diff options
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/InfoExtractors.py | 195 | ||||
| -rw-r--r-- | youtube_dl/PostProcessor.py | 10 | ||||
| -rw-r--r-- | youtube_dl/__init__.py | 21 |
3 files changed, 216 insertions, 10 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d95423f7d..6442888d8 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -13,6 +13,8 @@ import urllib import urllib2 import email.utils import xml.etree.ElementTree +import random +import math from urlparse import parse_qs try: @@ -95,7 +97,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _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).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _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' @@ -402,7 +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 @@ -1471,7 +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' @@ -2955,3 +2957,190 @@ 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' + IE_NAME = u'Youku' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id) + + def _gen_sid(self): + nowTime = int(time.time() * 1000) + random1 = random.randint(1000,1998) + random2 = random.randint(1000,9999) + + return "%d%d%d" %(nowTime,random1,random2) + + def _get_file_ID_mix_string(self, seed): + mixed = [] + source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") + seed = float(seed) + for i in range(len(source)): + seed = (seed * 211 + 30031 ) % 65536 + index = math.floor(seed / 65536 * len(source) ) + mixed.append(source[int(index)]) + source.remove(source[int(index)]) + #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: + realId.append(mixed[int(ch)]) + return ''.join(realId) + + 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('ID') + + info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id + + request = urllib2.Request(info_url, None, std_headers) + try: + self.report_download_webpage(video_id) + jsondata = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + try: + config = json.loads(jsondata) + + video_title = config['data'][0]['title'] + seed = config['data'][0]['seed'] + + format = self._downloader.params.get('format', None) + supported_format = config['data'][0]['streamfileids'].keys() + + if format is None or format == 'best': + if 'hd2' in supported_format: + format = 'hd2' + else: + format = 'flv' + ext = u'flv' + elif format == 'worst': + format = 'mp4' + ext = u'mp4' + else: + format = 'flv' + ext = u'flv' + + + fileid = config['data'][0]['streamfileids'][format] + seg_number = len(config['data'][0]['segs'][format]) + + keys=[] + for i in xrange(seg_number): + keys.append(config['data'][0]['segs'][format][i]['k']) + + #TODO check error + #youku only could be viewed from mainland china + except: + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + files_info=[] + sid = self._gen_sid() + fileid = self._get_file_id(fileid, seed) + + #column 8,9 of fileid represent the segment number + #fileid[7:9] should be changed + for index, key in enumerate(keys): + + 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) + + info = { + 'id': '%s_part%02d' % (video_id, index), + 'url': download_url, + 'uploader': None, + 'title': video_title, + 'ext': ext, + 'format': u'NA' + } + 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=(.*?)&' + VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' + VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' + + 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] diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py index 527dc3a3d..375da1aa3 100644 --- a/youtube_dl/PostProcessor.py +++ b/youtube_dl/PostProcessor.py @@ -142,14 +142,20 @@ class FFmpegExtractAudioPP(PostProcessor): extension = 'mp3' more_opts = [] if self._preferredquality is not None: - more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality] + if int(self._preferredquality) < 10: + more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality] + else: + more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality] else: # We convert the audio (lossy) acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec] extension = self._preferredcodec more_opts = [] if self._preferredquality is not None: - more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality] + if int(self._preferredquality) < 10: + more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality] + else: + more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality] if self._preferredcodec == 'aac': more_opts += ['-f', 'adts'] if self._preferredcodec == 'm4a': diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 86951840d..aee444b53 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -19,7 +19,7 @@ __authors__ = ( ) __license__ = 'Public Domain' -__version__ = '2012.02.27' +__version__ = '2012.09.27' UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' UPDATE_URL_VERSION = 'https://raw.github.com/rg3/youtube-dl/master/LATEST_VERSION' @@ -186,16 +186,18 @@ def parseOpts(): general.add_option('-r', '--rate-limit', dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') general.add_option('-R', '--retries', - dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) + dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10) general.add_option('--dump-user-agent', action='store_true', dest='dump_user_agent', help='display the current browser identification', default=False) + general.add_option('--user-agent', + dest='user_agent', help='specify a custom user agent', metavar='UA') 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) + dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1) selection.add_option('--playlist-end', dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') @@ -296,8 +298,8 @@ def parseOpts(): help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default') - postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K', - help='ffmpeg/avconv audio bitrate specification, 128k by default') + postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5', + help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)') 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') @@ -351,6 +353,8 @@ def gen_extractors(): MixcloudIE(), StanfordOpenClassroomIE(), MTVIE(), + YoukuIE(), + XNXXIE(), GenericIE() ] @@ -368,6 +372,9 @@ def _real_main(): jar.load() except (IOError, OSError), err: sys.exit(u'ERROR: unable to open cookie file') + # Set user agent + if opts.user_agent is not None: + std_headers['User-Agent'] = opts.user_agent # Dump user agent if opts.dump_user_agent: @@ -444,6 +451,10 @@ def _real_main(): if opts.extractaudio: if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']: parser.error(u'invalid audio format specified') + if opts.audioquality: + opts.audioquality = opts.audioquality.strip('k').strip('K') + if not opts.audioquality.isdigit(): + parser.error(u'invalid audio quality specified') # File downloader fd = FileDownloader({ |