From: Filippo Valsorda Date: Tue, 9 Oct 2012 08:48:49 +0000 (+0200) Subject: Merge PR #422 from 'kevinamadeus/master' X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=fd873c69a42eb596290ec53e53ac802298128095;hp=-c;p=youtube-dl Merge PR #422 from 'kevinamadeus/master' Add InfoExtractor for Google Plus video (with fixes) --- fd873c69a42eb596290ec53e53ac802298128095 diff --combined youtube_dl/InfoExtractors.py index 9e5ea7c61,ddb9fbca1..f97611cb9 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@@ -13,8 -13,6 +13,8 @@@ import urlli import urllib2 import email.utils import xml.etree.ElementTree +import random +import math from urlparse import parse_qs try: @@@ -97,25 -95,7 +97,25 @@@ 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?://)? # http(s):// (optional) + (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| + tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains + (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs + (?: # the various things that can precede the ID: + (?:(?:v|embed|e)/) # v/ or embed/ or e/ + |(?: # or the v= param in all its forms + (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:\?|\#!?) # the params delimiter ? or # or #! + (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) + v= + ) + )? # optional -> youtube.com/xxxx is OK + )? # all until now is optional -> you can pass the naked ID + ([0-9A-Za-z_-]+) # here is it! the YouTube video ID + (?(1).+)? # if we found the ID, everything can follow + $""" _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' @@@ -154,10 -134,6 +154,10 @@@ } IE_NAME = u'youtube' + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url, re.VERBOSE) is not None + def report_lang(self): """Report attempt to set language.""" self._downloader.to_screen(u'[youtube] Setting language') @@@ -292,7 -268,7 +292,7 @@@ url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/') # Extract video id from URL - mobj = re.match(self._VALID_URL, url) + mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return @@@ -426,7 -402,7 +426,7 @@@ 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 @@@ -616,7 -592,7 +616,7 @@@ class MetacafeIE(InfoExtractor) class DailymotionIE(InfoExtractor): """Information Extractor for Dailymotion""" - _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' + _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' IE_NAME = u'dailymotion' def __init__(self, downloader=None): @@@ -637,9 -613,9 +637,9 @@@ self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - video_id = mobj.group(1) + video_id = mobj.group(1).split('_')[0].split('?')[0] - video_extension = 'flv' + video_extension = 'mp4' # Retrieve video webpage to extract further information request = urllib2.Request(url) @@@ -653,23 -629,20 +653,23 @@@ # Extract URL, uploader and title from webpage self.report_extraction(video_id) - mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) + mobj = re.search(r'\s*var flashvars = (.*)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - sequence = urllib.unquote(mobj.group(1)) - mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) + flashvars = urllib.unquote(mobj.group(1)) + if 'hqURL' in flashvars: max_quality = 'hqURL' + elif 'sdURL' in flashvars: max_quality = 'sdURL' + else: max_quality = 'ldURL' + mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) + if mobj is None: + mobj = re.search(r'"video_url":"(.*?)",', flashvars) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') - - # if needed add http://www.dailymotion.com/ if relative URL + video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/') - video_url = mediaURL + # TODO: support choosing qualities mobj = re.search(r'', webpage) if mobj is None: @@@ -683,16 -656,11 +683,16 @@@ return video_uploader = mobj.group(1) + video_upload_date = u'NA' + mobj = re.search(r'
([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage) + if mobj is not None: + video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) + return [{ 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), - 'upload_date': u'NA', + 'upload_date': video_upload_date, 'title': video_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', @@@ -1503,7 -1471,7 +1503,7 @@@ 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' @@@ -2988,189 -2956,126 +2988,313 @@@ class MTVIE(InfoExtractor) return [info] + +class YoukuIE(InfoExtractor): + + _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P[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'(.*?)\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] ++ ++ + class GooglePlusIE(InfoExtractor): + """Information extractor for plus.google.com.""" + - _VALID_URL = r'(?:https://)?plus\.google\.com/(\d+)/posts/(\w+)' ++ _VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)' + IE_NAME = u'plus.google' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8')) + + def report_date(self, upload_date): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) + + def report_uploader(self, uploader): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8')) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8')) + + def report_extract_vid_page(self, video_page): + """Report information extraction.""" + self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8')) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + post_url = mobj.group(0) + video_id = mobj.group(2) + + video_extension = 'flv' + + # Step 1, Retrieve post webpage to extract further information ++ self.report_extract_entry(post_url) + request = urllib2.Request(post_url) + try: - self.report_extract_entry(post_url) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % str(err)) + return + + # Extract update date + upload_date = u'NA' + pattern = 'title="Timestamp">(.*?)</a>' + mobj = re.search(pattern, webpage) + if mobj: + upload_date = mobj.group(1) - """Convert timestring to a format suitable for filename""" ++ # Convert timestring to a format suitable for filename + upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") + upload_date = upload_date.strftime('%Y%m%d') + self.report_date(upload_date) + + # Extract uploader + uploader = u'NA' + pattern = r'rel\="author".*?>(.*?)</a>' + mobj = re.search(pattern, webpage) + if mobj: + uploader = mobj.group(1) + self.report_uploader(uploader) + + # Extract title - """Get the first line for title""" ++ # Get the first line for title + video_title = u'NA' - pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\s<"]' ++ pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]' + mobj = re.search(pattern, webpage) + if mobj: + video_title = mobj.group(1) + self.report_title(video_title) + + # Step 2, Stimulate clicking the image box to launch video + pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]' + mobj = re.search(pattern, webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video page URL') + + video_page = mobj.group(1) + request = urllib2.Request(video_page) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + self.report_extract_vid_page(video_page) + + + # Extract video links on video page + """Extract video links of all sizes""" + pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' + mobj = re.findall(pattern, webpage) - if mobj is None: ++ if len(mobj) == 0: + self._downloader.trouble(u'ERROR: unable to extract video links') + + # Sort in resolution + links = sorted(mobj) + + # Choose the lowest of the sort, i.e. highest resolution + video_url = links[-1] + # Only get the url. The resolution part in the tuple has no use anymore + video_url = video_url[-1] + # Treat escaped \u0026 style hex - video_url = unicode(video_url, "unicode_escape").encode("utf8") ++ video_url = unicode(video_url, "unicode_escape") + + + return [{ + 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), ++ 'url': video_url, + 'uploader': uploader.decode('utf-8'), + 'upload_date': upload_date.decode('utf-8'), + 'title': video_title.decode('utf-8'), + 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }] - diff --combined youtube_dl/__init__.py index b21416daf,fc8101f82..15a3ec4cf --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@@ -19,7 -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' @@@ -186,18 -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)') @@@ -269,7 -267,7 +269,7 @@@ action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False) filesystem.add_option('-o', '--output', - dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.') + dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout.') filesystem.add_option('-a', '--batch-file', dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') filesystem.add_option('-w', '--no-overwrites', @@@ -298,8 -296,8 +298,8 @@@ 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') @@@ -353,8 -351,7 +353,9 @@@ def gen_extractors() MixcloudIE(), StanfordOpenClassroomIE(), MTVIE(), + YoukuIE(), + XNXXIE(), + GooglePlusIE(), GenericIE() ] @@@ -372,9 -369,6 +373,9 @@@ 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: @@@ -451,10 -445,6 +452,10 @@@ 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({