieProcessor(jar)
+       opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
+       urllib2.install_opener(opener)
+       socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+       extractors = gen_extractors()
+
+       if opts.list_extractors:
+               for ie in extractors:
+                       print(ie.IE_NAME)
+                       matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
+                       all_urls = filter(lambda url: url not in matchedUrls, all_urls)
+                       for mu in matchedUrls:
+                               print(u'  ' + mu)
+               sys.exit(0)
+
        # Conflicting, missing and erroneous options
        if opts.usenetrc and (opts.username is not None or opts.password is not None):
                parser.error(u'using .netrc conflicts with giving username/password')
@@ -3695,45 +3716,20 @@ def main():
                if opts.audioformat not in ['best', 'aac', 'mp3']:
                        parser.error(u'invalid audio format specified')
 
-       # Information extractors
-       youtube_ie = YoutubeIE()
-       google_ie = GoogleIE()
-       yahoo_ie = YahooIE()
-       extractors = [ # Order does matter
-               youtube_ie,
-               MetacafeIE(youtube_ie),
-               DailymotionIE(),
-               YoutubePlaylistIE(youtube_ie),
-               YoutubeUserIE(youtube_ie),
-               YoutubeSearchIE(youtube_ie),
-               google_ie,
-               GoogleSearchIE(google_ie),
-               PhotobucketIE(),
-               yahoo_ie,
-               YahooSearchIE(yahoo_ie),
-               DepositFilesIE(),
-               FacebookIE(),
-               BlipTVIE(),
-               VimeoIE(),
-               MyVideoIE(),
-               ComedyCentralIE(),
-               EscapistIE(),
-
-               GenericIE()
-       ]
-
        # File downloader
        fd = FileDownloader({
                'usenetrc': opts.usenetrc,
                'username': opts.username,
                'password': opts.password,
-               'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
+               'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
                'forceurl': opts.geturl,
                'forcetitle': opts.gettitle,
                'forcethumbnail': opts.getthumbnail,
                'forcedescription': opts.getdescription,
                'forcefilename': opts.getfilename,
-               'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
+               'forceformat': opts.getformat,
+               'simulate': opts.simulate,
+               'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
                'format': opts.format,
                'format_limit': opts.format_limit,
                'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
@@ -3768,7 +3764,7 @@ def main():
 
        # PostProcessors
        if opts.extractaudio:
-               fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
+               fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
 
        # Update version
        if opts.update_self: