X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..f16b10fb8c485cdd113f9a55a6a2f32c2d81d717:/youtube_dl/extractor/vgtv.py diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index d3fa70e..fe7a26b 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -4,11 +4,55 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import float_or_none +from .xstream import XstreamIE +from ..utils import ( + ExtractorError, + float_or_none, + try_get, +) -class VGTVIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P[0-9]+)' +class VGTVIE(XstreamIE): + IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet' + _GEO_BYPASS = False + + _HOST_TO_APPNAME = { + 'vgtv.no': 'vgtv', + 'bt.no/tv': 'bttv', + 'aftenbladet.no/tv': 'satv', + 'fvn.no/fvntv': 'fvntv', + 'aftenposten.no/webtv': 'aptv', + 'ap.vgtv.no/webtv': 'aptv', + 'tv.aftonbladet.se/abtv': 'abtv', + 'www.aftonbladet.se/tv': 'abtv', + } + + _APP_NAME_TO_VENDOR = { + 'vgtv': 'vgtv', + 'bttv': 'bt', + 'satv': 'sa', + 'fvntv': 'fvn', + 'aptv': 'ap', + 'abtv': 'ab', + } + + _VALID_URL = r'''(?x) + (?:https?://(?:www\.)? + (?P + %s + ) + /? + (?: + (?:\#!/)?(?:video|live)/| + embed?.*id=| + a(?:rticles)?/ + )| + (?P + %s + ):) + (?P\d+) + ''' % ('|'.join(_HOST_TO_APPNAME.keys()), '|'.join(_APP_NAME_TO_VENDOR.keys())) + _TESTS = [ { # streamType: vod @@ -17,9 +61,9 @@ class VGTVIE(InfoExtractor): 'info_dict': { 'id': '84196', 'ext': 'mp4', - 'title': 'Hevnen er søt episode 1:10 - Abu', + 'title': 'Hevnen er søt: Episode 10 - Abu', 'description': 'md5:e25e4badb5f544b04341e14abdc72234', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 648.000, 'timestamp': 1404626400, 'upload_date': '20140706', @@ -34,8 +78,8 @@ class VGTVIE(InfoExtractor): 'ext': 'flv', 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen', 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3', - 'thumbnail': 're:^https?://.*\.jpg', - 'duration': 9056.000, + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 9103.0, 'timestamp': 1410113864, 'upload_date': '20140907', 'view_count': int, @@ -44,19 +88,20 @@ class VGTVIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + 'skip': 'Video is no longer available', }, { - # streamType: live - 'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen', + # streamType: wasLive + 'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla', 'info_dict': { - 'id': '100015', - 'ext': 'flv', - 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!', - 'description': 'md5:9a60cc23fa349f761628924e56eeec2d', - 'thumbnail': 're:^https?://.*\.jpg', - 'duration': 0, - 'timestamp': 1407423348, - 'upload_date': '20140807', + 'id': '113063', + 'ext': 'mp4', + 'title': 'V75 fra Solvalla 30.05.15', + 'description': 'md5:b3743425765355855f88e096acc93231', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 25966, + 'timestamp': 1432975582, + 'upload_date': '20150530', 'view_count': int, }, 'params': { @@ -64,54 +109,199 @@ class VGTVIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more', + 'md5': 'fd828cd29774a729bf4d4425fe192972', + 'info_dict': { + 'id': '21039', + 'ext': 'mp4', + 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more', + 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238', + 'duration': 66, + 'timestamp': 1417002452, + 'upload_date': '20141126', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien', + 'only_matching': True, + }, + { + 'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil', + 'only_matching': True, + }, + { + # geoblocked + 'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk', + 'only_matching': True, + }, + { + 'url': 'http://tv.aftonbladet.se/abtv/articles/36015', + 'only_matching': True, + }, + { + 'url': 'https://www.aftonbladet.se/tv/a/36015', + 'only_matching': True, + }, + { + 'url': 'abtv:140026', + 'only_matching': True, + }, + { + 'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu', + 'only_matching': True, + }, ] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') + appname = self._HOST_TO_APPNAME[host] if host else mobj.group('appname') + vendor = self._APP_NAME_TO_VENDOR[appname] + data = self._download_json( - 'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id, + 'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website' + % (vendor, video_id, appname), video_id, 'Downloading media JSON') - streams = data['streamUrls'] + if data.get('status') == 'inactive': + raise ExtractorError( + 'Video %s is no longer available' % video_id, expected=True) + + info = { + 'formats': [], + } + if len(video_id) == 5: + if appname == 'bttv': + info = self._extract_video_info('btno', video_id) + streams = data['streamUrls'] + stream_type = data.get('streamType') + is_live = stream_type == 'live' formats = [] hls_url = streams.get('hls') if hls_url: - formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4')) + formats.extend(self._extract_m3u8_formats( + hls_url, video_id, 'mp4', + entry_protocol='m3u8' if is_live else 'm3u8_native', + m3u8_id='hls', fatal=False)) hds_url = streams.get('hds') if hds_url: - formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id)) + hdcore_sign = 'hdcore=3.7.0' + f4m_formats = self._extract_f4m_formats( + hds_url + '?%s' % hdcore_sign, video_id, f4m_id='hds', fatal=False) + if f4m_formats: + for entry in f4m_formats: + # URLs without the extra param induce an 404 error + entry.update({'extra_param_to_segment_url': hdcore_sign}) + formats.append(entry) + mp4_urls = streams.get('pseudostreaming') or [] mp4_url = streams.get('mp4') if mp4_url: - _url = hls_url or hds_url - MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1]) - for mp4_format in _url.split(','): - m = re.search('(?P\d+)_(?P\d+)_(?P\d+)', mp4_format) - if not m: - continue - width = int(m.group('width')) - height = int(m.group('height')) - vbr = int(m.group('vbr')) - formats.append({ - 'url': MP4_URL_TEMPLATE % mp4_format, - 'format_id': 'mp4-%s' % vbr, - 'width': width, - 'height': height, - 'vbr': vbr, - 'preference': 1, + mp4_urls.append(mp4_url) + for mp4_url in mp4_urls: + format_info = { + 'url': mp4_url, + } + mobj = re.search(r'(\d+)_(\d+)_(\d+)', mp4_url) + if mobj: + tbr = int(mobj.group(3)) + format_info.update({ + 'width': int(mobj.group(1)), + 'height': int(mobj.group(2)), + 'tbr': tbr, + 'format_id': 'mp4-%s' % tbr, }) - self._sort_formats(formats) + formats.append(format_info) + + info['formats'].extend(formats) + + if not info['formats']: + properties = try_get( + data, lambda x: x['streamConfiguration']['properties'], list) + if properties and 'geoblocked' in properties: + raise self.raise_geo_restricted( + countries=[host.rpartition('.')[-1].partition('/')[0].upper()]) - return { + self._sort_formats(info['formats']) + + info.update({ 'id': video_id, - 'title': data['title'], + 'title': self._live_title(data['title']) if is_live else data['title'], 'description': data['description'], 'thumbnail': data['images']['main'] + '?t[]=900x506q80', 'timestamp': data['published'], 'duration': float_or_none(data['duration'], 1000), 'view_count': data['displays'], - 'formats': formats, - } \ No newline at end of file + 'is_live': is_live, + }) + return info + + +class BTArticleIE(InfoExtractor): + IE_NAME = 'bt:article' + IE_DESC = 'Bergens Tidende Articles' + _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P[^/]+)-\d+\.html' + _TEST = { + 'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html', + 'md5': '2acbe8ad129b3469d5ae51b1158878df', + 'info_dict': { + 'id': '23199', + 'ext': 'mp4', + 'title': 'Alrekstad internat', + 'description': 'md5:dc81a9056c874fedb62fc48a300dac58', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 191, + 'timestamp': 1289991323, + 'upload_date': '20101117', + 'view_count': int, + }, + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, self._match_id(url)) + video_id = self._search_regex( + r']+data-id="(\d+)"', webpage, 'video id') + return self.url_result('bttv:%s' % video_id, 'VGTV') + + +class BTVestlendingenIE(InfoExtractor): + IE_NAME = 'bt:vestlendingen' + IE_DESC = 'Bergens Tidende - Vestlendingen' + _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P\d+)' + _TESTS = [{ + 'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588', + 'md5': 'd7d17e3337dc80de6d3a540aefbe441b', + 'info_dict': { + 'id': '86588', + 'ext': 'mov', + 'title': 'Otto Wollertsen', + 'description': 'Vestlendingen Otto Fredrik Wollertsen', + 'timestamp': 1430473209, + 'upload_date': '20150501', + }, + 'skip': '404 Error', + }, { + 'url': 'http://www.bt.no/spesial/vestlendingen/#!/86255', + 'md5': 'a2893f8632e96389f4bdf36aa9463ceb', + 'info_dict': { + 'id': '86255', + 'ext': 'mov', + 'title': 'Du må tåle å fryse og være sulten', + 'description': 'md5:b8046f4d022d5830ddab04865791d063', + 'upload_date': '20150321', + 'timestamp': 1426942023, + }, + }] + + def _real_extract(self, url): + return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')