diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/collegehumor.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 31 | ||||
| -rw-r--r-- | youtube_dl/extractor/lifenews.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/mit.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/mixcloud.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/prosiebensat1.py | 297 | ||||
| -rw-r--r-- | youtube_dl/extractor/rtlnow.py | 251 | ||||
| -rw-r--r-- | youtube_dl/extractor/vimeo.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/xhamster.py | 1 | ||||
| -rw-r--r-- | youtube_dl/utils.py | 1 | ||||
| -rw-r--r-- | youtube_dl/version.py | 2 |
12 files changed, 474 insertions, 127 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e16bbd969..8549a1a1e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -175,6 +175,7 @@ from .podomatic import PodomaticIE from .pornhd import PornHdIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE from .radiofrance import RadioFranceIE from .rbmaradio import RBMARadioIE diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py index 10c925dfe..6b9fa4209 100644 --- a/youtube_dl/extractor/collegehumor.py +++ b/youtube_dl/extractor/collegehumor.py @@ -40,7 +40,7 @@ class CollegeHumorIE(InfoExtractor): 'id': 'W5gMp3ZjYg4', 'ext': 'mp4', 'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]', - 'uploader': 'Funnyplox TV', + 'uploader': 'FunnyPlox TV', 'uploader_id': 'funnyploxtv', 'description': 'md5:7ded37421526d54afdf005e25bc2b7a3', 'upload_date': '20140128', diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 22d1b5daa..595ba268f 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -83,10 +83,10 @@ class GenericIE(InfoExtractor): # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', - 'file': 'trailer.mp4', 'md5': '67d406c2bcb6af27fa886f31aa934bbe', 'info_dict': { 'id': 'trailer', + 'ext': 'mp4', 'title': 'trailer', 'upload_date': '20100513', } @@ -94,7 +94,6 @@ class GenericIE(InfoExtractor): # ooyala video { 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', - 'file': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ.mp4', 'md5': '5644c6ca5d5782c1d0d350dad9bd840c', 'info_dict': { 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', @@ -102,6 +101,22 @@ class GenericIE(InfoExtractor): 'title': '2cc213299525360.mov', # that's what we get }, }, + # google redirect + { + 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE', + 'info_dict': { + 'id': 'cmQHVoWB5FY', + 'ext': 'mp4', + 'upload_date': '20130224', + 'uploader_id': 'TheVerge', + 'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.', + 'uploader': 'The Verge', + 'title': 'First Firefox OS phones side-by-side', + }, + 'params': { + 'skip_download': False, + } + } ] def report_download_webpage(self, video_id): @@ -412,6 +427,18 @@ class GenericIE(InfoExtractor): # HTML5 video mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL) if mobj is None: + mobj = re.search( + r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' + r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"', + webpage) + if mobj: + new_url = mobj.group(1) + self.report_following_redirect(new_url) + return { + '_type': 'url', + 'url': new_url, + } + if mobj is None: raise ExtractorError('Unsupported URL: %s' % url) # It's possible that one of the regexes diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 7b7185f9a..bb1bae643 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -32,7 +32,7 @@ class LifeNewsIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page') + webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page') video_url = self._html_search_regex( r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL') @@ -50,7 +50,7 @@ class LifeNewsIE(InfoExtractor): view_count = self._html_search_regex( r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False) comment_count = self._html_search_regex( - r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count', fatal=False) + r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False) upload_date = self._html_search_regex( r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False) diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 270fdf04b..807b1dc89 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -73,7 +73,6 @@ class MITIE(TechTVMITIE): _TEST = { 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', - 'file': '.mp4', 'md5': '7db01d5ccc1895fc5010e9c9e13648da', 'info_dict': { 'id': '21783', diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index b8d363eb6..c4bd53fe7 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( unified_strdate, + compat_urllib_parse, ExtractorError, ) @@ -15,8 +16,9 @@ class MixcloudIE(InfoExtractor): _TEST = { 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', - 'file': 'dholbach-cryptkeeper.mp3', 'info_dict': { + 'id': 'dholbach-cryptkeeper', + 'ext': 'mp3', 'title': 'Cryptkeeper', 'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', 'uploader': 'Daniel Holbach', @@ -45,7 +47,7 @@ class MixcloudIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) uploader = mobj.group(1) cloudcast_name = mobj.group(2) - track_id = '-'.join((uploader, cloudcast_name)) + track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name))) webpage = self._download_webpage(url, track_id) diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py new file mode 100644 index 000000000..564fa5d04 --- /dev/null +++ b/youtube_dl/extractor/prosiebensat1.py @@ -0,0 +1,297 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from hashlib import sha1 +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + unified_strdate, + clean_html, + RegexNotFoundError, +) + + +class ProSiebenSat1IE(InfoExtractor): + IE_NAME = 'prosiebensat1' + IE_DESC = 'ProSiebenSat.1 Digital' + _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)' + + _TESTS = [ + { + 'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge', + 'info_dict': { + 'id': '2104602', + 'ext': 'mp4', + 'title': 'Staffel 2, Episode 18 - Jahresrückblick', + 'description': 'md5:8733c81b702ea472e069bc48bb658fc1', + 'upload_date': '20131231', + 'duration': 5845.04, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.prosieben.de/videokatalog/Gesellschaft/Leben/Trends/video-Lady-Umstyling-f%C3%BCr-Audrina-Rebekka-Audrina-Fergen-billig-aussehen-Battal-Modica-700544.html', + 'info_dict': { + 'id': '2570327', + 'ext': 'mp4', + 'title': 'Lady-Umstyling für Audrina', + 'description': 'md5:4c16d0c17a3461a0d43ea4084e96319d', + 'upload_date': '20131014', + 'duration': 606.76, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'Seems to be broken', + }, + { + 'url': 'http://www.prosiebenmaxx.de/yep/one-piece/video/148-folge-48-gold-rogers-heimat-ganze-folge', + 'info_dict': { + 'id': '2437108', + 'ext': 'mp4', + 'title': 'Folge 48: Gold Rogers Heimat', + 'description': 'Ruffy erreicht die Insel, auf der der berühmte Gold Roger lebte und hingerichtet wurde.', + 'upload_date': '20140226', + 'duration': 1401.48, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip', + 'info_dict': { + 'id': '2904997', + 'ext': 'mp4', + 'title': 'Sexy laufen in Ugg Boots', + 'description': 'md5:edf42b8bd5bc4e5da4db4222c5acb7d6', + 'upload_date': '20140122', + 'duration': 245.32, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip', + 'info_dict': { + 'id': '2906572', + 'ext': 'mp4', + 'title': 'Im Interview: Kai Wiesinger', + 'description': 'md5:e4e5370652ec63b95023e914190b4eb9', + 'upload_date': '20140225', + 'duration': 522.56, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge', + 'info_dict': { + 'id': '2992323', + 'ext': 'mp4', + 'title': 'Jagd auf Fertigkost im Elsthal - Teil 2', + 'description': 'md5:2669cde3febe9bce13904f701e774eb6', + 'upload_date': '20140225', + 'duration': 2410.44, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge', + 'info_dict': { + 'id': '3004256', + 'ext': 'mp4', + 'title': 'Schalke: Tönnies möchte Raul zurück', + 'description': 'md5:4b5b271d9bcde223b54390754c8ece3f', + 'upload_date': '20140226', + 'duration': 228.96, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip', + 'info_dict': { + 'id': '2572814', + 'ext': 'mp4', + 'title': 'Andreas Kümmert: Rocket Man', + 'description': 'md5:6ddb02b0781c6adf778afea606652e38', + 'upload_date': '20131017', + 'duration': 469.88, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html', + 'info_dict': { + 'id': '2156342', + 'ext': 'mp4', + 'title': 'Kurztrips zum Valentinstag', + 'description': 'md5:8ba6301e70351ae0bedf8da00f7ba528', + 'upload_date': '20130206', + 'duration': 307.24, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + _CLIPID_REGEXES = [ + r'"clip_id"\s*:\s+"(\d+)"', + r'clipid: "(\d+)"', + ] + _TITLE_REGEXES = [ + r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', + r'<header class="clearfix">\s*<h3>(.+?)</h3>', + r'<!-- start video -->\s*<h1>(.+?)</h1>', + r'<div class="ep-femvideos-pi4-video-txt">\s*<h2>(.+?)</h2>', + ] + _DESCRIPTION_REGEXES = [ + r'<p itemprop="description">\s*(.+?)</p>', + r'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>', + r'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>', + r'<p>(.+?)</p>\s*<div class="ep-femvideos-pi4-video-footer">', + ] + _UPLOAD_DATE_REGEXES = [ + r'<meta property="og:published_time" content="(.+?)">', + r'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration"', + r'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr', + r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>', + r'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>', + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id, 'Downloading page') + + def extract(patterns, name, page, fatal=False): + for pattern in patterns: + mobj = re.search(pattern, page) + if mobj: + return clean_html(mobj.group(1)) + if fatal: + raise RegexNotFoundError(u'Unable to extract %s' % name) + return None + + clip_id = extract(self._CLIPID_REGEXES, 'clip id', page, fatal=True) + + access_token = 'testclient' + client_name = 'kolibri-1.2.5' + client_location = url + + videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({ + 'access_token': access_token, + 'client_location': client_location, + 'client_name': client_name, + 'ids': clip_id, + }) + + videos = self._download_json(videos_api_url, clip_id, 'Downloading videos JSON') + + duration = float(videos[0]['duration']) + source_ids = [source['id'] for source in videos[0]['sources']] + source_ids_str = ','.join(map(str, source_ids)) + + g = '01!8d8F_)r9]4s[qeuXfP%' + + client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]) + .encode('utf-8')).hexdigest() + + sources_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id, compat_urllib_parse.urlencode({ + 'access_token': access_token, + 'client_id': client_id, + 'client_location': client_location, + 'client_name': client_name, + })) + + sources = self._download_json(sources_api_url, clip_id, 'Downloading sources JSON') + server_id = sources['server_id'] + + client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id, + client_location, source_ids_str, g, client_name]) + .encode('utf-8')).hexdigest() + + url_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id, compat_urllib_parse.urlencode({ + 'access_token': access_token, + 'client_id': client_id, + 'client_location': client_location, + 'client_name': client_name, + 'server_id': server_id, + 'source_ids': source_ids_str, + })) + + urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON') + + title = extract(self._TITLE_REGEXES, 'title', page, fatal=True) + description = extract(self._DESCRIPTION_REGEXES, 'description', page) + thumbnail = self._og_search_thumbnail(page) + + upload_date = extract(self._UPLOAD_DATE_REGEXES, 'upload date', page) + if upload_date: + upload_date = unified_strdate(upload_date) + + formats = [] + + urls_sources = urls['sources'] + if isinstance(urls_sources, dict): + urls_sources = urls_sources.values() + + def fix_bitrate(bitrate): + return bitrate / 1000 if bitrate % 1000 == 0 else bitrate + + for source in urls_sources: + protocol = source['protocol'] + if protocol == 'rtmp' or protocol == 'rtmpe': + mobj = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', source['url']) + if not mobj: + continue + formats.append({ + 'url': mobj.group('url'), + 'app': mobj.group('app'), + 'play_path': mobj.group('playpath'), + 'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf', + 'page_url': 'http://www.prosieben.de', + 'vbr': fix_bitrate(source['bitrate']), + 'ext': 'mp4', + 'format_id': '%s_%s' % (source['cdn'], source['bitrate']), + }) + else: + formats.append({ + 'url': source['url'], + 'vbr': fix_bitrate(source['bitrate']), + }) + + self._sort_formats(formats) + + return { + 'id': clip_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index cd50f708d..4835ec5ec 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -1,148 +1,165 @@ # encoding: utf-8 - from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( - clean_html, ExtractorError, + clean_html, + unified_strdate, + int_or_none, ) class RTLnowIE(InfoExtractor): """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" - _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)' - _TESTS = [{ - 'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', - 'file': '90419.flv', - 'info_dict': { - 'upload_date': '20070416', - 'title': 'Ahornallee - Folge 1 - Der Einzug', - 'description': 'Folge 1 - Der Einzug', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Only works from Germany', - }, - { - 'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', - 'file': '69756.flv', - 'info_dict': { - 'upload_date': '20120519', - 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...', - 'description': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', - 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Only works from Germany', - }, - { - 'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', - 'file': '13883.flv', - 'info_dict': { - 'upload_date': '20090627', - 'title': 'Voxtours - Südafrika-Reporter II', - 'description': 'Südafrika-Reporter II', - }, - 'params': { - 'skip_download': True, + _VALID_URL = r'''(?x) + (?:https?://)? + (?P<url> + (?P<domain> + rtl-now\.rtl\.de| + rtl2now\.rtl2\.de| + (?:www\.)?voxnow\.de| + (?:www\.)?rtlnitronow\.de| + (?:www\.)?superrtlnow\.de| + (?:www\.)?n-tvnow\.de) + /+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\? + (?:container_id|film_id)=(?P<video_id>[0-9]+)& + player=1(?:&season=[0-9]+)?(?:&.*)? + )''' + + _TESTS = [ + { + 'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', + 'info_dict': { + 'id': '90419', + 'ext': 'flv', + 'title': 'Ahornallee - Folge 1 - Der Einzug', + 'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de', + 'upload_date': '20070416', + 'duration': 1685, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Only works from Germany', }, - }, - { - 'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', - 'file': '99205.flv', - 'info_dict': { - 'upload_date': '20080928', - 'title': 'Medicopter 117 - Angst!', - 'description': 'Angst!', - 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg' + { + 'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', + 'info_dict': { + 'id': '69756', + 'ext': 'flv', + 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', + 'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0', + 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', + 'upload_date': '20120519', + 'duration': 1245, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Only works from Germany', }, - 'params': { - 'skip_download': True, + { + 'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', + 'info_dict': { + 'id': '13883', + 'ext': 'flv', + 'title': 'Voxtours - Südafrika-Reporter II', + 'description': 'md5:de7f8d56be6fd4fed10f10f57786db00', + 'upload_date': '20090627', + 'duration': 1800, + }, + 'params': { + 'skip_download': True, + }, }, - }, - { - 'url': 'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10', - 'file': '124903.flv', - 'info_dict': { - 'upload_date': '20130101', - 'title': 'Top Gear vom 01.01.2013', - 'description': 'Episode 1', + { + 'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', + 'info_dict': { + 'id': '99205', + 'ext': 'flv', + 'title': 'Medicopter 117 - Angst!', + 'description': 'md5:895b1df01639b5f61a04fc305a5cb94d', + 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg', + 'upload_date': '20080928', + 'duration': 2691, + }, + 'params': { + 'skip_download': True, + }, }, - 'params': { - 'skip_download': True, + { + 'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0', + 'info_dict': { + 'id': '153819', + 'ext': 'flv', + 'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner', + 'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631', + 'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg', + 'upload_date': '20140221', + 'duration': 2429, + }, + 'skip': 'Only works from Germany', }, - 'skip': 'Only works from Germany', - }] + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - - webpage_url = 'http://' + mobj.group('url') - video_page_url = 'http://' + mobj.group('domain') + '/' + video_page_url = 'http://%s/' % mobj.group('domain') video_id = mobj.group('video_id') - webpage = self._download_webpage(webpage_url, video_id) + webpage = self._download_webpage('http://' + mobj.group('url'), video_id) - note_m = re.search(r'''(?sx) - <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?) - <div[ ]id="playerteaser">''', webpage) - if note_m: - msg = clean_html(note_m.group(1)) - raise ExtractorError(msg) + mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage) + if mobj: + raise ExtractorError(clean_html(mobj.group(1)), expected=True) - video_title = self._html_search_regex( - r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>', - webpage, 'title') - playerdata_url = self._html_search_regex( - r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'', - webpage, 'playerdata_url') + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage, default=None) - playerdata = self._download_webpage(playerdata_url, video_id) - mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]></title>', playerdata) - if mobj: - video_description = mobj.group('description') - if mobj.group('upload_date_Y'): - video_upload_date = mobj.group('upload_date_Y') - elif mobj.group('upload_date_y'): - video_upload_date = '20' + mobj.group('upload_date_y') - else: - video_upload_date = None - if video_upload_date: - video_upload_date += mobj.group('upload_date_m') + mobj.group('upload_date_d') - else: - video_description = None - video_upload_date = None - self._downloader.report_warning('Unable to extract description and upload date') + upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date')) - # Thumbnail: not every video has an thumbnail - mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage) - if mobj: - video_thumbnail = mobj.group('thumbnail') - else: - video_thumbnail = None + mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage) + duration = int(mobj.group('seconds')) if mobj else None - mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata) - if mobj is None: - raise ExtractorError('Unable to extract media URL') - video_url = mobj.group('url') - video_play_path = 'mp4:' + mobj.group('play_path') - video_player_url = video_page_url + 'includes/vodplayer.swf' + playerdata_url = self._html_search_regex( + r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url') + + playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML') + + videoinfo = playerdata.find('./playlist/videoinfo') + + formats = [] + for filename in videoinfo.findall('filename'): + mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text) + if mobj: + fmt = { + 'url': mobj.group('url'), + 'play_path': 'mp4:' + mobj.group('play_path'), + 'page_url': video_page_url, + 'player_url': video_page_url + 'includes/vodplayer.swf', + } + else: + fmt = { + 'url': filename.text, + } + fmt.update({ + 'width': int_or_none(filename.get('width')), + 'height': int_or_none(filename.get('height')), + 'vbr': int_or_none(filename.get('bitrate')), + 'ext': 'flv', + }) + formats.append(fmt) return { 'id': video_id, - 'url': video_url, - 'play_path': video_play_path, - 'page_url': video_page_url, - 'player_url': video_player_url, - 'ext': 'flv', - 'title': video_title, - 'description': video_description, - 'upload_date': video_upload_date, - 'thumbnail': video_thumbnail, - } + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index c5ee84807..10c3d992d 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -221,7 +221,9 @@ class VimeoIE(SubtitlesInfoExtractor): # Extract video thumbnail video_thumbnail = config["video"].get("thumbnail") if video_thumbnail is None: - _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in config["video"]["thumbs"].items())[-1] + video_thumbs = config["video"].get("thumbs") + if video_thumbs and isinstance(video_thumbs, dict): + _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description video_description = None diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index a75e1380d..5374495f9 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -103,6 +103,7 @@ class XHamsterIE(InfoExtractor): }] if not hd: + mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url') webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage') if is_hd(webpage): video_url = extract_video_url(webpage) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 0c482631a..02b8f7c45 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -772,6 +772,7 @@ def unified_strdate(date_str): '%B %d %Y', '%b %d %Y', '%Y-%m-%d', + '%d.%m.%Y', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S', diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 00b1ba0d9..c53f1c417 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,2 @@ -__version__ = '2014.02.26' +__version__ = '2014.02.27.1' |