diff options
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
-rw-r--r-- | youtube_dl/InfoExtractors.py | 928 |
1 files changed, 695 insertions, 233 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 82459e7a8..cea30dad8 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 +97,26 @@ 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 + (?:.*?\#/)? # handle anchor (#/) redirect urls + (?!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' @@ -134,6 +155,10 @@ class YoutubeIE(InfoExtractor): } 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') @@ -188,9 +213,9 @@ class YoutubeIE(InfoExtractor): return srt def _print_formats(self, formats): - print 'Available formats:' + print('Available formats:') for x in formats: - print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')) + print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))) def _real_initialize(self): if self._downloader is None: @@ -213,7 +238,7 @@ class YoutubeIE(InfoExtractor): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError), err: - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) return # Set language @@ -222,7 +247,7 @@ class YoutubeIE(InfoExtractor): self.report_lang() urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) return # No authentication to be performed @@ -245,7 +270,7 @@ class YoutubeIE(InfoExtractor): self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') return except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) return # Confirm age @@ -258,7 +283,7 @@ class YoutubeIE(InfoExtractor): self.report_age_confirmation() age_results = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) return def _real_extract(self, url): @@ -268,7 +293,7 @@ class YoutubeIE(InfoExtractor): 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 @@ -280,7 +305,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return # Attempt to extract SWF player URL @@ -302,7 +327,7 @@ class YoutubeIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) return if 'token' not in video_info: if 'reason' in video_info: @@ -365,7 +390,7 @@ class YoutubeIE(InfoExtractor): try: srt_list = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) + raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) if not srt_lang_list: @@ -382,13 +407,19 @@ class YoutubeIE(InfoExtractor): try: srt_xml = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) + raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) if not srt_xml: raise Trouble(u'WARNING: unable to download video subtitles') video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) except Trouble as trouble: self._downloader.trouble(trouble[0]) + if 'length_seconds' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video duration') + video_duration = '' + else: + video_duration = urllib.unquote_plus(video_info['length_seconds'][0]) + # token video_token = urllib.unquote_plus(video_info['token'][0]) @@ -402,7 +433,7 @@ 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 @@ -455,7 +486,8 @@ class YoutubeIE(InfoExtractor): 'thumbnail': video_thumbnail.decode('utf-8'), 'description': video_description, 'player_url': player_url, - 'subtitles': video_subtitles + 'subtitles': video_subtitles, + 'duration': video_duration }) return results @@ -494,7 +526,7 @@ class MetacafeIE(InfoExtractor): self.report_disclaimer() disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) return # Confirm age @@ -507,7 +539,7 @@ class MetacafeIE(InfoExtractor): self.report_age_confirmation() disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err)) return def _real_extract(self, url): @@ -531,7 +563,7 @@ class MetacafeIE(InfoExtractor): self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) return # Extract URL, uploader and title from webpage @@ -571,7 +603,7 @@ class MetacafeIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') - mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage) + mobj = re.search(r'submitter=(.*?);', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -592,7 +624,7 @@ 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): @@ -613,9 +645,9 @@ class DailymotionIE(InfoExtractor): 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) @@ -624,25 +656,34 @@ class DailymotionIE(InfoExtractor): self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) return # 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)) + + for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: + if key in flashvars: + max_quality = key + self._downloader.to_screen(u'[dailymotion] Using %s' % key) + break + else: + self._downloader.trouble(u'ERROR: unable to extract video URL') + return + + mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') + self._downloader.trouble(u'ERROR: unable to extract video 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'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) if mobj is None: @@ -650,17 +691,28 @@ class DailymotionIE(InfoExtractor): return video_title = unescapeHTML(mobj.group('title').decode('utf-8')) - mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage) + video_uploader = u'NA' + mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = mobj.group(1) + # lookin for official user + mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage) + if mobj_official is None: + self._downloader.trouble(u'WARNING: unable to extract uploader nickname') + else: + video_uploader = mobj_official.group(1) + else: + video_uploader = mobj.group(1) + + video_upload_date = u'NA' + mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', 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', @@ -702,7 +754,7 @@ class GoogleIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract URL, uploader, and title from webpage @@ -741,7 +793,7 @@ class GoogleIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) if mobj is None: @@ -797,7 +849,7 @@ class PhotobucketIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract URL, uploader, and title from webpage @@ -867,7 +919,7 @@ class YahooIE(InfoExtractor): 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) @@ -891,7 +943,7 @@ class YahooIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract uploader and title from webpage @@ -949,7 +1001,7 @@ class YahooIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Extract media URL from playlist XML @@ -978,7 +1030,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' + _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)' IE_NAME = u'vimeo' def __init__(self, downloader=None): @@ -1007,7 +1059,7 @@ class VimeoIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return # Now we begin extracting as much information as we can from what we @@ -1048,21 +1100,32 @@ class VimeoIE(InfoExtractor): timestamp = config['request']['timestamp'] # Vimeo specific: extract video codec and quality information + # First consider quality, then codecs, then take everything # TODO bind to format param codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] - for codec in codecs: - if codec[0] in config["video"]["files"]: - video_codec = codec[0] - video_extension = codec[1] - if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd' - else: quality = 'sd' + files = { 'hd': [], 'sd': [], 'other': []} + for codec_name, codec_extension in codecs: + if codec_name in config["video"]["files"]: + if 'hd' in config["video"]["files"][codec_name]: + files['hd'].append((codec_name, codec_extension, 'hd')) + elif 'sd' in config["video"]["files"][codec_name]: + files['sd'].append((codec_name, codec_extension, 'sd')) + else: + files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) + + for quality in ('hd', 'sd', 'other'): + if len(files[quality]) > 0: + video_quality = files[quality][0][2] + video_codec = files[quality][0][0] + video_extension = files[quality][0][1] + self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) break else: self._downloader.trouble(u'ERROR: no known codec found') return video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ - %(video_id, sig, timestamp, quality, video_codec.upper()) + %(video_id, sig, timestamp, video_quality, video_codec.upper()) return [{ 'id': video_id, @@ -1078,158 +1141,140 @@ class VimeoIE(InfoExtractor): class ArteTvIE(InfoExtractor): - """arte.tv information extractor.""" - - _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' - _LIVE_URL = r'index-[0-9]+\.html$' - - IE_NAME = u'arte.tv' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) - - def fetch_webpage(self, url): - self._downloader.increment_downloads() - request = urllib2.Request(url) - try: - self.report_download_webpage(url) - 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 - except ValueError, err: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - return webpage - - def grep_webpage(self, url, regex, regexFlags, matchTuples): - page = self.fetch_webpage(url) - mobj = re.search(regex, page, regexFlags) - info = {} - - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - for (i, key, err) in matchTuples: - if mobj.group(i) is None: - self._downloader.trouble(err) - return - else: - info[key] = mobj.group(i) - - return info - - def extractLiveStream(self, url): - - video_lang = url.split('/')[-4] - - info = self.grep_webpage( - url, - r'src="(.*?/videothek_js.*?\.js)', - 0, - [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) - ] - ) - - http_host = url.split('/')[2] - next_url = 'http://%s%s' % (http_host, urllib.unquote(info.get('url'))) - - info = self.grep_webpage( - next_url, - r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + - '(http://.*?\.swf).*?' + - '(rtmp://.*?)\'', - re.DOTALL, - [ - (1, 'path', u'ERROR: could not extract video path: %s' % url), - (2, 'player', u'ERROR: could not extract video player: %s' % url), - (3, 'url', u'ERROR: could not extract video url: %s' % url) - ] - ) - - video_url = u'%s/%s' % (info.get('url'), info.get('path')) - - print u'rtmpdump --swfVfy \'%s\' --rtmp \'%s\' --live -o arte-live.mp4' % (info.get('player'), video_url) - - def extractPlus7Stream(self, url): - - video_lang = url.split('/')[-3] - - info = self.grep_webpage( - url, - r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', - 0, - [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) - ] - ) - - next_url = urllib.unquote(info.get('url')) - - info = self.grep_webpage( - next_url, - r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, - 0, - [ - (1, 'url', u'ERROR: Could not find <video> tag: %s' % url) - ] - ) - - next_url = urllib.unquote(info.get('url')) - - info = self.grep_webpage( - next_url, - r'<video id="(.*?)".*?>.*?' + - '<name>(.*?)</name>.*?' + - '<dateVideo>(.*?)</dateVideo>.*?' + - '<url quality="hd">(.*?)</url>', - re.DOTALL, - [ - (1, 'id', u'ERROR: could not extract video id: %s' % url), - (2, 'title', u'ERROR: could not extract video title: %s' % url), - (3, 'date', u'ERROR: could not extract video date: %s' % url), - (4, 'url', u'ERROR: could not extract video url: %s' % url) - ] - ) - - return { - 'id': info.get('id'), - 'url': urllib.unquote(info.get('url')), - 'uploader': u'arte.tv', - 'upload_date': info.get('date'), - 'title': info.get('title'), - 'ext': u'mp4', - 'format': u'NA', - 'player_url': None, - } - - def _real_extract(self, url): - - video_id = url.split('/')[-1] - - self.report_extraction(video_id) - - if re.search(self._LIVE_URL, video_id) is not None: - self.extractLiveStream(url) - return - else: - info = self.extractPlus7Stream(url) - - try: - # Process video information - self._downloader.process_info(info) - except UnavailableVideoError, err: - self._downloader.trouble(u'\nERROR: unable to download video') + """arte.tv information extractor.""" + + _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' + _LIVE_URL = r'index-[0-9]+\.html$' + + IE_NAME = u'arte.tv' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) + + def fetch_webpage(self, url): + self._downloader.increment_downloads() + request = urllib2.Request(url) + try: + self.report_download_webpage(url) + 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 + except ValueError, err: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + return webpage + + def grep_webpage(self, url, regex, regexFlags, matchTuples): + page = self.fetch_webpage(url) + mobj = re.search(regex, page, regexFlags) + info = {} + + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + for (i, key, err) in matchTuples: + if mobj.group(i) is None: + self._downloader.trouble(err) + return + else: + info[key] = mobj.group(i) + + return info + + def extractLiveStream(self, url): + video_lang = url.split('/')[-4] + info = self.grep_webpage( + url, + r'src="(.*?/videothek_js.*?\.js)', + 0, + [ + (1, 'url', u'ERROR: Invalid URL: %s' % url) + ] + ) + http_host = url.split('/')[2] + next_url = 'http://%s%s' % (http_host, urllib.unquote(info.get('url'))) + info = self.grep_webpage( + next_url, + r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + + '(http://.*?\.swf).*?' + + '(rtmp://.*?)\'', + re.DOTALL, + [ + (1, 'path', u'ERROR: could not extract video path: %s' % url), + (2, 'player', u'ERROR: could not extract video player: %s' % url), + (3, 'url', u'ERROR: could not extract video url: %s' % url) + ] + ) + video_url = u'%s/%s' % (info.get('url'), info.get('path')) + + def extractPlus7Stream(self, url): + video_lang = url.split('/')[-3] + info = self.grep_webpage( + url, + r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', + 0, + [ + (1, 'url', u'ERROR: Invalid URL: %s' % url) + ] + ) + next_url = urllib.unquote(info.get('url')) + info = self.grep_webpage( + next_url, + r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang, + 0, + [ + (1, 'url', u'ERROR: Could not find <video> tag: %s' % url) + ] + ) + next_url = urllib.unquote(info.get('url')) + + info = self.grep_webpage( + next_url, + r'<video id="(.*?)".*?>.*?' + + '<name>(.*?)</name>.*?' + + '<dateVideo>(.*?)</dateVideo>.*?' + + '<url quality="hd">(.*?)</url>', + re.DOTALL, + [ + (1, 'id', u'ERROR: could not extract video id: %s' % url), + (2, 'title', u'ERROR: could not extract video title: %s' % url), + (3, 'date', u'ERROR: could not extract video date: %s' % url), + (4, 'url', u'ERROR: could not extract video url: %s' % url) + ] + ) + + return { + 'id': info.get('id'), + 'url': urllib.unquote(info.get('url')), + 'uploader': u'arte.tv', + 'upload_date': info.get('date'), + 'title': info.get('title'), + 'ext': u'mp4', + 'format': u'NA', + 'player_url': None, + } + + def _real_extract(self, url): + video_id = url.split('/')[-1] + self.report_extraction(video_id) + + if re.search(self._LIVE_URL, video_id) is not None: + self.extractLiveStream(url) + return + else: + info = self.extractPlus7Stream(url) + + return [info] class GenericIE(InfoExtractor): @@ -1317,7 +1362,7 @@ class GenericIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return except ValueError, err: # since this is the last-resort InfoExtractor, if @@ -1438,7 +1483,7 @@ class YoutubeSearchIE(InfoExtractor): try: data = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err)) return api_response = json.loads(data)['data'] @@ -1515,7 +1560,7 @@ class GoogleSearchIE(InfoExtractor): try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1598,7 +1643,7 @@ class YahooSearchIE(InfoExtractor): try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1624,9 +1669,9 @@ class YahooSearchIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _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_-]+))?.*' + _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|EC)?|PL|EC)([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' @@ -1668,7 +1713,7 @@ class YoutubePlaylistIE(InfoExtractor): try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1694,6 +1739,56 @@ class YoutubePlaylistIE(InfoExtractor): return +class YoutubeChannelIE(InfoExtractor): + """Information Extractor for YouTube channels.""" + + _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" + _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' + _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO + IE_NAME = u'youtube:channel' + + def report_download_page(self, channel_id, pagenum): + """Report attempt to download channel page with given number.""" + self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) + + def _real_extract(self, url): + # Extract channel id + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + # Download channel pages + channel_id = mobj.group(1) + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(channel_id, pagenum) + url = self._TEMPLATE_URL % (channel_id, pagenum) + request = urllib2.Request(url) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) + return + + # Extract video identifiers + ids_in_page = [] + for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + video_ids.extend(ids_in_page) + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + break + pagenum = pagenum + 1 + + for id in video_ids: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) + return + + class YoutubeUserIE(InfoExtractor): """Information Extractor for YouTube users.""" @@ -1738,7 +1833,7 @@ class YoutubeUserIE(InfoExtractor): try: page = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return # Extract video identifiers @@ -1810,7 +1905,7 @@ class BlipTVUserIE(InfoExtractor): mobj = re.search(r'data-users-id="([^"]+)"', page) page_base = page_base % mobj.group(1) except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return @@ -1898,7 +1993,7 @@ class DepositFilesIE(InfoExtractor): self.report_download_webpage(file_id) webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err)) return # Search for the real file URL @@ -2015,7 +2110,7 @@ class FacebookIE(InfoExtractor): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError), err: - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) return if useremail is None: @@ -2035,7 +2130,7 @@ class FacebookIE(InfoExtractor): self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') return except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) return def _real_extract(self, url): @@ -2052,7 +2147,7 @@ class FacebookIE(InfoExtractor): page = urllib2.urlopen(request) video_webpage = page.read() 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 webpage: %s' % compat_str(err)) return # Start extracting information @@ -2186,13 +2281,13 @@ class BlipTVIE(InfoExtractor): 'urlhandle': urlh } except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) return if info is None: # Regular URL try: json_code = urlh.read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err)) return try: @@ -2260,7 +2355,7 @@ class MyVideoIE(InfoExtractor): self.report_download_webpage(video_id) 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)) + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) return self.report_extraction(video_id) @@ -2295,6 +2390,25 @@ class ComedyCentralIE(InfoExtractor): _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' + _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] + + _video_extensions = { + '3500': 'mp4', + '2200': 'mp4', + '1700': 'mp4', + '1200': 'mp4', + '750': 'mp4', + '400': 'mp4', + } + _video_dimensions = { + '3500': '1280x720', + '2200': '960x540', + '1700': '768x432', + '1200': '640x360', + '750': '512x288', + '400': '384x216', + } + def report_extraction(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) @@ -2307,6 +2421,13 @@ class ComedyCentralIE(InfoExtractor): def report_player_url(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) + + def _print_formats(self, formats): + print('Available formats:') + for x in formats: + print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) + + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -2347,10 +2468,19 @@ class ComedyCentralIE(InfoExtractor): epTitle = mobj.group('episode') mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html) + if len(mMovieParams) == 0: - self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) - return + # The Colbert Report embeds the information in a without + # a URL prefix; so extract the alternate reference + # and then add the URL prefix manually. + altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html) + if len(altMovieParams) == 0: + self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) + return + else: + mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] + playerUrl_raw = mMovieParams[0][0] self.report_player_url(epTitle) try: @@ -2399,10 +2529,31 @@ class ComedyCentralIE(InfoExtractor): if len(turls) == 0: self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') continue + + if self._downloader.params.get('listformats', None): + self._print_formats([i[0] for i in turls]) + return # For now, just pick the highest bitrate format,video_url = turls[-1] + # Get the format arg from the arg stream + req_format = self._downloader.params.get('format', None) + + # Select format if we can find one + for f,v in turls: + if f == req_format: + format, video_url = f, v + break + + # Patch to download from alternative CDN, which does not + # break on current RTMPDump builds + broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/" + better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/" + + if video_url.startswith(broken_cdn): + video_url = video_url.replace(broken_cdn, better_cdn) + effTitle = showId + u'-' + epTitle info = { 'id': shortMediaId, @@ -2414,7 +2565,7 @@ class ComedyCentralIE(InfoExtractor): 'format': format, 'thumbnail': None, 'description': officialTitle, - 'player_url': playerUrl + 'player_url': None #playerUrl } results.append(info) @@ -2522,7 +2673,7 @@ class CollegeHumorIE(InfoExtractor): try: 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage) @@ -2541,7 +2692,7 @@ class CollegeHumorIE(InfoExtractor): try: metaXml = urllib2.urlopen(xmlUrl).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) return mdoc = xml.etree.ElementTree.fromstring(metaXml) @@ -2587,7 +2738,7 @@ class XVideosIE(InfoExtractor): try: 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return self.report_extraction(video_id) @@ -2673,7 +2824,7 @@ class SoundcloudIE(InfoExtractor): try: 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return self.report_extraction('%s/%s' % (uploader, slug_title)) @@ -2700,7 +2851,7 @@ class SoundcloudIE(InfoExtractor): mobj = re.search('track-description-value"><p>(.*?)</p>', webpage) if mobj: description = mobj.group(1) - + # upload date upload_date = None mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage) @@ -2708,7 +2859,7 @@ class SoundcloudIE(InfoExtractor): try: upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') except Exception, e: - self._downloader.to_stderr(str(e)) + self._downloader.to_stderr(compat_str(e)) # for soundcloud, a request to a cross domain is required for cookies request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) @@ -2752,7 +2903,7 @@ class InfoQIE(InfoExtractor): try: 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return self.report_extraction(url) @@ -2838,15 +2989,15 @@ class MixcloudIE(InfoExtractor): return None def _print_formats(self, formats): - print 'Available formats:' + print('Available formats:') for fmt in formats.keys(): for b in formats[fmt]: try: ext = formats[fmt][b][0] - print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]) + print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) except TypeError: # we have no bitrate info ext = formats[fmt][0] - print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]) + print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) break def _real_extract(self, url): @@ -2866,7 +3017,7 @@ class MixcloudIE(InfoExtractor): self.report_download_json(file_url) jsonData = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err)) + self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err)) return # parse JSON @@ -3050,7 +3201,7 @@ class MTVIE(InfoExtractor): try: 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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) @@ -3083,7 +3234,7 @@ class MTVIE(InfoExtractor): try: metadataXml = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err)) + self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err)) return mdoc = xml.etree.ElementTree.fromstring(metadataXml) @@ -3110,3 +3261,314 @@ 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' % compat_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] + + +class GooglePlusIE(InfoExtractor): + """Information extractor for plus.google.com.""" + + _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: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_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 + 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 + video_title = u'NA' + 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' % compat_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 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") + + + return [{ + 'id': video_id.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, + }] |