X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2FInfoExtractors.py;h=d2b9fbedcedcc91a122cdd23837efb89a198f6be;hb=be8786a6a46f43be54daa85d6c70091948175f34;hp=d77154dcb4902422f9297c6b0d0fbf90168f5975;hpb=9e6dd238761e6628d7bd0b6bdb7a997604de3757;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d77154dcb..d2b9fbedc 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -12,23 +12,14 @@ import time import urllib import urllib2 import email.utils +import xml.etree.ElementTree +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 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 * @@ -48,7 +39,6 @@ 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). @@ -112,8 +102,8 @@ class YoutubeIE(InfoExtractor): _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', @@ -124,6 +114,7 @@ class YoutubeIE(InfoExtractor): '43': 'webm', '44': 'webm', '45': 'webm', + '46': 'webm', } _video_dimensions = { '5': '240x400', @@ -139,6 +130,7 @@ class YoutubeIE(InfoExtractor): '43': '360x640', '44': '480x854', '45': '720x1280', + '46': '1080x1920', } IE_NAME = u'youtube' @@ -189,8 +181,8 @@ class YoutubeIE(InfoExtractor): 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 = unescapeHTML(caption) - caption = unescapeHTML(caption) # double cycle, inentional - srt += str(n) + '\n' + caption = unescapeHTML(caption) # double cycle, intentional + srt += str(n+1) + '\n' srt += start + ' --> ' + end + '\n' srt += caption + '\n\n' return srt @@ -319,6 +311,11 @@ 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) @@ -334,10 +331,6 @@ 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: @@ -359,40 +352,42 @@ class YoutubeIE(InfoExtractor): pass # description - video_description = get_element_by_id("eow-description", video_webpage) - if video_description: video_description = clean_html(video_description.decode('utf8')) + 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]) # token video_token = urllib.unquote_plus(video_info['token'][0]) @@ -450,12 +445,12 @@ class YoutubeIE(InfoExtractor): video_extension = self._video_extensions.get(format_param, 'flv') results.append({ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_real_url.decode('utf-8'), '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'), @@ -531,8 +526,6 @@ 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: @@ -578,7 +571,6 @@ 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) if mobj is None: @@ -587,12 +579,12 @@ class MetacafeIE(InfoExtractor): video_uploader = mobj.group(1) return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), '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, @@ -659,8 +651,6 @@ class DailymotionIE(InfoExtractor): 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) if mobj is None: @@ -669,12 +659,12 @@ class DailymotionIE(InfoExtractor): video_uploader = mobj.group(1) return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), '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, @@ -738,8 +728,6 @@ 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) @@ -767,12 +755,12 @@ class GoogleIE(InfoExtractor): video_thumbnail = '' return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), '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, @@ -831,18 +819,16 @@ 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') return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), '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, @@ -920,7 +906,6 @@ 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: @@ -981,12 +966,12 @@ class YahooIE(InfoExtractor): video_url = unescapeHTML(video_url) return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_url, '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, @@ -1046,7 +1031,6 @@ class VimeoIE(InfoExtractor): # Extract title video_title = config["video"]["title"] - simple_title = simplify_title(video_title) # Extract uploader video_uploader = config["video"]["owner"]["name"] @@ -1055,8 +1039,8 @@ class VimeoIE(InfoExtractor): video_thumbnail = config["video"]["thumbnail"] # Extract video description - video_description = get_element_by_id("description", webpage) - if video_description: video_description = clean_html(video_description.decode('utf8')) + 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 @@ -1087,12 +1071,12 @@ class VimeoIE(InfoExtractor): %(video_id, sig, timestamp, quality, video_codec.upper()) return [{ + 'provider': IE_NAME, 'id': video_id, 'url': video_url, 'uploader': video_uploader, 'upload_date': video_upload_date, 'title': video_title, - 'stitle': simple_title, 'ext': video_extension, 'thumbnail': video_thumbnail, 'description': video_description, @@ -1227,8 +1211,6 @@ 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) @@ -1238,12 +1220,12 @@ class GenericIE(InfoExtractor): video_uploader = mobj.group(1).decode('utf-8') return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), '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, @@ -1261,7 +1243,7 @@ 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)) @@ -1497,8 +1479,8 @@ class YoutubePlaylistIE(InfoExtractor): _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' - _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&' - _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' + _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=(PL)?%s&' + _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' IE_NAME = u'youtube:playlist' def __init__(self, downloader=None): @@ -1648,6 +1630,98 @@ 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""" @@ -1703,12 +1777,12 @@ class DepositFilesIE(InfoExtractor): file_title = mobj.group(1).decode('utf-8') return [{ + 'provider': IE_NAME, 'id': file_id.decode('utf-8'), 'url': file_url.decode('utf-8'), '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, @@ -1853,9 +1927,6 @@ 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: @@ -1911,12 +1982,12 @@ class FacebookIE(InfoExtractor): video_extension = self._video_extensions.get(format_param, 'mp4') results.append({ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': video_real_url.decode('utf-8'), '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'), @@ -1951,7 +2022,7 @@ 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: @@ -1963,10 +2034,10 @@ class BlipTVIE(InfoExtractor): ext = ext.replace('.', '') self.report_direct_download(title) info = { + 'provider': IE_NAME, 'id': title, 'url': url, 'title': title, - 'stitle': simplify_title(title), 'ext': ext, 'urlhandle': urlh } @@ -1986,21 +2057,21 @@ 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 = { + 'provider': IE_NAME, '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'], @@ -2011,6 +2082,7 @@ 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] @@ -2062,17 +2134,14 @@ class MyVideoIE(InfoExtractor): return video_title = mobj.group(1) - video_title = sanitize_title(video_title) - - simple_title = simplify_title(video_title) return [{ + 'provider': IE_NAME, 'id': video_id, 'url': video_url, 'uploader': u'NA', 'upload_date': u'NA', 'title': video_title, - 'stitle': simple_title, 'ext': u'flv', 'format': u'NA', 'player_url': None, @@ -2086,7 +2155,7 @@ 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) @@ -2194,12 +2263,12 @@ class ComedyCentralIE(InfoExtractor): effTitle = showId + u'-' + epTitle info = { + 'provider': IE_NAME, 'id': shortMediaId, 'url': video_url, 'uploader': showId, 'upload_date': officialDate, 'title': effTitle, - 'stitle': simplify_title(effTitle), 'ext': 'mp4', 'format': format, 'thumbnail': None, @@ -2234,7 +2303,10 @@ 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 @@ -2268,12 +2340,12 @@ class EscapistIE(InfoExtractor): videoUrl = playlist[1]['url'] info = { + 'provider': IE_NAME, 'id': videoId, 'url': videoUrl, 'uploader': showName, 'upload_date': None, 'title': showName, - 'stitle': simplify_title(showName), 'ext': 'flv', 'format': 'flv', 'thumbnail': imgUrl, @@ -2320,6 +2392,7 @@ class CollegeHumorIE(InfoExtractor): internal_video_id = m.group('internalvideoid') info = { + 'provider': IE_NAME, 'id': video_id, 'internal_id': internal_video_id, } @@ -2337,7 +2410,6 @@ class CollegeHumorIE(InfoExtractor): videoNode = mdoc.findall('./video')[0] info['description'] = videoNode.findall('./description')[0].text info['title'] = videoNode.findall('./caption')[0].text - info['stitle'] = simplify_title(info['title']) info['url'] = videoNode.findall('./file')[0].text info['thumbnail'] = videoNode.findall('./thumbnail')[0].text info['ext'] = info['url'].rpartition('.')[2] @@ -2399,19 +2471,19 @@ class XVideosIE(InfoExtractor): # Extract video thumbnail - mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage) + mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract video thumbnail') return - video_thumbnail = mobj.group(1).decode('utf-8') + video_thumbnail = mobj.group(0).decode('utf-8') info = { + 'provider': IE_NAME, 'id': video_id, 'url': video_url, 'uploader': None, 'upload_date': None, 'title': video_title, - 'stitle': simplify_title(video_title), 'ext': 'flv', 'format': 'flv', 'thumbnail': video_thumbnail, @@ -2455,7 +2527,7 @@ class SoundcloudIE(InfoExtractor): uploader = mobj.group(1).decode('utf-8') # extract simple title (uploader + slug of song title) slug_title = mobj.group(2).decode('utf-8') - simple_title = uploader + '-' + slug_title + simple_title = uploader + u'-' + slug_title self.report_webpage('%s/%s' % (uploader, slug_title)) @@ -2477,7 +2549,9 @@ class SoundcloudIE(InfoExtractor): # extract unsimplified title mobj = re.search('"title":"(.*?)",', webpage) if mobj: - title = mobj.group(1) + title = mobj.group(1).decode('utf-8') + else: + title = simple_title # construct media url (with uid/token) mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" @@ -2496,18 +2570,18 @@ class SoundcloudIE(InfoExtractor): try: upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') except Exception, e: - print str(e) + self._downloader.to_stderr(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) return [{ + 'provider': IE_NAME, 'id': video_id.decode('utf-8'), 'url': mediaURL, 'uploader': uploader.decode('utf-8'), 'upload_date': upload_date, - 'title': simple_title.decode('utf-8'), - 'stitle': simple_title.decode('utf-8'), + 'title': title, 'ext': u'mp3', 'format': u'NA', 'player_url': None, @@ -2572,12 +2646,12 @@ class InfoQIE(InfoExtractor): video_id, extension = video_filename.split('.') info = { + 'provider': IE_NAME, 'id': video_id, 'url': video_url, 'uploader': None, 'upload_date': None, 'title': video_title, - 'stitle': simplify_title(video_title), 'ext': extension, 'format': extension, # Extension is always(?) mp4, but seems to be flv 'thumbnail': None, @@ -2614,7 +2688,6 @@ class MixcloudIE(InfoExtractor): url_list = jsonData[fmt][bitrate] except TypeError: # we have no bitrate info. url_list = jsonData[fmt] - return url_list def check_urls(self, url_list): @@ -2689,12 +2762,12 @@ class MixcloudIE(InfoExtractor): format_param = req_format return [{ + 'provider': IE_NAME, 'id': file_id.decode('utf-8'), 'url': file_url.decode('utf-8'), 'uploader': uploader.decode('utf-8'), 'upload_date': u'NA', 'title': json_data['name'], - 'stitle': simplify_title(json_data['name']), 'ext': file_url.split('.')[-1].decode('utf-8'), 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), 'thumbnail': json_data['thumbnail_url'], @@ -2726,9 +2799,10 @@ class StanfordOpenClassroomIE(InfoExtractor): course = mobj.group('course') video = mobj.group('video') info = { - 'id': simplify_title(course + '_' + video), + 'provider': IE_NAME, + 'id': course + '_' + video, } - + self.report_extraction(info['id']) baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' xmlUrl = baseUrl + video + '.xml' @@ -2744,14 +2818,14 @@ class StanfordOpenClassroomIE(InfoExtractor): except IndexError: self._downloader.trouble(u'\nERROR: Invalid metadata XML file') return - info['stitle'] = simplify_title(info['title']) info['ext'] = info['url'].rpartition('.')[2] info['format'] = info['ext'] return [info] elif mobj.group('course'): # A course page course = mobj.group('course') info = { - 'id': simplify_title(course), + 'provider': IE_NAME, + 'id': course, 'type': 'playlist', } @@ -2767,7 +2841,6 @@ class StanfordOpenClassroomIE(InfoExtractor): info['title'] = unescapeHTML(m.group(1)) else: info['title'] = info['id'] - info['stitle'] = simplify_title(info['title']) m = re.search('([^<]+)', coursepage) if m: @@ -2788,6 +2861,7 @@ class StanfordOpenClassroomIE(InfoExtractor): else: # Root page info = { + 'provider': IE_NAME, 'id': 'Stanford OpenClassroom', 'type': 'playlist', } @@ -2801,7 +2875,6 @@ class StanfordOpenClassroomIE(InfoExtractor): return info['title'] = info['id'] - info['stitle'] = simplify_title(info['title']) links = orderedSet(re.findall('', rootpage)) info['list'] = [ @@ -2896,11 +2969,11 @@ class MTVIE(InfoExtractor): return info = { + 'provider': IE_NAME, 'id': video_id, 'url': video_url, 'uploader': performer, 'title': video_title, - 'stitle': simplify_title(video_title), 'ext': ext, 'format': format, }