X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=d2d8d7b778107e0321bd7b684bc89ec19a88de0b;hb=6b5076122246f8b7b43bac232b1da9a8dbdc2411;hp=8c5b7256788f966804cfa2da57dee020f47c1fec;hpb=58ca755f4062146fbb9ce9d4383f033b8a631ed0;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 8c5b72567..d2d8d7b77 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -12,29 +12,17 @@ import time import urllib import urllib2 import email.utils +import xml.etree.ElementTree +import random +import math +from urlparse import parse_qs try: import cStringIO as StringIO except ImportError: import StringIO -# parse_qs was moved from the cgi module to the urlparse module recently. -try: - from urlparse import parse_qs -except ImportError: - from cgi import parse_qs - -try: - import lxml.etree -except ImportError: - pass # Handled below - -try: - import xml.etree.ElementTree -except ImportError: # Python<2.5: Not officially supported, but let it slip - warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.') - -from Utils import * +from utils import * class InfoExtractor(object): @@ -53,7 +41,6 @@ class InfoExtractor(object): url: Final video URL. uploader: Nickname of the video uploader. title: Literal title. - stitle: Simplified title. ext: Video filename extension. format: Video format. player_url: SWF Player URL (may be None). @@ -110,15 +97,34 @@ 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' _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' _NETRC_MACHINE = 'youtube' # Listed in order of quality - _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] - _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] + _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] + _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] _video_extensions = { '13': '3gp', '17': 'mp4', @@ -129,6 +135,7 @@ class YoutubeIE(InfoExtractor): '43': 'webm', '44': 'webm', '45': 'webm', + '46': 'webm', } _video_dimensions = { '5': '240x400', @@ -144,9 +151,14 @@ class YoutubeIE(InfoExtractor): '43': '360x640', '44': '480x854', '45': '720x1280', + '46': '1080x1920', } 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') @@ -193,9 +205,9 @@ class YoutubeIE(InfoExtractor): end = start + float(dur) start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) - caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) - caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional - srt += str(n) + '\n' + caption = unescapeHTML(caption) + caption = unescapeHTML(caption) # double cycle, intentional + srt += str(n+1) + '\n' srt += start + ' --> ' + end + '\n' srt += caption + '\n\n' return srt @@ -281,7 +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 @@ -324,6 +336,11 @@ class YoutubeIE(InfoExtractor): self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') return + # Check for "rental" videos + if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: + self._downloader.trouble(u'ERROR: "rental" videos not supported') + return + # Start extracting information self.report_information_extraction(video_id) @@ -339,10 +356,6 @@ class YoutubeIE(InfoExtractor): 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 = simplify_title(video_title) # thumbnail image if 'thumbnail_url' not in video_info: @@ -364,49 +377,48 @@ class YoutubeIE(InfoExtractor): pass # description - try: - lxml.etree - except NameError: - video_description = u'No description available.' - mobj = re.search(r'', video_webpage) - if mobj is not None: - video_description = mobj.group(1).decode('utf-8') - else: - html_parser = lxml.etree.HTMLParser(encoding='utf-8') - vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) - video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) - # TODO use another parser + video_description = get_element_by_id("eow-description", video_webpage.decode('utf8')) + if video_description: video_description = clean_html(video_description) + else: video_description = '' # closed captions video_subtitles = None if self._downloader.params.get('writesubtitles', False): - self.report_video_subtitles_download(video_id) - request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) try: - srt_list = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) - else: - srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list) - if srt_lang_list: - if self._downloader.params.get('subtitleslang', False): - srt_lang = self._downloader.params.get('subtitleslang') - elif 'en' in srt_lang_list: - srt_lang = 'en' - else: - srt_lang = srt_lang_list[0] - if not srt_lang in srt_lang_list: - self._downloader.trouble(u'WARNING: no closed captions found in the specified language') - else: - request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id)) - try: - srt_xml = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) - else: - video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) + self.report_video_subtitles_download(video_id) + request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) + 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)) + 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: + raise Trouble(u'WARNING: video has no closed captions') + if self._downloader.params.get('subtitleslang', False): + srt_lang = self._downloader.params.get('subtitleslang') + elif 'en' in srt_lang_list: + srt_lang = 'en' else: - self._downloader.trouble(u'WARNING: video has no closed captions') + srt_lang = srt_lang_list.keys()[0] + if not srt_lang in srt_lang_list: + raise Trouble(u'WARNING: no closed captions found in the specified language') + request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) + 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)) + 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]) @@ -421,7 +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 @@ -469,13 +481,13 @@ class YoutubeIE(InfoExtractor): 'uploader': video_uploader.decode('utf-8'), 'upload_date': upload_date, 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), 'thumbnail': video_thumbnail.decode('utf-8'), 'description': video_description, 'player_url': player_url, - 'subtitles': video_subtitles + 'subtitles': video_subtitles, + 'duration': video_duration }) return results @@ -545,8 +557,6 @@ class MetacafeIE(InfoExtractor): self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) return - simple_title = mobj.group(2).decode('utf-8') - # Retrieve video webpage to extract further information request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) try: @@ -592,9 +602,8 @@ class MetacafeIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') return video_title = mobj.group(1).decode('utf-8') - video_title = sanitize_title(video_title) - mobj = re.search(r'(?ms)By:\s*(.+?)<', webpage) + mobj = re.search(r'submitter=(.*?);', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -606,7 +615,6 @@ class MetacafeIE(InfoExtractor): 'uploader': video_uploader.decode('utf-8'), 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', 'player_url': None, @@ -616,7 +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): @@ -637,9 +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) @@ -653,42 +661,59 @@ class DailymotionIE(InfoExtractor): # 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'', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract title') return video_title = unescapeHTML(mobj.group('title').decode('utf-8')) - video_title = sanitize_title(video_title) - simple_title = simplify_title(video_title) - mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) + video_uploader = u'NA' + mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', 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'', 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'
([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, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', 'player_url': None, @@ -752,8 +777,6 @@ class GoogleIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') return video_title = mobj.group(1).decode('utf-8') - video_title = sanitize_title(video_title) - simple_title = simplify_title(video_title) # Extract video description mobj = re.search(r'([^<]*)', webpage) @@ -786,7 +809,6 @@ class GoogleIE(InfoExtractor): 'uploader': u'NA', 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', 'player_url': None, @@ -845,8 +867,6 @@ class PhotobucketIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') return video_title = mobj.group(1).decode('utf-8') - video_title = sanitize_title(video_title) - simple_title = simplify_title(video_title) video_uploader = mobj.group(2).decode('utf-8') @@ -856,7 +876,6 @@ class PhotobucketIE(InfoExtractor): 'uploader': video_uploader, 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', 'player_url': None, @@ -934,7 +953,6 @@ class YahooIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract video title') return video_title = mobj.group(1).decode('utf-8') - simple_title = simplify_title(video_title) mobj = re.search(r'

(.*)

', webpage) if mobj is None: @@ -992,7 +1010,7 @@ class YahooIE(InfoExtractor): self._downloader.trouble(u'ERROR: Unable to extract media URL') return video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') - video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) + video_url = unescapeHTML(video_url) return [{ 'id': video_id.decode('utf-8'), @@ -1000,7 +1018,6 @@ class YahooIE(InfoExtractor): 'uploader': video_uploader, 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'thumbnail': video_thumbnail.decode('utf-8'), 'description': video_description, @@ -1013,7 +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): @@ -1060,7 +1077,6 @@ class VimeoIE(InfoExtractor): # Extract title video_title = config["video"]["title"] - simple_title = simplify_title(video_title) # Extract uploader video_uploader = config["video"]["owner"]["name"] @@ -1069,18 +1085,9 @@ class VimeoIE(InfoExtractor): video_thumbnail = config["video"]["thumbnail"] # Extract video description - try: - lxml.etree - except NameError: - video_description = u'No description available.' - mobj = re.search(r'', webpage, re.MULTILINE) - if mobj is not None: - video_description = mobj.group(1) - else: - html_parser = lxml.etree.HTMLParser() - vwebpage_doc = lxml.etree.parse(StringIO.StringIO(webpage), html_parser) - video_description = u''.join(vwebpage_doc.xpath('id("description")//text()')).strip() - # TODO use another parser + video_description = get_element_by_id("description", webpage.decode('utf8')) + if video_description: video_description = clean_html(video_description) + else: video_description = '' # Extract upload date video_upload_date = u'NA' @@ -1093,21 +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, @@ -1115,7 +1133,6 @@ class VimeoIE(InfoExtractor): 'uploader': video_uploader, 'upload_date': video_upload_date, 'title': video_title, - 'stitle': simple_title, 'ext': video_extension, 'thumbnail': video_thumbnail, 'description': video_description, @@ -1158,16 +1175,16 @@ class GenericIE(InfoExtractor): """ def redirect_request(self, req, fp, code, msg, headers, newurl): if code in (301, 302, 303, 307): - newurl = newurl.replace(' ', '%20') - newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) - return HeadRequest(newurl, - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True) + newurl = newurl.replace(' ', '%20') + newheaders = dict((k,v) for k,v in req.headers.items() + if k.lower() not in ("content-length", "content-type")) + return HeadRequest(newurl, + headers=newheaders, + origin_req_host=req.get_origin_req_host(), + unverifiable=True) else: - raise urllib2.HTTPError(req.get_full_url(), code, msg, headers, fp) - + raise urllib2.HTTPError(req.get_full_url(), code, msg, headers, fp) + class HTTPMethodFallback(urllib2.BaseHandler): """ Fallback to GET if HEAD is not allowed (405 HTTP error) @@ -1177,17 +1194,17 @@ class GenericIE(InfoExtractor): fp.close() newheaders = dict((k,v) for k,v in req.headers.items() - if k.lower() not in ("content-length", "content-type")) + if k.lower() not in ("content-length", "content-type")) return self.parent.open(urllib2.Request(req.get_full_url(), - headers=newheaders, - origin_req_host=req.get_origin_req_host(), - unverifiable=True)) + headers=newheaders, + origin_req_host=req.get_origin_req_host(), + unverifiable=True)) # Build our opener opener = urllib2.OpenerDirector() for handler in [urllib2.HTTPHandler, urllib2.HTTPDefaultErrorHandler, - HTTPMethodFallback, HEADRedirectHandler, - urllib2.HTTPErrorProcessor, urllib2.HTTPSHandler]: + HTTPMethodFallback, HEADRedirectHandler, + urllib2.HTTPErrorProcessor, urllib2.HTTPSHandler]: opener.add_handler(handler()) response = opener.open(HeadRequest(url)) @@ -1250,8 +1267,6 @@ class GenericIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') return video_title = mobj.group(1).decode('utf-8') - video_title = sanitize_title(video_title) - simple_title = simplify_title(video_title) # video uploader is domain name mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) @@ -1266,7 +1281,6 @@ class GenericIE(InfoExtractor): 'uploader': video_uploader, 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': u'NA', 'player_url': None, @@ -1284,7 +1298,7 @@ class YoutubeSearchIE(InfoExtractor): InfoExtractor.__init__(self, downloader) def report_download_page(self, query, pagenum): - """Report attempt to download playlist page with given number.""" + """Report attempt to download search page with given number.""" query = query.decode(preferredencoding()) self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) @@ -1518,10 +1532,10 @@ 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&' - _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' + _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s' + _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' IE_NAME = u'youtube:playlist' def __init__(self, downloader=None): @@ -1588,6 +1602,56 @@ 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_-]+)(?:/.*)?$" + _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' + _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO + IE_NAME = u'youtube:channel' + + def report_download_page(self, channel_id, pagenum): + """Report attempt to download channel page with given number.""" + self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum)) + + def _real_extract(self, url): + # Extract channel id + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + # Download channel pages + channel_id = mobj.group(1) + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(channel_id, pagenum) + url = self._TEMPLATE_URL % (channel_id, pagenum) + request = urllib2.Request(url) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + ids_in_page = [] + for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + video_ids.extend(ids_in_page) + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + break + pagenum = pagenum + 1 + + for id in video_ids: + self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) + return + + class YoutubeUserIE(InfoExtractor): """Information Extractor for YouTube users.""" @@ -1671,6 +1735,98 @@ class YoutubeUserIE(InfoExtractor): self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) +class BlipTVUserIE(InfoExtractor): + """Information Extractor for blip.tv users.""" + + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' + _PAGE_SIZE = 12 + IE_NAME = u'blip.tv:user' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_page(self, username, pagenum): + """Report attempt to download user page.""" + self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % + (self.IE_NAME, username, pagenum)) + + def _real_extract(self, url): + # Extract username + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + username = mobj.group(1) + + page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' + + request = urllib2.Request(url) + + try: + page = urllib2.urlopen(request).read().decode('utf-8') + 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)) + return + + + # Download video ids using BlipTV Ajax calls. Result size per + # query is limited (currently to 12 videos) so we need to query + # page by page until there are no video ids - it means we got + # all of them. + + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(username, pagenum) + + request = urllib2.Request( page_base + "&page=" + str(pagenum) ) + + try: + page = urllib2.urlopen(request).read().decode('utf-8') + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + ids_in_page = [] + + for mobj in re.finditer(r'href="/([^"]+)"', page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(unescapeHTML(mobj.group(1))) + + video_ids.extend(ids_in_page) + + # A little optimization - if current page is not + # "full", ie. does not contain PAGE_SIZE video ids then + # we can assume that this page is the last one - there + # are no more ids on further pages - no need to query + # again. + + if len(ids_in_page) < self._PAGE_SIZE: + break + + pagenum += 1 + + all_ids_count = len(video_ids) + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] + + self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % + (self.IE_NAME, username, all_ids_count, len(video_ids))) + + for video_id in video_ids: + self._downloader.download([u'http://blip.tv/'+video_id]) + + class DepositFilesIE(InfoExtractor): """Information extractor for depositfiles.com""" @@ -1731,7 +1887,6 @@ class DepositFilesIE(InfoExtractor): 'uploader': u'NA', 'upload_date': u'NA', 'title': file_title, - 'stitle': file_title, 'ext': file_extension.decode('utf-8'), 'format': u'NA', 'player_url': None, @@ -1876,9 +2031,6 @@ class FacebookIE(InfoExtractor): return video_title = video_info['title'] video_title = video_title.decode('utf-8') - video_title = sanitize_title(video_title) - - simple_title = simplify_title(video_title) # thumbnail image if 'thumbnail' not in video_info: @@ -1939,7 +2091,6 @@ class FacebookIE(InfoExtractor): 'uploader': video_uploader.decode('utf-8'), 'upload_date': upload_date, 'title': video_title, - 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), 'thumbnail': video_thumbnail.decode('utf-8'), @@ -1974,7 +2125,7 @@ class BlipTVIE(InfoExtractor): else: cchar = '?' json_url = url + cchar + 'skin=json&version=2&no_wrap=1' - request = urllib2.Request(json_url) + request = urllib2.Request(json_url.encode('utf-8')) self.report_extraction(mobj.group(1)) info = None try: @@ -1989,7 +2140,6 @@ class BlipTVIE(InfoExtractor): 'id': title, 'url': url, 'title': title, - 'stitle': simplify_title(title), 'ext': ext, 'urlhandle': urlh } @@ -2009,21 +2159,20 @@ class BlipTVIE(InfoExtractor): data = json_data['Post'] else: data = json_data - + upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') video_url = data['media']['url'] umobj = re.match(self._URL_EXT, video_url) if umobj is None: raise ValueError('Can not determine filename extension') ext = umobj.group(1) - + info = { 'id': data['item_id'], 'url': video_url, 'uploader': data['display_name'], 'upload_date': upload_date, 'title': data['title'], - 'stitle': simplify_title(data['title']), 'ext': ext, 'format': data['media']['mimeType'], 'thumbnail': data['thumbnailUrl'], @@ -2034,6 +2183,7 @@ class BlipTVIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) return + std_headers['User-Agent'] = 'iTunes/10.6.1' return [info] @@ -2085,9 +2235,6 @@ class MyVideoIE(InfoExtractor): return video_title = mobj.group(1) - video_title = sanitize_title(video_title) - - simple_title = simplify_title(video_title) return [{ 'id': video_id, @@ -2095,7 +2242,6 @@ class MyVideoIE(InfoExtractor): 'uploader': u'NA', 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': u'flv', 'format': u'NA', 'player_url': None, @@ -2109,7 +2255,7 @@ class ComedyCentralIE(InfoExtractor): def report_extraction(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) - + def report_config_download(self, episode_id): self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) @@ -2222,7 +2368,6 @@ class ComedyCentralIE(InfoExtractor): 'uploader': showId, 'upload_date': officialDate, 'title': effTitle, - 'stitle': simplify_title(effTitle), 'ext': 'mp4', 'format': format, 'thumbnail': None, @@ -2248,8 +2393,6 @@ class EscapistIE(InfoExtractor): self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) def _real_extract(self, url): - htmlParser = HTMLParser.HTMLParser() - mobj = re.match(self._VALID_URL, url) if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) @@ -2259,17 +2402,20 @@ class EscapistIE(InfoExtractor): self.report_extraction(showName) try: - webPage = urllib2.urlopen(url).read() + webPage = urllib2.urlopen(url) + webPageBytes = webPage.read() + m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) + webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) return descMatch = re.search('([^<]+)', coursepage) if m: @@ -2822,8 +2951,6 @@ class StanfordOpenClassroomIE(InfoExtractor): return results else: # Root page - unescapeHTML = HTMLParser.HTMLParser().unescape - info = { 'id': 'Stanford OpenClassroom', 'type': 'playlist', @@ -2838,7 +2965,6 @@ class StanfordOpenClassroomIE(InfoExtractor): return info['title'] = info['id'] - info['stitle'] = simplify_title(info['title']) links = orderedSet(re.findall('', rootpage)) info['list'] = [ @@ -2937,9 +3063,319 @@ class MTVIE(InfoExtractor): 'url': video_url, 'uploader': performer, 'title': video_title, - 'stitle': simplify_title(video_title), 'ext': ext, 'format': format, } 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/(?:\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' % 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' % 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, + }]