X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=6a6545c9b578fba948962542d602bc5352b86840;hb=44696667805343a2f60bdec25d8ab9ed90b5963c;hp=c50052a733b8174dfc1d4008203f5a477f8375b6;hpb=c72938240e8edd75296c1dbe262769e5002ce811;p=youtube-dl.git diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index c50052a73..6a6545c9b 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -116,7 +116,7 @@ class InfoExtractor(object): if note is None: note = u'Downloading video webpage' if note is not False: - self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + self.to_screen(u'%s: %s' % (video_id, note)) try: return compat_urllib_request.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -139,11 +139,23 @@ class InfoExtractor(object): url = url_or_request.get_full_url() except AttributeError: url = url_or_request - self._downloader.to_screen(u'Dumping request to ' + url) + self.to_screen(u'Dumping request to ' + url) dump = base64.b64encode(webpage_bytes).decode('ascii') self._downloader.to_screen(dump) return webpage_bytes.decode(encoding, 'replace') - + + def to_screen(self, msg): + """Print msg to screen, prefixing it with '[ie_name]'""" + self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) + + def report_extraction(self, id_or_name): + """Report information extraction.""" + self.to_screen(u'%s: Extracting information' % id_or_name) + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self.to_screen(u'Confirming age') + #Methods for following #608 #They set the correct value of the '_type' key def video_result(self, video_info): @@ -236,48 +248,44 @@ class YoutubeIE(InfoExtractor): def report_lang(self): """Report attempt to set language.""" - self._downloader.to_screen(u'[youtube] Setting language') + self.to_screen(u'Setting language') def report_login(self): """Report attempt to log in.""" - self._downloader.to_screen(u'[youtube] Logging in') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[youtube] Confirming age') + self.to_screen(u'Logging in') def report_video_webpage_download(self, video_id): """Report attempt to download video webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) + self.to_screen(u'%s: Downloading video webpage' % video_id) def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) + self.to_screen(u'%s: Downloading video info webpage' % video_id) def report_video_subtitles_download(self, video_id): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Checking available subtitles' % video_id) + self.to_screen(u'%s: Checking available subtitles' % video_id) def report_video_subtitles_request(self, video_id, sub_lang, format): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) + self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) def report_video_subtitles_available(self, video_id, sub_lang_list): """Report available subtitles.""" sub_lang = ",".join(list(sub_lang_list.keys())) - self._downloader.to_screen(u'[youtube] %s: Available subtitles for video: %s' % (video_id, sub_lang)) + self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) + self.to_screen(u'%s: Extracting video information' % video_id) def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" - self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) + self.to_screen(u'%s: Format %s not available' % (video_id, format)) def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" - self._downloader.to_screen(u'[youtube] RTMP download detected') + self.to_screen(u'RTMP download detected') def _get_available_subtitles(self, video_id): self.report_video_subtitles_download(video_id) @@ -614,8 +622,7 @@ class YoutubeIE(InfoExtractor): format_list = available_formats existing_formats = [x for x in format_list if x in url_map] if len(existing_formats) == 0: - self._downloader.report_error(u'no known formats available for video') - return + raise ExtractorError(u'no known formats available for video') if self._downloader.params.get('listformats', None): self._print_formats(existing_formats) return @@ -635,11 +642,9 @@ class YoutubeIE(InfoExtractor): video_url_list = [(rf, url_map[rf])] break if video_url_list is None: - self._downloader.report_error(u'requested format not available') - return + raise ExtractorError(u'requested format not available') else: - self._downloader.report_error(u'no conn or url_encoded_fmt_stream_map information found in video info') - return + raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info') results = [] for format_param, video_real_url in video_url_list: @@ -680,19 +685,11 @@ class MetacafeIE(InfoExtractor): def report_disclaimer(self): """Report disclaimer retrieval.""" - self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[metacafe] Confirming age') + self.to_screen(u'Retrieving disclaimer') def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_initialize(self): # Retrieve disclaimer @@ -797,10 +794,6 @@ class DailymotionIE(InfoExtractor): def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) - def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) @@ -828,7 +821,7 @@ class DailymotionIE(InfoExtractor): 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) + self.to_screen(u'Using %s' % key) break else: self._downloader.report_error(u'unable to extract video URL') @@ -887,11 +880,7 @@ class PhotobucketIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url): # Extract id from URL @@ -956,11 +945,7 @@ class YahooIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url, new_video=True): # Extract ID from URL @@ -1096,11 +1081,7 @@ class VimeoIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url, new_video=True): # Extract ID from URL @@ -1182,7 +1163,7 @@ class VimeoIE(InfoExtractor): 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)) + self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) break else: self._downloader.report_error(u'no known codec found') @@ -1217,11 +1198,7 @@ class ArteTvIE(InfoExtractor): 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) + self.to_screen(u'%s: Downloading webpage' % video_id) def fetch_webpage(self, url): request = compat_urllib_request.Request(url) @@ -1352,12 +1329,8 @@ class GenericIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" if not self._downloader.params.get('test', False): - self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') - self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) + self._downloader.report_warning(u'Falling back on generic information extractor.') + self.to_screen(u'%s: Downloading webpage' % video_id) def report_following_redirect(self, new_url): """Report information extraction.""" @@ -1510,11 +1483,9 @@ class YoutubeSearchIE(InfoExtractor): prefix = prefix[8:] query = query.encode('utf-8') if prefix == '': - self._download_n_results(query, 1) - return + return self._get_n_results(query, 1) elif prefix == 'all': - self._download_n_results(query, self._max_youtube_results) - return + self._get_n_results(query, self._max_youtube_results) else: try: n = int(prefix) @@ -1524,14 +1495,12 @@ class YoutubeSearchIE(InfoExtractor): elif n > self._max_youtube_results: self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) n = self._max_youtube_results - self._download_n_results(query, n) - return + return self._get_n_results(query, n) except ValueError: # parsing prefix as integer fails - self._download_n_results(query, 1) - return + return self._get_n_results(query, 1) - def _download_n_results(self, query, n): - """Downloads a specified number of results for a query""" + def _get_n_results(self, query, n): + """Get a specified number of results for a query""" video_ids = [] pagenum = 0 @@ -1560,9 +1529,8 @@ class YoutubeSearchIE(InfoExtractor): if len(video_ids) > n: video_ids = video_ids[:n] - for id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) - return + videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids] + return videos class GoogleSearchIE(InfoExtractor): @@ -1580,7 +1548,7 @@ class GoogleSearchIE(InfoExtractor): def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) + self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum)) def _real_extract(self, query): mobj = re.match(self._VALID_URL, query) @@ -1664,7 +1632,7 @@ class YahooSearchIE(InfoExtractor): def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) + self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum)) def _real_extract(self, query): mobj = re.match(self._VALID_URL, query) @@ -1975,8 +1943,8 @@ class BlipTVUserIE(InfoExtractor): 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)) + self.to_screen(u'user %s: Downloading video ids from page %d' % + (username, pagenum)) def _real_extract(self, url): # Extract username @@ -2050,11 +2018,7 @@ class DepositFilesIE(InfoExtractor): def report_download_webpage(self, file_id): """Report webpage download.""" - self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) + self.to_screen(u'%s: Downloading webpage' % file_id) def _real_extract(self, url): file_id = url.split('/')[-1] @@ -2113,7 +2077,7 @@ class FacebookIE(InfoExtractor): def report_login(self): """Report attempt to log in.""" - self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME) + self.to_screen(u'Logging in') def _real_initialize(self): if self._downloader is None: @@ -2209,13 +2173,9 @@ class BlipTVIE(InfoExtractor): _URL_EXT = r'^.*\.([a-z0-9]+)$' IE_NAME = u'blip.tv' - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) - def report_direct_download(self, title): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) + self.to_screen(u'%s: Direct download detected' % title) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2313,10 +2273,6 @@ class MyVideoIE(InfoExtractor): def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) - def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -2394,14 +2350,11 @@ class ComedyCentralIE(InfoExtractor): """Receives a URL and returns True if suitable for this IE.""" return re.match(cls._VALID_URL, url, re.VERBOSE) is not None - def report_extraction(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) - def report_config_download(self, episode_id, media_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id)) + self.to_screen(u'%s: Downloading configuration for %s' % (episode_id, media_id)) def report_index_download(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) + self.to_screen(u'%s: Downloading show index' % episode_id) def _print_formats(self, formats): print('Available formats:') @@ -2555,11 +2508,8 @@ class EscapistIE(InfoExtractor): _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P[^/]+)/(?P[^/?]+)[/?]?.*$' IE_NAME = u'escapist' - def report_extraction(self, showName): - self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) - def report_config_download(self, showName): - self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) + self.to_screen(u'%s: Downloading configuration' % showName) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2632,11 +2582,7 @@ class CollegeHumorIE(InfoExtractor): def report_manifest(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (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)) + self.to_screen(u'%s: Downloading XML manifest' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2701,10 +2647,6 @@ class XVideosIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' IE_NAME = u'xvideos' - 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: @@ -2771,11 +2713,7 @@ class SoundcloudIE(InfoExtractor): def report_resolve(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Resolving id' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2844,11 +2782,7 @@ class SoundcloudSetIE(InfoExtractor): def report_resolve(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Resolving id' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2913,10 +2847,6 @@ class InfoQIE(InfoExtractor): """Information extractor for infoq.com""" _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -2975,11 +2905,7 @@ class MixcloudIE(InfoExtractor): def report_download_json(self, file_id): """Report JSON download.""" - self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + self.to_screen(u'Downloading json') def get_urls(self, jsonData, fmt, bitrate='best'): """Get urls from 'audio_formats' section in json""" @@ -3086,11 +3012,7 @@ class StanfordOpenClassroomIE(InfoExtractor): def report_download_webpage(self, objid): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Downloading webpage' % objid) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -3196,10 +3118,6 @@ class MTVIE(InfoExtractor): _VALID_URL = r'^(?Phttps?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P[0-9]+)/[^/]+$' IE_NAME = u'mtv' - 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: @@ -3276,11 +3194,7 @@ class YoukuIE(InfoExtractor): def report_download_webpage(self, file_id): """Report webpage download.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id)) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + self.to_screen(u'%s: Downloading webpage' % file_id) def _gen_sid(self): nowTime = int(time.time() * 1000) @@ -3393,11 +3307,7 @@ class XNXXIE(InfoExtractor): 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)) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -3457,23 +3367,23 @@ class GooglePlusIE(InfoExtractor): def report_extract_entry(self, url): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url) + self.to_screen(u'Downloading entry: %s' % url) def report_date(self, upload_date): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) + self.to_screen(u'Entry date: %s' % upload_date) def report_uploader(self, uploader): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader) + self.to_screen(u'Uploader: %s' % uploader) def report_title(self, video_title): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Title: %s' % video_title) + self.to_screen(u'Title: %s' % video_title) def report_extract_vid_page(self, video_page): """Report information extraction.""" - self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page) + self.to_screen(u'Extracting video page: %s' % video_page) def _real_extract(self, url): # Extract id from URL @@ -3617,14 +3527,10 @@ class JustinTVIE(InfoExtractor): _JUSTIN_PAGE_LIMIT = 100 IE_NAME = u'justin.tv' - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) - def report_download_page(self, channel, offset): """Report attempt to download a single page of videos.""" - self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' % - (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) + self.to_screen(u'%s: Downloading video information from %d to %d' % + (channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) # Return count of items, list of *valid* items def _parse_page(self, url): @@ -3746,10 +3652,13 @@ class SteamIE(InfoExtractor): def _real_extract(self, url): m = re.match(self._VALID_URL, url, re.VERBOSE) - urlRE = r"'movie_(?P\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\}," gameID = m.group('gameID') - videourl = 'http://store.steampowered.com/video/%s/' % gameID + videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID + self.report_age_confirmation() webpage = self._download_webpage(videourl, gameID) + game_title = re.search(r'

(?P.*?)

', webpage).group('game_title') + + urlRE = r"'movie_(?P\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\}," mweb = re.finditer(urlRE, webpage) namesRE = r'(?P.+?)' titles = re.finditer(namesRE, webpage) @@ -3771,7 +3680,7 @@ class SteamIE(InfoExtractor): 'thumbnail': video_thumb } videos.append(info) - return videos + return [self.playlist_result(videos, gameID, game_title)] class UstreamIE(InfoExtractor): _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P\d+)' @@ -3953,7 +3862,7 @@ class YouPornIE(InfoExtractor): if(len(links) == 0): raise ExtractorError(u'ERROR: no known formats available for video') - self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) + self.to_screen(u'Links found: %d' % len(links)) formats = [] for link in links: @@ -3989,7 +3898,7 @@ class YouPornIE(InfoExtractor): return req_format = self._downloader.params.get('format', None) - self._downloader.to_screen(u'[youporn] Format: %s' % req_format) + self.to_screen(u'Format: %s' % req_format) if req_format is None or req_format == 'best': return [formats[0]] @@ -4184,7 +4093,7 @@ class TEDIE(InfoExtractor): else : playlist_id=m.group('playlist_id') name=m.group('name') - self._downloader.to_screen(u'[%s] Getting info of playlist %s: "%s"' % (self.IE_NAME,playlist_id,name)) + self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name)) return [self._playlist_videos_info(url,name,playlist_id)] def _talk_video_link(self,mediaSlug): @@ -4409,7 +4318,7 @@ class ARDIE(InfoExtractor): # there's two possibilities: RTMP stream or HTTP download info = {'id': video_id, 'title': title, 'ext': 'mp4'} if stream['rtmp_url']: - self._downloader.to_screen(u'[%s] RTMP download detected' % self.IE_NAME) + self.to_screen(u'RTMP download detected') assert stream['video_url'].startswith('mp4:') info["url"] = stream["rtmp_url"] info["play_path"] = stream['video_url'] @@ -4418,6 +4327,40 @@ class ARDIE(InfoExtractor): info["url"] = stream["video_url"] return [info] +class TumblrIE(InfoExtractor): + _VALID_URL = r'http://(?P.*?).tumblr.com/((post)|(video))/(?P\d*)/(.*?)' + + def _real_extract(self, url): + m_url = re.match(self._VALID_URL, url) + video_id = m_url.group('id') + blog = m_url.group('blog_name') + + url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) + webpage = self._download_webpage(url, video_id) + + re_video = r'src=\\x22(?Phttp://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P.*?)\\x22' % (blog, video_id) + video = re.search(re_video, webpage) + if video is None: + self.to_screen("No video founded") + return [] + video_url = video.group('video_url') + ext = video.group('ext') + + re_thumb = r'posters(.*?)\[\\x22(?P.*?)\\x22' # We pick the first poster + thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '') + + # The only place where you can get a title, it's not complete, + # but searching in other places doesn't work for all videos + re_title = r'(.*?) - (?P<title>.*?)' + title = unescapeHTML(re.search(re_title, webpage).group('title')) + + return [{'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumb, + 'ext': ext + }] + def gen_extractors(): """ Return a list of an instance of every supported extractor. @@ -4472,6 +4415,7 @@ def gen_extractors(): SpiegelIE(), LiveLeakIE(), ARDIE(), + TumblrIE(), GenericIE() ]