X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/147e1f3ceb674aa51d1837ca812f8176381d5d7b..d1b3edec11dc27709c45b3b16fa4e50a40726794:/youtube-dl?ds=sidebyside diff --git a/youtube-dl b/youtube-dl index e89c915..d546949 100755 --- a/youtube-dl +++ b/youtube-dl @@ -27,7 +27,7 @@ except ImportError: from cgi import parse_qs std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.6) Gecko/20100627 Firefox/3.6.6', + 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.8) Gecko/20100723 Firefox/3.6.8', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'en-us,en;q=0.5', @@ -131,7 +131,7 @@ class PostProcessingError(Exception): """ pass -class UnavailableFormatError(Exception): +class UnavailableVideoError(Exception): """Unavailable Format exception. This exception will be thrown when a video is requested @@ -287,16 +287,6 @@ class FileDownloader(object): multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) return long(round(number * multiplier)) - @staticmethod - def verify_url(url): - """Verify a URL is valid and data could be downloaded. Return real data URL.""" - request = urllib2.Request(url, None, std_headers) - data = urllib2.urlopen(request) - data.read(1) - url = data.geturl() - data.close() - return url - def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) @@ -396,13 +386,6 @@ class FileDownloader(object): """Process a single dictionary returned by an InfoExtractor.""" # Do nothing else if in simulate mode if self.params.get('simulate', False): - # Verify URL if it's an HTTP one - if info_dict['url'].startswith('http'): - try: - self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8') - except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err: - raise UnavailableFormatError - # Forced printings if self.params.get('forcetitle', False): print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') @@ -435,7 +418,7 @@ class FileDownloader(object): try: success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) except (OSError, IOError), err: - raise UnavailableFormatError + raise UnavailableVideoError except (urllib2.URLError, httplib.HTTPException, socket.error), err: self.trouble('ERROR: unable to download video data: %s' % str(err)) return @@ -539,32 +522,50 @@ class FileDownloader(object): count = 0 retries = self.params.get('retries', 0) - while True: + while count <= retries: # Establish connection try: data = urllib2.urlopen(request) break except (urllib2.HTTPError, ), err: - if err.code == 503: - # Retry in case of HTTP error 503 - count += 1 - if count <= retries: - self.report_retry(count, retries) - continue - if err.code != 416: # 416 is 'Requested range not satisfiable' + if err.code != 503 and err.code != 416: + # Unexpected HTTP error raise - # Unable to resume - data = urllib2.urlopen(basic_request) - content_length = data.info()['Content-Length'] - - if content_length is not None and long(content_length) == resume_len: - # Because the file had already been fully downloaded - self.report_file_already_downloaded(filename) - return True - else: - # Because the server didn't let us - self.report_unable_to_resume() - open_mode = 'wb' + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = urllib2.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (urllib2.HTTPError, ), err: + if err.code != 503: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < long(content_length) < resume_len + 100)): + # The file had already been fully downloaded. + # Explanation to the above condition: in issue #175 it was revealed that + # YouTube sometimes adds or removes a few bytes from the end of the file, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.trouble(u'ERROR: giving up after %s retries' % retries) + return False data_len = data.info().get('Content-length', None) data_len_str = self.format_bytes(data_len) @@ -684,12 +685,12 @@ class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' - _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NETRC_MACHINE = 'youtube' - # Listed in order of priority for the -b option - _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13', None] + # Listed in order of quality + _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13'] _video_extensions = { '13': '3gp', '17': 'mp4', @@ -812,124 +813,121 @@ class YoutubeIE(InfoExtractor): if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - - # At this point we have a new video - if self._downloader is not None: - self._downloader.increment_downloads() video_id = mobj.group(2) - # Downloader parameters - best_quality = False - all_formats = False - format_param = None - quality_index = 0 - if self._downloader is not None: - params = self._downloader.params - format_param = params.get('format', None) - if format_param == '0': - format_limit = params.get('format_limit', None) - if format_limit is not None: - try: - # Start at a different format if the user has limited the maximum quality - quality_index = self._available_formats.index(format_limit) - except ValueError: - pass - format_param = self._available_formats[quality_index] - best_quality = True - elif format_param == '-1': - format_param = self._available_formats[quality_index] - all_formats = True - - while True: - # Extension - video_extension = self._video_extensions.get(format_param, 'flv') + # Get video webpage + self.report_video_webpage_download(video_id) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers) + try: + video_webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return - # Get video webpage - self.report_video_webpage_download(video_id) - request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers) + # Attempt to extract SWF player URL + mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage) + if mobj is not None: + player_url = mobj.group(1) + else: + player_url = None + + # Get video info + self.report_video_info_webpage_download(video_id) + for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: + video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (video_id, el_type)) + request = urllib2.Request(video_info_url, None, std_headers) try: - video_webpage = urllib2.urlopen(request).read() + video_info_webpage = urllib2.urlopen(request).read() + video_info = parse_qs(video_info_webpage) + if 'token' in video_info: + break except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) return + if 'token' not in video_info: + if 'reason' in video_info: + self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0]) + else: + self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') + return + + # Start extracting information + self.report_information_extraction(video_id) - # Attempt to extract SWF player URL - mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage) + # uploader + if 'author' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = urllib.unquote_plus(video_info['author'][0]) + + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = urllib.unquote_plus(video_info['title'][0]) + video_title = video_title.decode('utf-8') + video_title = sanitize_title(video_title) + + # simplified title + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = simple_title.strip(ur'_') + + # thumbnail image + if 'thumbnail_url' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: # don't panic if we can't find it + video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) + + # description + video_description = 'No description available.' + if self._downloader.params.get('forcedescription', False): + mobj = re.search(r'', video_webpage) if mobj is not None: - player_url = mobj.group(1) + video_description = mobj.group(1) + + # token + video_token = urllib.unquote_plus(video_info['token'][0]) + + # Decide which formats to download + requested_format = self._downloader.params.get('format', None) + get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token) + + if 'fmt_url_map' in video_info: + url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) + format_limit = self._downloader.params.get('format_limit', None) + if format_limit is not None and format_limit in self._available_formats: + format_list = self._available_formats[self._available_formats.index(format_limit):] else: - player_url = None - - # Get video info - self.report_video_info_webpage_download(video_id) - for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) - request = urllib2.Request(video_info_url, None, std_headers) - try: - video_info_webpage = urllib2.urlopen(request).read() - video_info = parse_qs(video_info_webpage) - if 'token' in video_info: - break - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) - return - self.report_information_extraction(video_id) - - # "t" param - if 'token' not in video_info: - # Attempt to see if YouTube has issued an error message - if 'reason' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason') - stream = open('reportme-ydl-%s.dat' % time.time(), 'wb') - stream.write(video_info_webpage) - stream.close() - else: - reason = urllib.unquote_plus(video_info['reason'][0]) - self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8')) + format_list = self._available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') return - token = urllib.unquote_plus(video_info['token'][0]) - video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token) - if format_param is not None: - video_real_url = '%s&fmt=%s' % (video_real_url, format_param) - - # Check possible RTMP download - if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_real_url = video_info['conn'][0] - - # uploader - if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = urllib.unquote_plus(video_info['author'][0]) + if requested_format is None: + video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality + elif requested_format == '-1': + video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats + else: + video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format - # title - if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = urllib.unquote_plus(video_info['title'][0]) - video_title = video_title.decode('utf-8') - video_title = sanitize_title(video_title) - - # simplified title - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) - simple_title = simple_title.strip(ur'_') - - # thumbnail image - if 'thumbnail_url' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video thumbnail') - video_thumbnail = '' - else: # don't panic if we can't find it - video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) - - # description - video_description = 'No description available.' - if self._downloader.params.get('forcedescription', False): - mobj = re.search(r'', video_webpage) - if mobj is not None: - video_description = mobj.group(1) + elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_url_list = [(None, video_info['conn'][0])] + + else: + self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info') + return + for format_param, video_real_url in video_url_list: + # At this point we have a new video + self._downloader.increment_downloads() + + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -944,32 +942,8 @@ class YoutubeIE(InfoExtractor): 'description': video_description.decode('utf-8'), 'player_url': player_url, }) - - if all_formats: - quality_index += 1 - if quality_index == len(self._available_formats): - # None left to get - return - else: - format_param = self._available_formats[quality_index] - continue - return - - except UnavailableFormatError, err: - if best_quality or all_formats: - quality_index += 1 - if quality_index == len(self._available_formats): - # I don't ever expect this to happen - if not all_formats: - self._downloader.trouble(u'ERROR: no known formats available for video') - return - else: - self.report_unavailable_format(video_id, format_param) - format_param = self._available_formats[quality_index] - continue - else: - self._downloader.trouble('ERROR: format not available for video') - return + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download video (format may not be available)') class MetacafeIE(InfoExtractor): @@ -1043,8 +1017,7 @@ class MetacafeIE(InfoExtractor): return # At this point we have a new video - if self._downloader is not None: - self._downloader.increment_downloads() + self._downloader.increment_downloads() simple_title = mobj.group(2).decode('utf-8') video_extension = 'flv' @@ -1066,15 +1039,15 @@ class MetacafeIE(InfoExtractor): return mediaURL = urllib.unquote(mobj.group(1)) - #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) - #if mobj is None: - # self._downloader.trouble(u'ERROR: unable to extract gdaKey') - # return - #gdaKey = mobj.group(1) - # - #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - - video_url = mediaURL + # Extract gdaKey if available + mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + if mobj is None: + video_url = mediaURL + #self._downloader.trouble(u'ERROR: unable to extract gdaKey') + #return + else: + gdaKey = mobj.group(1) + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: @@ -1101,8 +1074,8 @@ class MetacafeIE(InfoExtractor): 'format': u'NA', 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class DailymotionIE(InfoExtractor): @@ -1136,8 +1109,7 @@ class DailymotionIE(InfoExtractor): return # At this point we have a new video - if self._downloader is not None: - self._downloader.increment_downloads() + self._downloader.increment_downloads() video_id = mobj.group(1) simple_title = mobj.group(2).decode('utf-8') @@ -1190,8 +1162,8 @@ class DailymotionIE(InfoExtractor): 'format': u'NA', 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class GoogleIE(InfoExtractor): """Information extractor for video.google.com.""" @@ -1224,8 +1196,7 @@ class GoogleIE(InfoExtractor): return # At this point we have a new video - if self._downloader is not None: - self._downloader.increment_downloads() + self._downloader.increment_downloads() video_id = mobj.group(1) video_extension = 'mp4' @@ -1300,8 +1271,8 @@ class GoogleIE(InfoExtractor): 'format': u'NA', 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class PhotobucketIE(InfoExtractor): @@ -1335,8 +1306,7 @@ class PhotobucketIE(InfoExtractor): return # At this point we have a new video - if self._downloader is not None: - self._downloader.increment_downloads() + self._downloader.increment_downloads() video_id = mobj.group(1) video_extension = 'flv' @@ -1382,8 +1352,8 @@ class PhotobucketIE(InfoExtractor): 'format': u'NA', 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class YahooIE(InfoExtractor): @@ -1420,8 +1390,7 @@ class YahooIE(InfoExtractor): return # At this point we have a new video - if self._downloader is not None and new_video: - self._downloader.increment_downloads() + self._downloader.increment_downloads() video_id = mobj.group(2) video_extension = 'flv' @@ -1540,8 +1509,8 @@ class YahooIE(InfoExtractor): 'description': video_description, 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class GenericIE(InfoExtractor): @@ -1568,8 +1537,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): # At this point we have a new video - if self._downloader is not None: - self._downloader.increment_downloads() + self._downloader.increment_downloads() video_id = url.split('/')[-1] request = urllib2.Request(url) @@ -1640,8 +1608,8 @@ class GenericIE(InfoExtractor): 'format': u'NA', 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download video') class YoutubeSearchIE(InfoExtractor): @@ -1973,6 +1941,11 @@ class YoutubePlaylistIE(InfoExtractor): break pagenum = pagenum + 1 + playliststart = self._downloader.params.get('playliststart', 1) + playliststart -= 1 #our arrays are zero-based but the playlist is 1-based + if playliststart > 0: + video_ids = video_ids[playliststart:] + for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return @@ -2028,6 +2001,11 @@ class YoutubeUserIE(InfoExtractor): ids_in_page.append(mobj.group(1)) video_ids.extend(ids_in_page) + playliststart = self._downloader.params.get('playliststart', 1) + playliststart = playliststart-1 #our arrays are zero-based but the playlist is 1-based + if playliststart > 0: + video_ids = video_ids[playliststart:] + for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return @@ -2109,7 +2087,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2010.06.06', + version='2010.08.04', conflict_handler='resolve', ) @@ -2125,6 +2103,8 @@ if __name__ == '__main__': dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') parser.add_option('-R', '--retries', dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) + parser.add_option('--playlist-start', + dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', @@ -2138,16 +2118,14 @@ if __name__ == '__main__': video_format = optparse.OptionGroup(parser, 'Video Format Options') video_format.add_option('-f', '--format', action='store', dest='format', metavar='FORMAT', help='video format code') - video_format.add_option('-b', '--best-quality', - action='store_const', dest='format', help='download the best quality video possible', const='0') video_format.add_option('-m', '--mobile-version', action='store_const', dest='format', help='alias for -f 17', const='17') - video_format.add_option('-d', '--high-def', - action='store_const', dest='format', help='alias for -f 22', const='22') video_format.add_option('--all-formats', action='store_const', dest='format', help='download all available video formats', const='-1') video_format.add_option('--max-quality', - action='store', dest='format_limit', metavar='FORMAT', help='highest quality format limit for -b') + action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') + video_format.add_option('-b', '--best-quality', + action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)') parser.add_option_group(video_format) verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') @@ -2200,6 +2178,8 @@ if __name__ == '__main__': all_urls = batchurls + args # Conflicting, missing and erroneous options + if opts.bestquality: + print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n' 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') if opts.password is not None and opts.username is None: @@ -2220,6 +2200,11 @@ if __name__ == '__main__': opts.retries = long(opts.retries) except (TypeError, ValueError), err: parser.error(u'invalid retry count specified') + if opts.playliststart is not None: + try: + opts.playliststart = long(opts.playliststart) + except (TypeError, ValueError), err: + parser.error(u'invalid playlist page specified') # Information extractors youtube_ie = YoutubeIE() @@ -2261,6 +2246,7 @@ if __name__ == '__main__': 'retries': opts.retries, 'continuedl': opts.continue_dl, 'noprogress': opts.noprogress, + 'playliststart': opts.playliststart, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie)