from .aol import AolIE
from .allocine import AllocineIE
from .aparat import AparatIE
+from .appleconnect import AppleConnectIE
from .appletrailers import AppleTrailersIE
from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE, ARDMediathekIE
+from .ard import (
+ ARDIE,
+ ARDMediathekIE,
+ SportschauIE,
+)
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
- from .bbccouk import BBCCoUkIE
+ from .bbc import BBCCoUkIE, BBCNewsIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .beatportpro import BeatportProIE
)
from .elpais import ElPaisIE
from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
from .engadget import EngadgetIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .kontrtube import KontrTubeIE
from .krasview import KrasViewIE
from .ku6 import Ku6IE
+from .kuwo import (
+ KuwoIE,
+ KuwoAlbumIE,
+ KuwoChartIE,
+ KuwoSingerIE,
+ KuwoCategoryIE,
+ KuwoMvIE,
+)
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
+from .lecture2go import Lecture2GoIE
from .letv import (
LetvIE,
LetvTvIE,
from .muzu import MuzuTVIE
from .myspace import MySpaceIE, MySpaceAlbumIE
from .myspass import MySpassIE
+from .myvi import MyviIE
from .myvideo import MyVideoIE
from .myvidster import MyVidsterIE
from .nationalgeographic import NationalGeographicIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
from .nerdist import NerdistIE
+from .neteasemusic import (
+ NetEaseMusicIE,
+ NetEaseMusicAlbumIE,
+ NetEaseMusicSingerIE,
+ NetEaseMusicListIE,
+ NetEaseMusicMvIE,
+ NetEaseMusicProgramIE,
+ NetEaseMusicDjRadioIE,
+)
from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE
from .nextmedia import (
NPOLiveIE,
NPORadioIE,
NPORadioFragmentIE,
- TegenlichtVproIE,
+ VPROIE,
+ WNLIE
)
from .nrk import (
NRKIE,
from .nuvid import NuvidIE
from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE
+from .onionstudios import OnionStudiosIE
from .ooyala import (
OoyalaIE,
OoyalaExternalIE,
QQMusicSingerIE,
QQMusicAlbumIE,
QQMusicToplistIE,
+ QQMusicPlaylistIE,
)
from .quickvid import QuickVidIE
from .r7 import R7IE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE
+from .rds import RDSIE
from .redtube import RedTubeIE
from .restudy import RestudyIE
from .reverbnation import ReverbNationIE
SmotriUserIE,
SmotriBroadcastIE,
)
+from .snagfilms import (
+ SnagFilmsIE,
+ SnagFilmsEmbedIE,
+)
from .snotr import SnotrIE
from .sohu import SohuIE
from .soompi import (
from .theonion import TheOnionIE
from .theplatform import ThePlatformIE
from .thesixtyone import TheSixtyOneIE
+from .thisamericanlife import ThisAmericanLifeIE
from .thisav import ThisAVIE
from .tinypic import TinyPicIE
from .tlc import TlcIE, TlcDeIE
TMZIE,
TMZArticleIE,
)
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+ TNAFlixIE,
+ EMPFlixIE,
+ MovieFapIE,
+)
from .thvideo import (
THVideoIE,
THVideoPlaylistIE
TwitchBookmarksIE,
TwitchStreamIE,
)
+from .twitter import TwitterCardIE
from .ubu import UbuIE
from .udemy import (
UdemyIE,
WDRMobileIE,
WDRMausIE,
)
-from .webofstories import WebOfStoriesIE
+from .webofstories import (
+ WebOfStoriesIE,
+ WebOfStoriesPlaylistIE,
+)
from .weibo import WeiboIE
from .wimp import WimpIE
from .wistia import WistiaIE
YandexMusicPlaylistIE,
)
from .yesjapan import YesJapanIE
+from .yinyuetai import YinYueTaiIE
from .ynet import YnetIE
from .youjizz import YouJizzIE
from .youku import YoukuIE
from .common import InfoExtractor
from ..utils import (
ExtractorError,
+ parse_duration,
int_or_none,
)
from ..compat import compat_HTTPError
+ import re
class BBCCoUkIE(InfoExtractor):
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+ mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'
+
_TESTS = [
{
'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
def _extract_video(self, media, programme_id):
formats = []
- vbr = int(media.get('bitrate'))
+ vbr = int_or_none(media.get('bitrate'))
vcodec = media.get('encoding')
service = media.get('service')
- width = int(media.get('width'))
- height = int(media.get('height'))
- file_size = int(media.get('media_file_size'))
+ width = int_or_none(media.get('width'))
+ height = int_or_none(media.get('height'))
+ file_size = int_or_none(media.get('media_file_size'))
for connection in self._extract_connections(media):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
def _extract_audio(self, media, programme_id):
formats = []
- abr = int(media.get('bitrate'))
+ abr = int_or_none(media.get('bitrate'))
acodec = media.get('encoding')
service = media.get('service')
for connection in self._extract_connections(media):
def _download_media_selector(self, programme_id):
try:
media_selection = self._download_xml(
- 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
+ self.mediaselector_url % programme_id,
programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
if kind != 'programme' and kind != 'radioProgramme':
continue
programme_id = item.get('vpid')
- duration = int(item.get('duration'))
+ duration = int_or_none(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
return programme_id, title, description, duration, formats, subtitles
except ExtractorError as ee:
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
programme_id = item.get('identifier')
- duration = int(item.get('duration'))
+ duration = int_or_none(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
return programme_id, title, description, duration, formats, subtitles
'formats': formats,
'subtitles': subtitles,
}
+
+
+ class BBCNewsIE(BBCCoUkIE):
+ IE_NAME = 'bbc.com'
+ IE_DESC = 'BBC news'
+ _VALID_URL = r'https?://(?:www\.)?bbc\.com/.+?/(?P<id>[^/]+)$'
+
+ mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'
+
+ _TESTS = [{
+ 'url': 'http://www.bbc.com/news/world-europe-32668511',
+ 'info_dict': {
+ 'id': 'world-europe-32668511',
+ 'title': 'Russia stages massive WW2 parade despite Western boycott',
+ },
+ 'playlist_count': 2,
+ }, {
+ 'url': 'http://www.bbc.com/news/business-28299555',
+ 'info_dict': {
+ 'id': 'business-28299555',
+ 'title': 'Farnborough Airshow: Video highlights',
+ },
+ 'playlist_count': 9,
+ }, {
+ 'url': 'http://www.bbc.com/news/world-europe-32041533',
+ 'note': 'Video',
+ 'info_dict': {
+ 'id': 'p02mprgb',
+ 'ext': 'mp4',
+ 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+ 'description': 'Germanwings plane crash site in aerial video - Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+ 'duration': 47,
+ 'upload_date': '20150324',
+ 'uploader': 'BBC News',
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
+ 'note': 'Video',
+ 'info_dict': {
+ 'id': 'NA',
+ 'ext': 'mp4',
+ 'title': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
+ 'description': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
+ 'duration': 47,
+ 'upload_date': '20150615',
+ 'uploader': 'BBC News',
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
+ 'note': 'Video',
+ 'info_dict': {
+ 'id': '39275083',
+ 'ext': 'mp4',
+ 'title': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
+ 'description': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
+ 'duration': 87,
+ 'upload_date': '20150619',
+ 'uploader': 'BBC News',
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }]
+
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
+ webpage = self._download_webpage(url, list_id)
+
+ list_title = self._html_search_regex(r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'list title')
+
+ pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None)
+ if pubdate:
+ pubdate = pubdate.replace('-', '')
+
+ ret = []
+ jsent = []
+
+ # works with bbc.com/news/something-something-123456 articles
+ jsent = map(
+ lambda m: self._parse_json(m, list_id),
+ re.findall(r"data-media-meta='({[^']+})'", webpage)
+ )
+
+ if len(jsent) == 0:
+ # http://www.bbc.com/news/video_and_audio/international
+ # and single-video articles
+ masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None)
+ if masset:
+ jmasset = self._parse_json(masset, list_id)
+ for key, val in jmasset.get('videos', {}).items():
+ for skey, sval in val.items():
+ sval['id'] = skey
+ jsent.append(sval)
+
+ if len(jsent) == 0:
+ # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
+ # in http://www.bbc.com/news/video_and_audio/international
+ # prone to breaking if entries have sourceFiles list
+ jsent = map(
+ lambda m: self._parse_json(m, list_id),
+ re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
+ )
+
+ if len(jsent) == 0:
+ raise ExtractorError('No video found', expected=True)
+
+ for jent in jsent:
+ programme_id = jent.get('externalId')
+ xml_url = jent.get('href')
+
+ title = jent.get('caption', '')
+ if title == '':
+ title = list_title
+
+ duration = parse_duration(jent.get('duration'))
+ description = list_title
+ if jent.get('caption', '') != '':
+ description += ' - ' + jent.get('caption')
+ thumbnail = None
+ if jent.get('image') is not None:
+ thumbnail = jent['image'].get('href')
+
+ formats = []
+ subtitles = []
+
+ if programme_id:
+ formats, subtitles = self._download_media_selector(programme_id)
+ elif jent.get('sourceFiles') is not None:
+ # mediaselector not used at
+ # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu
+ for key, val in jent['sourceFiles'].items():
+ formats.append({
+ 'ext': val.get('encoding'),
+ 'url': val.get('url'),
+ 'filesize': int(val.get('filesize')),
+ 'format_id': key
+ })
+ elif xml_url:
+ # Cheap fallback
+ # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml
+ xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)')
+ programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
+ formats, subtitles = self._download_media_selector(programme_id)
+
+ if len(formats) == 0:
+ raise ExtractorError('unsupported json media entry.\n ' + str(jent) + '\n')
+
+ self._sort_formats(formats)
+
+ id = jent.get('id') if programme_id is None else programme_id
+ if id is None:
+ id = 'NA'
+
+ ret.append({
+ 'id': id,
+ 'uploader': 'BBC News',
+ 'upload_date': pubdate,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ })
+
+ if len(ret) > 0:
+ return self.playlist_result(ret, list_id, list_title)
+ raise ExtractorError('No video found', expected=True)
projects / youtube-dl.git / commitdiff