diff options
| -rw-r--r-- | test/test_all_urls.py | 18 | ||||
| -rw-r--r-- | test/test_youtube_subtitles.py | 12 | ||||
| -rw-r--r-- | test/tests.json | 27 | ||||
| -rw-r--r-- | youtube_dl/FileDownloader.py | 6 | ||||
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 205 | ||||
| -rw-r--r-- | youtube_dl/version.py | 2 |
6 files changed, 253 insertions, 17 deletions
diff --git a/test/test_all_urls.py b/test/test_all_urls.py index a40360122..dd67286a7 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -7,7 +7,7 @@ import unittest import os sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE +from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE class TestAllURLsMatching(unittest.TestCase): def test_youtube_playlist_matching(self): @@ -29,6 +29,22 @@ class TestAllURLsMatching(unittest.TestCase): self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')) self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')) + def test_justin_tv_channelid_matching(self): + self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv")) + self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv")) + self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv")) + self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv")) + self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv")) + self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv")) + self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/")) + self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/")) + + def test_justintv_videoid_matching(self): + self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483")) + + def test_justin_tv_chapterid_matching(self): + self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361")) + def test_youtube_extract(self): self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') diff --git a/test/test_youtube_subtitles.py b/test/test_youtube_subtitles.py index a123e6d72..c80c90cbe 100644 --- a/test/test_youtube_subtitles.py +++ b/test/test_youtube_subtitles.py @@ -28,7 +28,9 @@ compat_urllib_request.install_opener(opener) class FakeDownloader(FileDownloader): def __init__(self): self.result = [] - self.params = parameters + # Different instances of the downloader can't share the same dictionary + # some test set the "sublang" parameter, which would break the md5 checks. + self.params = dict(parameters) def to_screen(self, s): print(s) def trouble(self, s, tb=None): @@ -96,6 +98,14 @@ class TestYoutubeSubtitles(unittest.TestCase): IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') self.assertEqual(info_dict, None) + def test_youtube_automatic_captions(self): + DL = FakeDownloader() + DL.params['writesubtitles'] = True + DL.params['subtitleslang'] = 'it' + IE = YoutubeIE(DL) + info_dict = IE.extract('8YoUxe5ncPo') + sub = info_dict[0]['subtitles'][0] + self.assertTrue(sub[2] is not None) if __name__ == '__main__': unittest.main() diff --git a/test/tests.json b/test/tests.json index f57ebf1c9..04be912ce 100644 --- a/test/tests.json +++ b/test/tests.json @@ -482,5 +482,32 @@ "title": "Louis C.K. Interview Pt. 1 11/3/11", "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one." } + }, + { + "name": "XHamster", + "url": "http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html", + "file": "1509445.flv", + "md5": "9f48e0e8d58e3076bb236ff412ab62fa", + "info_dict":{ + "title":"FemaleAgent Shy beauty takes the bait" + } + }, + { + "name": "Hypem", + "url": "http://hypem.com/track/1v6ga/BODYWORK+-+TAME", + "file": "1v6ga.mp3", + "md5": "b9cc91b5af8995e9f0c1cee04c575828", + "info_dict":{ + "title":"TAME" + } + }, + { + "name": "Vbox7", + "url": "http://vbox7.com/play:249bb972c2", + "file": "249bb972c2.flv", + "md5": "9c70d6d956f888bdc08c124acc120cfe", + "info_dict":{ + "title":"Смях! Чудо - чист за секунди - Скрита камера" + } } ] diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 2c35a05d8..bf0f5bb9e 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -814,12 +814,10 @@ class FileDownloader(object): self.report_destination(filename) tmpfilename = self.temp_name(filename) -# args = ['mmsclient', url] # doesn't work anymore -# args = ['wpro', url, '-O', tmpfilename] # dont work args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url] # Check for mplayer first try: - subprocess.call(args[0], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) except (OSError, IOError): self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0] ) return False @@ -839,7 +837,7 @@ class FileDownloader(object): return True else: self.to_stderr(u"\n") - self.report_error(u'%s exited with code %d' % (args[0], retval)) + self.report_error(u'mplayer exited with code %d' % retval) return False diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 4ca744daf..24a77a1ab 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -376,6 +376,34 @@ class YoutubeIE(InfoExtractor): return (u'Did not fetch video subtitles', None, None) return (None, sub_lang, sub) + def _request_automatic_caption(self, video_id, webpage): + """We need the webpage for getting the captions url, pass it as an + argument to speed up the process.""" + sub_lang = self._downloader.params.get('subtitleslang') + sub_format = self._downloader.params.get('subtitlesformat') + self.to_screen(u'%s: Looking for automatic captions' % video_id) + mobj = re.search(r';ytplayer.config = ({.*?});', webpage) + err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang + if mobj is None: + return [(err_msg, None, None)] + player_config = json.loads(mobj.group(1)) + try: + args = player_config[u'args'] + caption_url = args[u'ttsurl'] + timestamp = args[u'timestamp'] + params = compat_urllib_parse.urlencode({ + 'lang': 'en', + 'tlang': sub_lang, + 'fmt': sub_format, + 'ts': timestamp, + 'kind': 'asr', + }) + subtitles_url = caption_url + '&' + params + sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions') + return [(None, sub_lang, sub)] + except KeyError: + return [(err_msg, None, None)] + def _extract_subtitle(self, video_id): """ Return a list with a tuple: @@ -623,7 +651,14 @@ class YoutubeIE(InfoExtractor): if video_subtitles: (sub_error, sub_lang, sub) = video_subtitles[0] if sub_error: - self._downloader.report_error(sub_error) + # We try with the automatic captions + video_subtitles = self._request_automatic_caption(video_id, video_webpage) + (sub_error_auto, sub_lang, sub) = video_subtitles[0] + if sub is not None: + pass + else: + # We report the original error + self._downloader.report_error(sub_error) if self._downloader.params.get('allsubtitles', False): video_subtitles = self._extract_all_subtitles(video_id) @@ -1025,7 +1060,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)' + _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)' IE_NAME = u'vimeo' def _real_extract(self, url, new_video=True): @@ -1037,7 +1072,7 @@ class VimeoIE(InfoExtractor): video_id = mobj.group('id') if not mobj.group('proto'): url = 'https://' + url - if mobj.group('direct_link'): + if mobj.group('direct_link') or mobj.group('pro'): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information @@ -1064,7 +1099,7 @@ class VimeoIE(InfoExtractor): # Extract uploader and uploader_id video_uploader = config["video"]["owner"]["name"] - video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] + video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None # Extract video thumbnail video_thumbnail = config["video"]["thumbnail"] @@ -1884,7 +1919,7 @@ class FacebookIE(InfoExtractor): class BlipTVIE(InfoExtractor): """Information extractor for blip.tv""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$' IE_NAME = u'blip.tv' @@ -1897,6 +1932,10 @@ class BlipTVIE(InfoExtractor): if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) + # See https://github.com/rg3/youtube-dl/issues/857 + api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url) + if api_mobj is not None: + url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') urlp = compat_urllib_parse_urlparse(url) if urlp.path.startswith('/play/'): request = compat_urllib_request.Request(url) @@ -3941,7 +3980,7 @@ class SpiegelIE(InfoExtractor): video_id = m.group('videoID') webpage = self._download_webpage(url, video_id) - m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage) + m = re.search(r'<div class="module-title">(.*?)</div>', webpage) if not m: raise ExtractorError(u'Cannot find title') video_title = unescapeHTML(m.group(1)) @@ -4070,8 +4109,8 @@ class ZDFIE(InfoExtractor): if streams is None: raise ExtractorError(u'No media url found.') - # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' und mms url - # s['media_type'] == 'hstreaming' -> use 'Quicktime' und rtsp url + # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url + # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url # choose first/default media type and highest quality for now for s in streams: #find 300 - dsl1000mbit if s['quality'] == '300' and s['media_type'] == 'wstreaming': @@ -4263,7 +4302,7 @@ class HowcastIE(InfoExtractor): self.report_extraction(video_id) - mobj = re.search(r'\'file\': "(http://mobile-media\.howcast\.com/\d+\.mp4)"', webpage) + mobj = re.search(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)"', webpage) if mobj is None: raise ExtractorError(u'Unable to extract video URL') video_url = mobj.group(1) @@ -4444,6 +4483,149 @@ class TeamcocoIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, }] + +class XHamsterIE(InfoExtractor): + """Information Extractor for xHamster""" + _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html' + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + + video_id = mobj.group('id') + mrss_url='http://xhamster.com/movies/%s/.html' % video_id + webpage = self._download_webpage(mrss_url, video_id) + mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract media URL') + if len(mobj.group('server')) == 0: + video_url = compat_urllib_parse.unquote(mobj.group('file')) + else: + video_url = mobj.group('server')+'/key='+mobj.group('file') + video_extension = video_url.split('.')[-1] + + mobj = re.search(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = unescapeHTML(mobj.group('title')) + + mobj = re.search(r'<span>Description: </span>(?P<description>[^<]+)', webpage) + if mobj is None: + video_description = u'' + else: + video_description = unescapeHTML(mobj.group('description')) + + mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract upload date') + video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') + + mobj = re.search(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)', webpage) + if mobj is None: + video_uploader_id = u'anonymous' + else: + video_uploader_id = mobj.group('uploader_id') + + mobj = re.search(r'\'image\':\'(?P<thumbnail>[^\']+)\'', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract thumbnail URL') + video_thumbnail = mobj.group('thumbnail') + + return [{ + 'id': video_id, + 'url': video_url, + 'ext': video_extension, + 'title': video_title, + 'description': video_description, + 'upload_date': video_upload_date, + 'uploader_id': video_uploader_id, + 'thumbnail': video_thumbnail + }] + +class HypemIE(InfoExtractor): + """Information Extractor for hypem""" + _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + track_id = mobj.group(1) + + data = { 'ax': 1, 'ts': time.time() } + data_encoded = compat_urllib_parse.urlencode(data) + complete_url = url + "?" + data_encoded + request = compat_urllib_request.Request(complete_url) + response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') + cookie = urlh.headers.get('Set-Cookie', '') + + self.report_extraction(track_id) + mobj = re.search(r'<script type="application/json" id="displayList-data">(.*?)</script>', response, flags=re.MULTILINE|re.DOTALL) + if mobj is None: + raise ExtractorError(u'Unable to extrack tracks') + html_tracks = mobj.group(1).strip() + try: + track_list = json.loads(html_tracks) + track = track_list[u'tracks'][0] + except ValueError: + raise ExtractorError(u'Hypemachine contained invalid JSON.') + + key = track[u"key"] + track_id = track[u"id"] + artist = track[u"artist"] + title = track[u"song"] + + serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key)) + request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'}) + request.add_header('cookie', cookie) + song_data_json = self._download_webpage(request, track_id, u'Downloading metadata') + try: + song_data = json.loads(song_data_json) + except ValueError: + raise ExtractorError(u'Hypemachine contained invalid JSON.') + final_url = song_data[u"url"] + + return [{ + 'id': track_id, + 'url': final_url, + 'ext': "mp3", + 'title': title, + 'artist': artist, + }] + +class Vbox7IE(InfoExtractor): + """Information Extractor for Vbox7""" + _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)' + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group(1) + + redirect_page, urlh = self._download_webpage_handle(url, video_id) + redirect_url = urlh.geturl() + re.search(r'window\.location = \'(.*)\';', redirect_page).group(1) + webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') + + title = re.search(r'<title>(.*)</title>', webpage) + title = (title.group(1)).split('/')[0].strip() + + ext = "flv" + info_url = "http://vbox7.com/play/magare.do" + data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id}) + info_request = compat_urllib_request.Request(info_url, data) + info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage') + if info_response is None: + raise ExtractorError(u'Unable to extract the media url') + (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) + + return [{ + 'id': video_id, + 'url': final_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + }] def gen_extractors(): """ Return a list of an instance of every supported extractor. @@ -4463,8 +4645,8 @@ def gen_extractors(): YahooSearchIE(), DepositFilesIE(), FacebookIE(), - BlipTVUserIE(), BlipTVIE(), + BlipTVUserIE(), VimeoIE(), MyVideoIE(), ComedyCentralIE(), @@ -4507,6 +4689,9 @@ def gen_extractors(): VineIE(), FlickrIE(), TeamcocoIE(), + XHamsterIE(), + HypemIE(), + Vbox7IE(), GenericIE() ] diff --git a/youtube_dl/version.py b/youtube_dl/version.py index dbc928394..1cda7fa74 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,2 @@ -__version__ = '2013.05.14' +__version__ = '2013.05.23' |