X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvgtv.py;h=811ee197d415bec57c355a986a07d65a8e0d8b7c;hb=3b68efdc6ae109a840ff5f15f0e28910c2463b3f;hp=8ce3d8b8f65008f234c6fc47c3317a10a8da408a;hpb=9f6b517671a7a9b16ccf2bc3f5153673a73895ff;p=youtube-dl diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 8ce3d8b8f..811ee197d 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -4,29 +4,48 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .xstream import XstreamIE from ..utils import ( ExtractorError, float_or_none, ) -class VGTVIE(InfoExtractor): +class VGTVIE(XstreamIE): IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet' + + _HOST_TO_APPNAME = { + 'vgtv.no': 'vgtv', + 'bt.no/tv': 'bttv', + 'aftenbladet.no/tv': 'satv', + 'fvn.no/fvntv': 'fvntv', + 'aftenposten.no/webtv': 'aptv', + } + + _APP_NAME_TO_VENDOR = { + 'vgtv': 'vgtv', + 'bttv': 'bt', + 'satv': 'sa', + 'fvntv': 'fvn', + 'aptv': 'ap', + } + _VALID_URL = r'''(?x) - https?://(?:www\.)? + (?:https?://(?:www\.)? (?P - vgtv.no| - (?:bt|aftenbladet).no/tv| - fvn.no/fvntv| - aftenposten.no/webtv + %s ) / (?: \#!/(?:video|live)/| embed?.*id= - ) + )| + (?P + %s + ):) (?P\d+) - ''' + ''' % ('|'.join(_HOST_TO_APPNAME.keys()), '|'.join(_APP_NAME_TO_VENDOR.keys())) + _TESTS = [ { # streamType: vod @@ -85,10 +104,10 @@ class VGTVIE(InfoExtractor): }, { 'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more', - 'md5': '7fbc265a3ca4933a423c7a66aa879a67', + 'md5': 'fd828cd29774a729bf4d4425fe192972', 'info_dict': { 'id': '21039', - 'ext': 'mp4', + 'ext': 'mov', 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more', 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238', 'duration': 66, @@ -102,43 +121,32 @@ class VGTVIE(InfoExtractor): 'only_matching': True, }, ] - _HOST_WEBSITES = { - 'vgtv.no': { - 'vendor': 'vgtv', - 'appname': 'vgtv', - }, - 'bt.no/tv': { - 'vendor': 'bt', - 'appname': 'bttv', - }, - 'aftenbladet.no/tv': { - 'vendor': 'sa', - 'appname': 'satv', - }, - 'fvn.no/fvntv': { - 'vendor': 'fvn', - 'appname': 'fvntv', - }, - 'aftenposten.no/webtv': { - 'vendor': 'ap', - 'appname': 'aptv', - }, - } def _real_extract(self, 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/%s/assets/%s?appName=%s-website' - % (self._HOST_WEBSITES[host]['vendor'], video_id, self._HOST_WEBSITES[host]['appname']), + % (vendor, video_id, appname), video_id, 'Downloading media JSON') 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) + elif appname == 'aptv': + info = self._extract_video_info('ap', video_id) + streams = data['streamUrls'] stream_type = data.get('streamType') @@ -146,14 +154,16 @@ class VGTVIE(InfoExtractor): hls_url = streams.get('hls') if hls_url: - m3u8_formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + m3u8_formats = self._extract_m3u8_formats( + hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False) if m3u8_formats: formats.extend(m3u8_formats) hds_url = streams.get('hds') # wasLive hds are always 404 if hds_url and stream_type != 'wasLive': - f4m_formats = self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id, f4m_id='hds', fatal=False) + f4m_formats = self._extract_f4m_formats( + hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id, f4m_id='hds', fatal=False) if f4m_formats: formats.extend(f4m_formats) @@ -164,22 +174,23 @@ class VGTVIE(InfoExtractor): for mp4_url in mp4_urls: format_info = { 'url': mp4_url, - 'preference': 1, } mobj = re.search('(\d+)_(\d+)_(\d+)', mp4_url) if mobj: - vbr = int(mobj.group(3)) + tbr = int(mobj.group(3)) format_info.update({ 'width': int(mobj.group(1)), 'height': int(mobj.group(2)), - 'vbr': vbr, - 'format_id': 'mp4-%s' % vbr, + 'tbr': tbr, + 'format_id': 'mp4-%s' % tbr, }) formats.append(format_info) - self._sort_formats(formats) + info['formats'].extend(formats) + + self._sort_formats(info['formats']) - return { + info.update({ 'id': video_id, 'title': self._live_title(data['title']) if stream_type == 'live' else data['title'], 'description': data['description'], @@ -187,9 +198,9 @@ class VGTVIE(InfoExtractor): 'timestamp': data['published'], 'duration': float_or_none(data['duration'], 1000), 'view_count': data['displays'], - 'formats': formats, 'is_live': True if stream_type == 'live' else False, - } + }) + return info class BTArticleIE(InfoExtractor): @@ -198,7 +209,7 @@ class BTArticleIE(InfoExtractor): _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P[^/]+)-\d+\.html' _TEST = { 'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html', - 'md5': 'd055e8ee918ef2844745fcfd1a4175fb', + 'md5': '2acbe8ad129b3469d5ae51b1158878df', 'info_dict': { 'id': '23199', 'ext': 'mp4', @@ -215,15 +226,15 @@ class BTArticleIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, self._match_id(url)) video_id = self._search_regex( - r'SVP\.Player\.load\(\s*(\d+)', webpage, 'video id') - return self.url_result('http://bt.no/tv/embed?id=%s' % video_id, 'VGTV') + 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 = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588', 'md5': 'd7d17e3337dc80de6d3a540aefbe441b', 'info_dict': { @@ -234,7 +245,19 @@ class BTVestlendingenIE(InfoExtractor): '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('http://bt.no/tv/embed?id=%s' % self._match_id(url), 'VGTV') + return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')