diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/beeg.py | 24 | ||||
| -rw-r--r-- | youtube_dl/extractor/dailymotion.py | 21 | ||||
| -rw-r--r-- | youtube_dl/extractor/funimation.py | 187 | ||||
| -rw-r--r-- | youtube_dl/extractor/ooyala.py | 25 | ||||
| -rw-r--r-- | youtube_dl/extractor/pbs.py | 321 | ||||
| -rw-r--r-- | youtube_dl/extractor/safari.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/vevo.py | 76 | ||||
| -rw-r--r-- | youtube_dl/extractor/wdr.py | 58 |
9 files changed, 499 insertions, 218 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3db5cd6d9..3cd95ba01 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -206,6 +206,7 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freevideo import FreeVideoIE +from .funimation import FunimationIE from .funnyordie import FunnyOrDieIE from .gameinformer import GameInformerIE from .gamekings import GamekingsIE diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index d151d38c9..c8d921daf 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -34,15 +34,29 @@ class BeegIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://beeg.com/api/v4/video/%s' % video_id, video_id) + 'http://beeg.com/api/v5/video/%s' % video_id, video_id) + + def split(o, e): + def cut(s, x): + n.append(s[:x]) + return s[x:] + n = [] + r = len(o) % e + if r > 0: + o = cut(o, r) + while len(o) > e: + o = cut(o, e) + n.append(o) + return n def decrypt_key(key): - # Reverse engineered from http://static.beeg.com/cpl/1067.js - a = '8RPUUCS35ZWp3ADnKcSmpH71ZusrROo' + # Reverse engineered from http://static.beeg.com/cpl/1105.js + a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB' e = compat_urllib_parse_unquote(key) - return ''.join([ - compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 25) + o = ''.join([ + compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) for n in range(len(e))]) + return ''.join(split(o, 3)[::-1]) def decrypt_url(encrypted_url): encrypted_url = self._proto_relative_url( diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index ab7f3aec4..428556213 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -99,6 +99,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor): { 'url': 'http://www.dailymotion.com/video/xhza0o', 'only_matching': True, + }, + # with subtitles + { + 'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news', + 'only_matching': True, } ] @@ -122,7 +127,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor): webpage, 'comment count', fatal=False)) player_v5 = self._search_regex( - [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'], + [r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826 + r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', + r'buildPlayer\(({.+?})\);'], webpage, 'player v5', default=None) if player_v5: player = self._parse_json(player_v5, video_id) @@ -172,11 +179,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): uploader_id = metadata.get('owner', {}).get('id') subtitles = {} - for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items(): - subtitles[subtitle_lang] = [{ - 'ext': determine_ext(subtitle_url), - 'url': subtitle_url, - } for subtitle_url in subtitle.get('urls', [])] + subtitles_data = metadata.get('subtitles', {}).get('data', {}) + if subtitles_data and isinstance(subtitles_data, dict): + for subtitle_lang, subtitle in subtitles_data.items(): + subtitles[subtitle_lang] = [{ + 'ext': determine_ext(subtitle_url), + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] return { 'id': video_id, diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py new file mode 100644 index 000000000..8a65343c5 --- /dev/null +++ b/youtube_dl/extractor/funimation.py @@ -0,0 +1,187 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + determine_ext, + encode_dict, + int_or_none, + sanitized_Request, + ExtractorError, + urlencode_postdata +) + + +class FunimationIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://www.funimation.com/shows/air/videos/official/breeze', + 'info_dict': { + 'id': '658', + 'display_id': 'breeze', + 'ext': 'mp4', + 'title': 'Air - 1 - Breeze', + 'description': 'md5:1769f43cd5fc130ace8fd87232207892', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play', + 'info_dict': { + 'id': '31128', + 'display_id': 'role-play', + 'ext': 'mp4', + 'title': '.hack//SIGN - 1 - Role Play', + 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd', + 'thumbnail': 're:https?://.*\.jpg', + }, + }, { + 'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview', + 'info_dict': { + 'id': '9635', + 'display_id': 'broadcast-dub-preview', + 'ext': 'mp4', + 'title': 'Attack on Titan: Junior High - Broadcast Dub Preview', + 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803', + 'thumbnail': 're:https?://.*\.(?:jpg|png)', + }, + }] + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + data = urlencode_postdata(encode_dict({ + 'email_field': username, + 'password_field': password, + })) + login_request = sanitized_Request('http://www.funimation.com/login', data, headers={ + 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0', + 'Content-Type': 'application/x-www-form-urlencoded' + }) + login = self._download_webpage( + login_request, None, 'Logging in as %s' % username) + if re.search(r'<meta property="og:url" content="http://www.funimation.com/login"/>', login) is not None: + raise ExtractorError('Unable to login, wrong username or password.', expected=True) + + def _real_initialize(self): + self._login() + + def _real_extract(self, url): + display_id = self._match_id(url) + + errors = [] + formats = [] + + ERRORS_MAP = { + 'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn', + 'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut', + 'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut', + 'ERROR_VIDEO_EXPIRED': 'videoExpired', + 'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable', + 'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription', + 'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription', + 'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding', + 'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN', + 'ERROR_STREAM_NOT_FOUND': 'streamNotFound', + } + + USER_AGENTS = ( + # PC UA is served with m3u8 that provides some bonus lower quality formats + ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'), + # Mobile UA allows to extract direct links and also does not fail when + # PC UA fails with hulu error (e.g. + # http://www.funimation.com/shows/hacksign/videos/official/role-play) + ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'), + ) + + for kind, user_agent in USER_AGENTS: + request = sanitized_Request(url) + request.add_header('User-Agent', user_agent) + webpage = self._download_webpage( + request, display_id, 'Downloading %s webpage' % kind) + + playlist = self._parse_json( + self._search_regex( + r'var\s+playersData\s*=\s*(\[.+?\]);\n', + webpage, 'players data'), + display_id)[0]['playlist'] + + items = next(item['items'] for item in playlist if item.get('items')) + item = next(item for item in items if item.get('itemAK') == display_id) + + error_messages = {} + video_error_messages = self._search_regex( + r'var\s+videoErrorMessages\s*=\s*({.+?});\n', + webpage, 'error messages', default=None) + if video_error_messages: + error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False) + if error_messages_json: + for _, error in error_messages_json.items(): + type_ = error.get('type') + description = error.get('description') + content = error.get('content') + if type_ == 'text' and description and content: + error_message = ERRORS_MAP.get(description) + if error_message: + error_messages[error_message] = content + + for video in item.get('videoSet', []): + auth_token = video.get('authToken') + if not auth_token: + continue + funimation_id = video.get('FUNImationID') or video.get('videoId') + preference = 1 if video.get('languageMode') == 'dub' else 0 + if not auth_token.startswith('?'): + auth_token = '?%s' % auth_token + for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)): + format_url = video.get('%sUrl' % quality) + if not format_url: + continue + if not format_url.startswith(('http', '//')): + errors.append(format_url) + continue + if determine_ext(format_url) == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native', + preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + else: + tbr = int_or_none(self._search_regex( + r'-(\d+)[Kk]', format_url, 'tbr', default=None)) + formats.append({ + 'url': format_url + auth_token, + 'format_id': '%s-http-%dp' % (funimation_id, height), + 'height': height, + 'tbr': tbr, + 'preference': preference, + }) + + if not formats and errors: + raise ExtractorError( + '%s returned error: %s' + % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))), + expected=True) + + self._sort_formats(formats) + + title = item['title'] + artist = item.get('artist') + if artist: + title = '%s - %s' % (artist, title) + description = self._og_search_description(webpage) or item.get('description') + thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl') + video_id = item.get('itemId') or display_id + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 35067e271..8603fd692 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -27,6 +27,7 @@ class OoyalaBaseIE(InfoExtractor): 'duration': float_or_none(metadata.get('duration'), 1000), } + urls = [] formats = [] for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'): auth_data = self._download_json( @@ -38,20 +39,28 @@ class OoyalaBaseIE(InfoExtractor): if cur_auth_data['authorized']: for stream in cur_auth_data['streams']: url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8') + if url in urls: + continue + urls.append(url) delivery_type = stream['delivery_type'] - if delivery_type == 'remote_asset': - video_info['url'] = url - return video_info - if delivery_type == 'hls': - formats.extend(self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - elif delivery_type == 'hds': - formats.extend(self._extract_f4m_formats(url, embed_code, -1, 'hds', fatal=False)) + if delivery_type == 'hls' or '.m3u8' in url: + m3u8_formats = self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif delivery_type == 'hds' or '.f4m' in url: + f4m_formats = self._extract_f4m_formats(url, embed_code, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + elif '.smil' in url: + smil_formats = self._extract_smil_formats(url, embed_code, fatal=False) + if smil_formats: + formats.extend(smil_formats) else: formats.append({ 'url': url, 'ext': stream.get('delivery_type'), 'vcodec': stream.get('video_codec'), - 'format_id': '%s-%s-%sp' % (stream.get('profile'), delivery_type, stream.get('height')), + 'format_id': delivery_type, 'width': int_or_none(stream.get('width')), 'height': int_or_none(stream.get('height')), 'abr': int_or_none(stream.get('audio_bitrate')), diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index d71d7eb76..604a0dd22 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -16,164 +16,165 @@ from ..utils import ( class PBSIE(InfoExtractor): _STATIONS = ( - ('aptv.org', 'APT - Alabama Public Television (WBIQ)'), # http://aptv.org/ - ('gpb.org', 'GPB/Georgia Public Broadcasting (WGTV)'), # http://www.gpb.org/ - ('mpbonline.org', 'Mississippi Public Broadcasting (WMPN)'), # http://www.mpbonline.org - ('wnpt.org', 'Nashville Public Television (WNPT)'), # http://www.wnpt.org - ('wfsu.org', 'WFSU-TV (WFSU)'), # http://wfsu.org/ - ('wsre.org', 'WSRE (WSRE)'), # http://www.wsre.org - ('wtcitv.org', 'WTCI (WTCI)'), # http://www.wtcitv.org - ('pba.org', 'WPBA/Channel 30 (WPBA)'), # http://pba.org/ - ('alaskapublic.org', 'Alaska Public Media (KAKM)'), # http://alaskapublic.org/kakm - ('kuac.org', 'KUAC (KUAC)'), # http://kuac.org/kuac-tv/ - ('ktoo.org', '360 North (KTOO)'), # http://www.ktoo.org/ - ('azpm.org', 'KUAT 6 (KUAT)'), # http://www.azpm.org/ - ('azpbs.org', 'Arizona PBS (KAET)'), # http://www.azpbs.org - ('newmexicopbs.org', 'KNME-TV/Channel 5 (KNME)'), # http://www.newmexicopbs.org/ - ('vegaspbs.org', 'Vegas PBS (KLVX)'), # http://vegaspbs.org/ - ('aetn.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'), # http://www.aetn.org/ - ('ket.org', 'KET (WKLE)'), # http://www.ket.org/ - ('wkno.org', 'WKNO/Channel 10 (WKNO)'), # http://www.wkno.org/ - ('lpb.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'), # http://www.lpb.org/ - ('oeta.tv', 'OETA (KETA)'), # http://www.oeta.tv - ('optv.org', 'Ozarks Public Television (KOZK)'), # http://www.optv.org/ - ('wsiu.org', 'WSIU Public Broadcasting (WSIU)'), # http://www.wsiu.org/ - ('keet.org', 'KEET TV (KEET)'), # http://www.keet.org - ('kixe.org', 'KIXE/Channel 9 (KIXE)'), # http://kixe.org/ - ('kpbs.org', 'KPBS San Diego (KPBS)'), # http://www.kpbs.org/ - ('kqed.org', 'KQED (KQED)'), # http://www.kqed.org - ('kvie.org', 'KVIE Public Television (KVIE)'), # http://www.kvie.org - ('pbssocal.org', 'PBS SoCal/KOCE (KOCE)'), # http://www.pbssocal.org/ - ('valleypbs.org', 'ValleyPBS (KVPT)'), # http://www.valleypbs.org/ - ('cptv.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'), # http://cptv.org - ('knpb.org', 'KNPB Channel 5 (KNPB)'), # http://www.knpb.org/ - ('soptv.org', 'SOPTV (KSYS)'), # http://www.soptv.org - ('klcs.org', 'KLCS/Channel 58 (KLCS)'), # http://www.klcs.org - ('krcb.org', 'KRCB Television & Radio (KRCB)'), # http://www.krcb.org - ('kvcr.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'), # http://kvcr.org - ('rmpbs.org', 'Rocky Mountain PBS (KRMA)'), # http://www.rmpbs.org - ('kenw.org', 'KENW-TV3 (KENW)'), # http://www.kenw.org - ('kued.org', 'KUED Channel 7 (KUED)'), # http://www.kued.org - ('wyomingpbs.org', 'Wyoming PBS (KCWC)'), # http://www.wyomingpbs.org - ('cpt12.org', 'Colorado Public Television / KBDI 12 (KBDI)'), # http://www.cpt12.org/ - ('kbyutv.org', 'KBYU-TV (KBYU)'), # http://www.kbyutv.org/ - ('thirteen.org', 'Thirteen/WNET New York (WNET)'), # http://www.thirteen.org - ('wgbh.org', 'WGBH/Channel 2 (WGBH)'), # http://wgbh.org - ('wgby.org', 'WGBY (WGBY)'), # http://www.wgby.org - ('njtvonline.org', 'NJTV Public Media NJ (WNJT)'), # http://www.njtvonline.org/ - ('ripbs.org', 'Rhode Island PBS (WSBE)'), # http://www.ripbs.org/home/ - ('wliw.org', 'WLIW21 (WLIW)'), # http://www.wliw.org/ - ('mpt.org', 'mpt/Maryland Public Television (WMPB)'), # http://www.mpt.org - ('weta.org', 'WETA Television and Radio (WETA)'), # http://www.weta.org - ('whyy.org', 'WHYY (WHYY)'), # http://www.whyy.org - ('wlvt.org', 'PBS 39 (WLVT)'), # http://www.wlvt.org/ - ('wvpt.net', 'WVPT - Your Source for PBS and More! (WVPT)'), # http://www.wvpt.net - ('whut.org', 'Howard University Television (WHUT)'), # http://www.whut.org - ('wedu.org', 'WEDU PBS (WEDU)'), # http://www.wedu.org - ('wgcu.org', 'WGCU Public Media (WGCU)'), # http://www.wgcu.org/ - ('wjct.org', 'WJCT Public Broadcasting (WJCT)'), # http://www.wjct.org - ('wpbt2.org', 'WPBT2 (WPBT)'), # http://www.wpbt2.org - ('wucftv.org', 'WUCF TV (WUCF)'), # http://wucftv.org - ('wuft.org', 'WUFT/Channel 5 (WUFT)'), # http://www.wuft.org - ('wxel.org', 'WXEL/Channel 42 (WXEL)'), # http://www.wxel.org/home/ - ('wlrn.org', 'WLRN/Channel 17 (WLRN)'), # http://www.wlrn.org/ - ('wusf.org', 'WUSF Public Broadcasting (WUSF)'), # http://wusf.org/ - ('scetv.org', 'ETV (WRLK)'), # http://www.scetv.org - ('unctv.org', 'UNC-TV (WUNC)'), # http://www.unctv.org/ - ('pbsguam.org', 'PBS Guam (KGTF)'), # http://www.pbsguam.org/ - ('pbshawaii.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'), # http://www.pbshawaii.org/ - ('idahoptv.org', 'Idaho Public Television (KAID)'), # http://idahoptv.org - ('ksps.org', 'KSPS (KSPS)'), # http://www.ksps.org/home/ - ('opb.org', 'OPB (KOPB)'), # http://www.opb.org - ('kwsu.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'), # http://www.kwsu.org - ('illinois.edu', 'WILL-TV (WILL)'), # http://will.illinois.edu/ - ('wsec.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'), # http://www.wsec.tv - ('wttw.com', 'WTTW11 (WTTW)'), # http://www.wttw.com/ - ('wtvp.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'), # http://www.wtvp.org/ - ('iptv.org', 'Iowa Public Television/IPTV (KDIN)'), # http://www.iptv.org/ - ('ninenet.org', 'Nine Network (KETC)'), # http://www.ninenet.org - ('wfwa.org', 'PBS39 Fort Wayne (WFWA)'), # http://wfwa.org/ - ('wfyi.org', 'WFYI Indianapolis (WFYI)'), # http://www.wfyi.org - ('mptv.org', 'Milwaukee Public Television (WMVS)'), # http://www.mptv.org - ('wnin.org', 'WNIN (WNIN)'), # http://www.wnin.org/ - ('wnit.org', 'WNIT Public Television (WNIT)'), # http://www.wnit.org/ - ('wpt.org', 'WPT (WPNE)'), # http://www.wpt.org/ - ('wvut.org', 'WVUT/Channel 22 (WVUT)'), # http://wvut.org/ - ('weiu.net', 'WEIU/Channel 51 (WEIU)'), # http://www.weiu.net - ('wqpt.org', 'WQPT-TV (WQPT)'), # http://www.wqpt.org - ('wycc.org', 'WYCC PBS Chicago (WYCC)'), # http://www.wycc.org - ('lakeshorepublicmedia.org', 'Lakeshore Public Television (WYIN)'), # http://lakeshorepublicmedia.org/ - ('wipb.org', 'WIPB-TV (WIPB)'), # http://wipb.org - ('indianapublicmedia.org', 'WTIU (WTIU)'), # http://indianapublicmedia.org/tv/ - ('cetconnect.org', 'CET (WCET)'), # http://www.cetconnect.org - ('thinktv.org', 'ThinkTVNetwork (WPTD)'), # http://www.thinktv.org - ('wbgu.org', 'WBGU-TV (WBGU)'), # http://wbgu.org - ('wgvu.org', 'WGVU TV (WGVU)'), # http://www.wgvu.org/ - ('netnebraska.org', 'NET1 (KUON)'), # http://netnebraska.org - ('pioneer.org', 'Pioneer Public Television (KWCM)'), # http://www.pioneer.org - ('sdpb.org', 'SDPB Television (KUSD)'), # http://www.sdpb.org - ('tpt.org', 'TPT (KTCA)'), # http://www.tpt.org - ('ksmq.org', 'KSMQ (KSMQ)'), # http://www.ksmq.org/ - ('kpts.org', 'KPTS/Channel 8 (KPTS)'), # http://www.kpts.org/ - ('ktwu.org', 'KTWU/Channel 11 (KTWU)'), # http://ktwu.org - ('shptv.org', 'Smoky Hills Public Television (KOOD)'), # http://www.shptv.org - ('kcpt.org', 'KCPT Kansas City Public Television (KCPT)'), # http://kcpt.org/ - ('blueridgepbs.org', 'Blue Ridge PBS (WBRA)'), # http://www.blueridgepbs.org/ - ('easttennesseepbs.org', 'East Tennessee PBS (WSJK)'), # http://easttennesseepbs.org - ('wcte.org', 'WCTE-TV (WCTE)'), # http://www.wcte.org - ('wljt.org', 'WLJT, Channel 11 (WLJT)'), # http://wljt.org/ - ('wosu.org', 'WOSU TV (WOSU)'), # http://wosu.org/ - ('woub.org', 'WOUB/WOUC (WOUB)'), # http://woub.org/tv/index.php?section=5 - ('wvpublic.org', 'WVPB (WVPB)'), # http://wvpublic.org/ - ('wkyupbs.org', 'WKYU-PBS (WKYU)'), # http://www.wkyupbs.org - ('wyes.org', 'WYES-TV/New Orleans (WYES)'), # http://www.wyes.org - ('kera.org', 'KERA 13 (KERA)'), # http://www.kera.org/ - ('mpbn.net', 'MPBN (WCBB)'), # http://www.mpbn.net/ - ('mountainlake.org', 'Mountain Lake PBS (WCFE)'), # http://www.mountainlake.org/ - ('nhptv.org', 'NHPTV (WENH)'), # http://nhptv.org/ - ('vpt.org', 'Vermont PBS (WETK)'), # http://www.vpt.org - ('witf.org', 'witf (WITF)'), # http://www.witf.org - ('wqed.org', 'WQED Multimedia (WQED)'), # http://www.wqed.org/ - ('wmht.org', 'WMHT Educational Telecommunications (WMHT)'), # http://www.wmht.org/home/ - ('deltabroadcasting.org', 'Q-TV (WDCQ)'), # http://www.deltabroadcasting.org - ('dptv.org', 'WTVS Detroit Public TV (WTVS)'), # http://www.dptv.org/ - ('wcmu.org', 'CMU Public Television (WCMU)'), # http://www.wcmu.org - ('wkar.org', 'WKAR-TV (WKAR)'), # http://wkar.org/ - ('nmu.edu', 'WNMU-TV Public TV 13 (WNMU)'), # http://wnmutv.nmu.edu - ('wdse.org', 'WDSE - WRPT (WDSE)'), # http://www.wdse.org/ - ('wgte.org', 'WGTE TV (WGTE)'), # http://www.wgte.org - ('lakelandptv.org', 'Lakeland Public Television (KAWE)'), # http://www.lakelandptv.org - ('prairiepublic.org', 'PRAIRIE PUBLIC (KFME)'), # http://www.prairiepublic.org/ - ('kmos.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'), # http://www.kmos.org/ - ('montanapbs.org', 'MontanaPBS (KUSM)'), # http://montanapbs.org - ('krwg.org', 'KRWG/Channel 22 (KRWG)'), # http://www.krwg.org - ('panhandlepbs.org', 'KACV (KACV)'), # http://www.panhandlepbs.org/home/ - ('kcostv.org', 'KCOS/Channel 13 (KCOS)'), # www.kcostv.org - ('wcny.org', 'WCNY/Channel 24 (WCNY)'), # http://www.wcny.org - ('wned.org', 'WNED (WNED)'), # http://www.wned.org/ - ('wpbstv.org', 'WPBS (WPBS)'), # http://www.wpbstv.org - ('wskg.org', 'WSKG Public TV (WSKG)'), # http://wskg.org - ('wxxi.org', 'WXXI (WXXI)'), # http://wxxi.org - ('wpsu.org', 'WPSU (WPSU)'), # http://www.wpsu.org - ('wqln.org', 'WQLN/Channel 54 (WQLN)'), # http://www.wqln.org - ('wvia.org', 'WVIA Public Media Studios (WVIA)'), # http://www.wvia.org/ - ('wtvi.org', 'WTVI (WTVI)'), # http://www.wtvi.org/ - ('whro.org', 'WHRO (WHRO)'), # http://whro.org - ('westernreservepublicmedia.org', 'Western Reserve PBS (WNEO)'), # http://www.WesternReservePublicMedia.org/ - ('wviz.org', 'WVIZ/PBS ideastream (WVIZ)'), # http://www.wviz.org/ - ('kcts9.org', 'KCTS 9 (KCTS)'), # http://kcts9.org/ - ('basinpbs.org', 'Basin PBS (KPBT)'), # http://www.basinpbs.org - ('houstonpublicmedia.org', 'KUHT / Channel 8 (KUHT)'), # http://www.houstonpublicmedia.org/ - ('tamu.edu', 'KAMU - TV (KAMU)'), # http://KAMU.tamu.edu - ('kedt.org', 'KEDT/Channel 16 (KEDT)'), # http://www.kedt.org - ('klrn.org', 'KLRN (KLRN)'), # http://www.klrn.org - ('klru.org', 'KLRU (KLRU)'), # http://www.klru.org - ('kmbh.org', 'KMBH-TV (KMBH)'), # http://www.kmbh.org - ('knct.org', 'KNCT (KNCT)'), # http://www.knct.org - ('ktxt.org', 'KTTZ-TV (KTXT)'), # http://www.ktxt.org - ('wtjx.org', 'WTJX Channel 12 (WTJX)'), # http://www.wtjx.org/ - ('ideastations.org', 'WCVE PBS (WCVE)'), # http://ideastations.org/ - ('kbtc.org', 'KBTC Public Television (KBTC)'), # http://kbtc.org + ('video.pbs.org', 'PBS: Public Broadcasting Service'), # http://www.pbs.org/ + ('video.aptv.org', 'APT - Alabama Public Television (WBIQ)'), # http://aptv.org/ + ('video.gpb.org', 'GPB/Georgia Public Broadcasting (WGTV)'), # http://www.gpb.org/ + ('video.mpbonline.org', 'Mississippi Public Broadcasting (WMPN)'), # http://www.mpbonline.org + ('video.wnpt.org', 'Nashville Public Television (WNPT)'), # http://www.wnpt.org + ('video.wfsu.org', 'WFSU-TV (WFSU)'), # http://wfsu.org/ + ('video.wsre.org', 'WSRE (WSRE)'), # http://www.wsre.org + ('video.wtcitv.org', 'WTCI (WTCI)'), # http://www.wtcitv.org + ('video.pba.org', 'WPBA/Channel 30 (WPBA)'), # http://pba.org/ + ('video.alaskapublic.org', 'Alaska Public Media (KAKM)'), # http://alaskapublic.org/kakm + # ('kuac.org', 'KUAC (KUAC)'), # http://kuac.org/kuac-tv/ + # ('ktoo.org', '360 North (KTOO)'), # http://www.ktoo.org/ + # ('azpm.org', 'KUAT 6 (KUAT)'), # http://www.azpm.org/ + ('video.azpbs.org', 'Arizona PBS (KAET)'), # http://www.azpbs.org + ('portal.knme.org', 'KNME-TV/Channel 5 (KNME)'), # http://www.newmexicopbs.org/ + ('video.vegaspbs.org', 'Vegas PBS (KLVX)'), # http://vegaspbs.org/ + ('watch.aetn.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'), # http://www.aetn.org/ + ('video.ket.org', 'KET (WKLE)'), # http://www.ket.org/ + ('video.wkno.org', 'WKNO/Channel 10 (WKNO)'), # http://www.wkno.org/ + ('video.lpb.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'), # http://www.lpb.org/ + ('videos.oeta.tv', 'OETA (KETA)'), # http://www.oeta.tv + ('video.optv.org', 'Ozarks Public Television (KOZK)'), # http://www.optv.org/ + ('watch.wsiu.org', 'WSIU Public Broadcasting (WSIU)'), # http://www.wsiu.org/ + ('video.keet.org', 'KEET TV (KEET)'), # http://www.keet.org + ('pbs.kixe.org', 'KIXE/Channel 9 (KIXE)'), # http://kixe.org/ + ('video.kpbs.org', 'KPBS San Diego (KPBS)'), # http://www.kpbs.org/ + ('video.kqed.org', 'KQED (KQED)'), # http://www.kqed.org + ('vids.kvie.org', 'KVIE Public Television (KVIE)'), # http://www.kvie.org + ('video.pbssocal.org', 'PBS SoCal/KOCE (KOCE)'), # http://www.pbssocal.org/ + ('video.valleypbs.org', 'ValleyPBS (KVPT)'), # http://www.valleypbs.org/ + ('video.cptv.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'), # http://cptv.org + ('watch.knpb.org', 'KNPB Channel 5 (KNPB)'), # http://www.knpb.org/ + ('video.soptv.org', 'SOPTV (KSYS)'), # http://www.soptv.org + # ('klcs.org', 'KLCS/Channel 58 (KLCS)'), # http://www.klcs.org + # ('krcb.org', 'KRCB Television & Radio (KRCB)'), # http://www.krcb.org + # ('kvcr.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'), # http://kvcr.org + ('video.rmpbs.org', 'Rocky Mountain PBS (KRMA)'), # http://www.rmpbs.org + ('video.kenw.org', 'KENW-TV3 (KENW)'), # http://www.kenw.org + ('video.kued.org', 'KUED Channel 7 (KUED)'), # http://www.kued.org + ('video.wyomingpbs.org', 'Wyoming PBS (KCWC)'), # http://www.wyomingpbs.org + ('video.cpt12.org', 'Colorado Public Television / KBDI 12 (KBDI)'), # http://www.cpt12.org/ + ('video.kbyueleven.org', 'KBYU-TV (KBYU)'), # http://www.kbyutv.org/ + ('video.thirteen.org', 'Thirteen/WNET New York (WNET)'), # http://www.thirteen.org + ('video.wgbh.org', 'WGBH/Channel 2 (WGBH)'), # http://wgbh.org + ('video.wgby.org', 'WGBY (WGBY)'), # http://www.wgby.org + ('watch.njtvonline.org', 'NJTV Public Media NJ (WNJT)'), # http://www.njtvonline.org/ + # ('ripbs.org', 'Rhode Island PBS (WSBE)'), # http://www.ripbs.org/home/ + ('watch.wliw.org', 'WLIW21 (WLIW)'), # http://www.wliw.org/ + ('video.mpt.tv', 'mpt/Maryland Public Television (WMPB)'), # http://www.mpt.org + ('watch.weta.org', 'WETA Television and Radio (WETA)'), # http://www.weta.org + ('video.whyy.org', 'WHYY (WHYY)'), # http://www.whyy.org + ('video.wlvt.org', 'PBS 39 (WLVT)'), # http://www.wlvt.org/ + ('video.wvpt.net', 'WVPT - Your Source for PBS and More! (WVPT)'), # http://www.wvpt.net + ('video.whut.org', 'Howard University Television (WHUT)'), # http://www.whut.org + ('video.wedu.org', 'WEDU PBS (WEDU)'), # http://www.wedu.org + ('video.wgcu.org', 'WGCU Public Media (WGCU)'), # http://www.wgcu.org/ + # ('wjct.org', 'WJCT Public Broadcasting (WJCT)'), # http://www.wjct.org + ('video.wpbt2.org', 'WPBT2 (WPBT)'), # http://www.wpbt2.org + ('video.wucftv.org', 'WUCF TV (WUCF)'), # http://wucftv.org + ('video.wuft.org', 'WUFT/Channel 5 (WUFT)'), # http://www.wuft.org + ('watch.wxel.org', 'WXEL/Channel 42 (WXEL)'), # http://www.wxel.org/home/ + ('video.wlrn.org', 'WLRN/Channel 17 (WLRN)'), # http://www.wlrn.org/ + ('video.wusf.usf.edu', 'WUSF Public Broadcasting (WUSF)'), # http://wusf.org/ + ('video.scetv.org', 'ETV (WRLK)'), # http://www.scetv.org + ('video.unctv.org', 'UNC-TV (WUNC)'), # http://www.unctv.org/ + # ('pbsguam.org', 'PBS Guam (KGTF)'), # http://www.pbsguam.org/ + ('video.pbshawaii.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'), # http://www.pbshawaii.org/ + ('video.idahoptv.org', 'Idaho Public Television (KAID)'), # http://idahoptv.org + ('video.ksps.org', 'KSPS (KSPS)'), # http://www.ksps.org/home/ + ('watch.opb.org', 'OPB (KOPB)'), # http://www.opb.org + ('watch.nwptv.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'), # http://www.kwsu.org + ('video.will.illinois.edu', 'WILL-TV (WILL)'), # http://will.illinois.edu/ + ('video.networkknowledge.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'), # http://www.wsec.tv + ('video.wttw.com', 'WTTW11 (WTTW)'), # http://www.wttw.com/ + # ('wtvp.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'), # http://www.wtvp.org/ + ('video.iptv.org', 'Iowa Public Television/IPTV (KDIN)'), # http://www.iptv.org/ + ('video.ninenet.org', 'Nine Network (KETC)'), # http://www.ninenet.org + ('video.wfwa.org', 'PBS39 Fort Wayne (WFWA)'), # http://wfwa.org/ + ('video.wfyi.org', 'WFYI Indianapolis (WFYI)'), # http://www.wfyi.org + ('video.mptv.org', 'Milwaukee Public Television (WMVS)'), # http://www.mptv.org + ('video.wnin.org', 'WNIN (WNIN)'), # http://www.wnin.org/ + ('video.wnit.org', 'WNIT Public Television (WNIT)'), # http://www.wnit.org/ + ('video.wpt.org', 'WPT (WPNE)'), # http://www.wpt.org/ + ('video.wvut.org', 'WVUT/Channel 22 (WVUT)'), # http://wvut.org/ + ('video.weiu.net', 'WEIU/Channel 51 (WEIU)'), # http://www.weiu.net + ('video.wqpt.org', 'WQPT-TV (WQPT)'), # http://www.wqpt.org + ('video.wycc.org', 'WYCC PBS Chicago (WYCC)'), # http://www.wycc.org + # ('lakeshorepublicmedia.org', 'Lakeshore Public Television (WYIN)'), # http://lakeshorepublicmedia.org/ + ('video.wipb.org', 'WIPB-TV (WIPB)'), # http://wipb.org + ('video.indianapublicmedia.org', 'WTIU (WTIU)'), # http://indianapublicmedia.org/tv/ + ('watch.cetconnect.org', 'CET (WCET)'), # http://www.cetconnect.org + ('video.thinktv.org', 'ThinkTVNetwork (WPTD)'), # http://www.thinktv.org + ('video.wbgu.org', 'WBGU-TV (WBGU)'), # http://wbgu.org + ('video.wgvu.org', 'WGVU TV (WGVU)'), # http://www.wgvu.org/ + ('video.netnebraska.org', 'NET1 (KUON)'), # http://netnebraska.org + ('video.pioneer.org', 'Pioneer Public Television (KWCM)'), # http://www.pioneer.org + ('watch.sdpb.org', 'SDPB Television (KUSD)'), # http://www.sdpb.org + ('video.tpt.org', 'TPT (KTCA)'), # http://www.tpt.org + ('watch.ksmq.org', 'KSMQ (KSMQ)'), # http://www.ksmq.org/ + ('watch.kpts.org', 'KPTS/Channel 8 (KPTS)'), # http://www.kpts.org/ + ('watch.ktwu.org', 'KTWU/Channel 11 (KTWU)'), # http://ktwu.org + # ('shptv.org', 'Smoky Hills Public Television (KOOD)'), # http://www.shptv.org + # ('kcpt.org', 'KCPT Kansas City Public Television (KCPT)'), # http://kcpt.org/ + # ('blueridgepbs.org', 'Blue Ridge PBS (WBRA)'), # http://www.blueridgepbs.org/ + ('watch.easttennesseepbs.org', 'East Tennessee PBS (WSJK)'), # http://easttennesseepbs.org + ('video.wcte.tv', 'WCTE-TV (WCTE)'), # http://www.wcte.org + ('video.wljt.org', 'WLJT, Channel 11 (WLJT)'), # http://wljt.org/ + ('video.wosu.org', 'WOSU TV (WOSU)'), # http://wosu.org/ + ('video.woub.org', 'WOUB/WOUC (WOUB)'), # http://woub.org/tv/index.php?section=5 + ('video.wvpublic.org', 'WVPB (WVPB)'), # http://wvpublic.org/ + ('video.wkyupbs.org', 'WKYU-PBS (WKYU)'), # http://www.wkyupbs.org + # ('wyes.org', 'WYES-TV/New Orleans (WYES)'), # http://www.wyes.org + ('video.kera.org', 'KERA 13 (KERA)'), # http://www.kera.org/ + ('video.mpbn.net', 'MPBN (WCBB)'), # http://www.mpbn.net/ + ('video.mountainlake.org', 'Mountain Lake PBS (WCFE)'), # http://www.mountainlake.org/ + ('video.nhptv.org', 'NHPTV (WENH)'), # http://nhptv.org/ + ('video.vpt.org', 'Vermont PBS (WETK)'), # http://www.vpt.org + ('video.witf.org', 'witf (WITF)'), # http://www.witf.org + ('watch.wqed.org', 'WQED Multimedia (WQED)'), # http://www.wqed.org/ + ('video.wmht.org', 'WMHT Educational Telecommunications (WMHT)'), # http://www.wmht.org/home/ + ('video.deltabroadcasting.org', 'Q-TV (WDCQ)'), # http://www.deltabroadcasting.org + ('video.dptv.org', 'WTVS Detroit Public TV (WTVS)'), # http://www.dptv.org/ + ('video.wcmu.org', 'CMU Public Television (WCMU)'), # http://www.wcmu.org + ('video.wkar.org', 'WKAR-TV (WKAR)'), # http://wkar.org/ + ('wnmuvideo.nmu.edu', 'WNMU-TV Public TV 13 (WNMU)'), # http://wnmutv.nmu.edu + ('video.wdse.org', 'WDSE - WRPT (WDSE)'), # http://www.wdse.org/ + ('video.wgte.org', 'WGTE TV (WGTE)'), # http://www.wgte.org + ('video.lptv.org', 'Lakeland Public Television (KAWE)'), # http://www.lakelandptv.org + # ('prairiepublic.org', 'PRAIRIE PUBLIC (KFME)'), # http://www.prairiepublic.org/ + ('video.kmos.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'), # http://www.kmos.org/ + ('watch.montanapbs.org', 'MontanaPBS (KUSM)'), # http://montanapbs.org + ('video.krwg.org', 'KRWG/Channel 22 (KRWG)'), # http://www.krwg.org + ('video.kacvtv.org', 'KACV (KACV)'), # http://www.panhandlepbs.org/home/ + ('video.kcostv.org', 'KCOS/Channel 13 (KCOS)'), # www.kcostv.org + ('video.wcny.org', 'WCNY/Channel 24 (WCNY)'), # http://www.wcny.org + ('video.wned.org', 'WNED (WNED)'), # http://www.wned.org/ + ('watch.wpbstv.org', 'WPBS (WPBS)'), # http://www.wpbstv.org + ('video.wskg.org', 'WSKG Public TV (WSKG)'), # http://wskg.org + ('video.wxxi.org', 'WXXI (WXXI)'), # http://wxxi.org + ('video.wpsu.org', 'WPSU (WPSU)'), # http://www.wpsu.org + # ('wqln.org', 'WQLN/Channel 54 (WQLN)'), # http://www.wqln.org + ('on-demand.wvia.org', 'WVIA Public Media Studios (WVIA)'), # http://www.wvia.org/ + ('video.wtvi.org', 'WTVI (WTVI)'), # http://www.wtvi.org/ + # ('whro.org', 'WHRO (WHRO)'), # http://whro.org + ('video.westernreservepublicmedia.org', 'Western Reserve PBS (WNEO)'), # http://www.WesternReservePublicMedia.org/ + ('video.ideastream.org', 'WVIZ/PBS ideastream (WVIZ)'), # http://www.wviz.org/ + ('video.kcts9.org', 'KCTS 9 (KCTS)'), # http://kcts9.org/ + ('video.basinpbs.org', 'Basin PBS (KPBT)'), # http://www.basinpbs.org + ('video.houstonpbs.org', 'KUHT / Channel 8 (KUHT)'), # http://www.houstonpublicmedia.org/ + # ('tamu.edu', 'KAMU - TV (KAMU)'), # http://KAMU.tamu.edu + # ('kedt.org', 'KEDT/Channel 16 (KEDT)'), # http://www.kedt.org + ('video.klrn.org', 'KLRN (KLRN)'), # http://www.klrn.org + ('video.klru.tv', 'KLRU (KLRU)'), # http://www.klru.org + # ('kmbh.org', 'KMBH-TV (KMBH)'), # http://www.kmbh.org + # ('knct.org', 'KNCT (KNCT)'), # http://www.knct.org + # ('ktxt.org', 'KTTZ-TV (KTXT)'), # http://www.ktxt.org + ('video.wtjx.org', 'WTJX Channel 12 (WTJX)'), # http://www.wtjx.org/ + ('video.ideastations.org', 'WCVE PBS (WCVE)'), # http://ideastations.org/ + ('video.kbtc.org', 'KBTC Public Television (KBTC)'), # http://kbtc.org ) IE_NAME = 'pbs' @@ -182,13 +183,13 @@ class PBSIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?: # Direct video URL - (?:videos?|watch)\.(?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? | + (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? | # Article with embedded player (or direct video) (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ ) - ''' % '|'.join(list(zip(*_STATIONS))[0]) + ''' % '|'.join(re.escape(p) for p in list(zip(*_STATIONS))[0]) _TESTS = [ { diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 919704261..7de7b7273 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -6,12 +6,12 @@ import re from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE -from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, sanitized_Request, smuggle_url, std_headers, + urlencode_postdata, ) @@ -57,7 +57,7 @@ class SafariBaseIE(InfoExtractor): } request = sanitized_Request( - self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers) + self._LOGIN_URL, urlencode_postdata(login_form), headers=headers) login_page = self._download_webpage( request, None, 'Logging in as %s' % username) diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index 571289421..02dfd36f4 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_etree_fromstring +from ..compat import ( + compat_etree_fromstring, + compat_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -67,6 +70,17 @@ class VevoIE(InfoExtractor): 'params': { 'skip_download': 'true', } + }, { + 'note': 'No video_info', + 'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000', + 'md5': '8b83cc492d72fc9cf74a02acee7dc1b0', + 'info_dict': { + 'id': 'USUV71503000', + 'ext': 'mp4', + 'title': 'Till I Die - K Camp ft. T.I.', + 'duration': 193, + }, + 'expected_warnings': ['Unable to download SMIL file'], }] _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/' @@ -81,11 +95,17 @@ class VevoIE(InfoExtractor): if webpage is False: self._oauth_token = None else: + if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage: + raise ExtractorError('%s said: This page is currently unavailable in your region.' % self.IE_NAME, expected=True) + self._oauth_token = self._search_regex( r'access_token":\s*"([^"]+)"', webpage, 'access token', fatal=False) def _formats_from_json(self, video_info): + if not video_info: + return [] + last_version = {'version': -1} for version in video_info['videoVersions']: # These are the HTTP downloads, other types are for different manifests @@ -110,9 +130,8 @@ class VevoIE(InfoExtractor): }) return formats - def _formats_from_smil(self, smil_xml): + def _formats_from_smil(self, smil_doc): formats = [] - smil_doc = compat_etree_fromstring(smil_xml.encode('utf-8')) els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video') for el in els: src = el.attrib['src'] @@ -145,14 +164,14 @@ class VevoIE(InfoExtractor): }) return formats - def _download_api_formats(self, video_id): + def _download_api_formats(self, video_id, video_url): if not self._oauth_token: self._downloader.report_warning( 'No oauth token available, skipping API HLS download') return [] - api_url = 'https://apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( - video_id, self._oauth_token) + api_url = compat_urlparse.urljoin(video_url, '//apiv2.vevo.com/video/%s/streams/hls?token=%s' % ( + video_id, self._oauth_token)) api_data = self._download_json( api_url, video_id, note='Downloading HLS formats', @@ -166,18 +185,26 @@ class VevoIE(InfoExtractor): preference=0) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + webpage = None json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id response = self._download_json(json_url, video_id) - video_info = response['video'] + video_info = response['video'] or {} - if not video_info: + if not video_info and response.get('statusCode') != 909: if 'statusMessage' in response: raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusMessage']), expected=True) raise ExtractorError('Unable to extract videos') + if not video_info: + if url.startswith('vevo:'): + raise ExtractorError('Please specify full Vevo URL for downloading', expected=True) + webpage = self._download_webpage(url, video_id) + + title = video_info.get('title') or self._og_search_title(webpage) + formats = self._formats_from_json(video_info) is_explicit = video_info.get('isExplicit') @@ -189,11 +216,11 @@ class VevoIE(InfoExtractor): age_limit = None # Download via HLS API - formats.extend(self._download_api_formats(video_id)) + formats.extend(self._download_api_formats(video_id, url)) # Download SMIL smil_blocks = sorted(( - f for f in video_info['videoVersions'] + f for f in video_info.get('videoVersions', []) if f['sourceType'] == 13), key=lambda f: f['version']) smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % ( @@ -205,23 +232,26 @@ class VevoIE(InfoExtractor): if smil_url_m is not None: smil_url = smil_url_m if smil_url: - smil_xml = self._download_webpage( - smil_url, video_id, 'Downloading SMIL info', fatal=False) - if smil_xml: - formats.extend(self._formats_from_smil(smil_xml)) + smil_doc = self._download_smil(smil_url, video_id, fatal=False) + if smil_doc: + formats.extend(self._formats_from_smil(smil_doc)) self._sort_formats(formats) - timestamp_ms = int_or_none(self._search_regex( + timestamp = int_or_none(self._search_regex( r'/Date\((\d+)\)/', - video_info['launchDate'], 'launch date', fatal=False)) + video_info['launchDate'], 'launch date', fatal=False), + scale=1000) if video_info else None + + duration = video_info.get('duration') or int_or_none( + self._html_search_meta('video:duration', webpage)) return { 'id': video_id, - 'title': video_info['title'], + 'title': title, 'formats': formats, - 'thumbnail': video_info['imageUrl'], - 'timestamp': timestamp_ms // 1000, - 'uploader': video_info['mainArtists'][0]['artistName'], - 'duration': video_info['duration'], + 'thumbnail': video_info.get('imageUrl'), + 'timestamp': timestamp, + 'uploader': video_info['mainArtists'][0]['artistName'] if video_info else None, + 'duration': duration, 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index b46802306..ef096cbd2 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -10,8 +10,8 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( - determine_ext, unified_strdate, + qualities, ) @@ -33,6 +33,7 @@ class WDRIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html', @@ -47,6 +48,7 @@ class WDRIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html', @@ -71,6 +73,7 @@ class WDRIE(InfoExtractor): 'upload_date': '20140717', 'is_live': False }, + 'skip': 'Page Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html', @@ -83,10 +86,10 @@ class WDRIE(InfoExtractor): 'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html', 'info_dict': { 'id': 'mdb-103364', - 'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', 'ext': 'flv', - 'upload_date': '20150212', + 'upload_date': '20150101', 'is_live': True }, 'params': { @@ -150,25 +153,52 @@ class WDRIE(InfoExtractor): if upload_date: upload_date = unified_strdate(upload_date) + formats = [] + preference = qualities(['S', 'M', 'L', 'XL']) + if video_url.endswith('.f4m'): - video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18' - ext = 'flv' + f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) elif video_url.endswith('.smil'): - fmt = self._extract_smil_formats(video_url, page_id)[0] - video_url = fmt['url'] - sep = '&' if '?' in video_url else '?' - video_url += sep - video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43' - ext = fmt['ext'] + smil_formats = self._extract_smil_formats(video_url, page_id, False, { + 'hdcore': '3.3.0', + 'plugin': 'aasp-3.3.0.99.43', + }) + if smil_formats: + formats.extend(smil_formats) else: - ext = determine_ext(video_url) + formats.append({ + 'url': video_url, + 'http_headers': { + 'User-Agent': 'mobile', + }, + }) + + m3u8_url = self._search_regex(r'rel="adaptiv"[^>]+href="([^"]+)"', webpage, 'm3u8 url', default=None) + if m3u8_url: + m3u8_formats = self._extract_m3u8_formats(m3u8_url, page_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + direct_urls = re.findall(r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage) + if direct_urls: + for quality, video_url in direct_urls: + formats.append({ + 'url': video_url, + 'preference': preference(quality), + 'http_headers': { + 'User-Agent': 'mobile', + }, + }) + + self._sort_formats(formats) description = self._html_search_meta('Description', webpage, 'description') return { 'id': page_id, - 'url': video_url, - 'ext': ext, + 'formats': formats, 'title': title, 'description': description, 'thumbnail': thumbnail, |