commit 71ebd35d5003cfc5f4c8518249e03e1da0e620b4
parent f8c55c6664e0d279ed01702b2af2ba5ee290ee4b
Author: Remita Amine <remitamine@gmail.com>
Date:   Tue,  7 May 2019 10:16:51 +0100

[sky] add support for news.sky.com (closes #13055)

Diffstat:
Myoutube_dl/extractor/extractors.py | 5++++-
Ayoutube_dl/extractor/sky.py | 70++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Dyoutube_dl/extractor/skysports.py | 49-------------------------------------------------
3 files changed, 74 insertions(+), 50 deletions(-)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py @@ -1033,7 +1033,10 @@ from .skynewsarabia import ( SkyNewsArabiaIE, SkyNewsArabiaArticleIE, ) -from .skysports import SkySportsIE +from .sky import ( + SkyNewsIE, + SkySportsIE, +) from .slideshare import SlideshareIE from .slideslive import SlidesLiveIE from .slutload import SlutloadIE diff --git a/youtube_dl/extractor/sky.py b/youtube_dl/extractor/sky.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + extract_attributes, + smuggle_url, + strip_or_none, + urljoin, +) + + +class SkyBaseIE(InfoExtractor): + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_data = extract_attributes(self._search_regex( + r'(<div.+?class="[^"]*sdc-article-video__media-ooyala[^"]*"[^>]+>)', + webpage, 'video data')) + + video_url = 'ooyala:%s' % video_data['data-video-id'] + if video_data.get('data-token-required') == 'true': + token_fetch_options = self._parse_json(video_data.get( + 'data-token-fetch-options', '{}'), video_id, fatal=False) or {} + token_fetch_url = token_fetch_options.get('url') + if token_fetch_url: + embed_token = self._download_webpage(urljoin( + url, token_fetch_url), video_id, fatal=False) + if embed_token: + video_url = smuggle_url( + video_url, {'embed_token': embed_token.strip('"')}) + + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': video_url, + 'title': self._og_search_title(webpage), + 'description': strip_or_none(self._og_search_description(webpage)), + 'ie_key': 'Ooyala', + } + + +class SkySportsIE(SkyBaseIE): + _VALID_URL = r'https?://(?:www\.)?skysports\.com/watch/video/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.skysports.com/watch/video/10328419/bale-its-our-time-to-shine', + 'md5': '77d59166cddc8d3cb7b13e35eaf0f5ec', + 'info_dict': { + 'id': 'o3eWJnNDE6l7kfNO8BOoBlRxXRQ4ANNQ', + 'ext': 'mp4', + 'title': 'Bale: It\'s our time to shine', + 'description': 'md5:e88bda94ae15f7720c5cb467e777bb6d', + }, + 'add_ie': ['Ooyala'], + } + + +class SkyNewsIE(SkyBaseIE): + _VALID_URL = r'https?://news\.sky\.com/video/[0-9a-z-]+-(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://news.sky.com/video/russian-plane-inspected-after-deadly-fire-11712962', + 'md5': 'd6327e581473cea9976a3236ded370cd', + 'info_dict': { + 'id': '1ua21xaDE6lCtZDmbYfl8kwsKLooJbNM', + 'ext': 'mp4', + 'title': 'Russian plane inspected after deadly fire', + 'description': 'The Russian Investigative Committee has released video of the wreckage of a passenger plane which caught fire near Moscow.', + }, + 'add_ie': ['Ooyala'], + } diff --git a/youtube_dl/extractor/skysports.py b/youtube_dl/extractor/skysports.py @@ -1,49 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - extract_attributes, - smuggle_url, - strip_or_none, - urljoin, -) - - -class SkySportsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?skysports\.com/watch/video/(?P<id>[0-9]+)' - _TEST = { - 'url': 'http://www.skysports.com/watch/video/10328419/bale-its-our-time-to-shine', - 'md5': '77d59166cddc8d3cb7b13e35eaf0f5ec', - 'info_dict': { - 'id': '10328419', - 'ext': 'mp4', - 'title': 'Bale: It\'s our time to shine', - 'description': 'md5:e88bda94ae15f7720c5cb467e777bb6d', - }, - 'add_ie': ['Ooyala'], - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_data = extract_attributes(self._search_regex( - r'(<div.+?class="sdc-article-video__media-ooyala"[^>]+>)', webpage, 'video data')) - - video_url = 'ooyala:%s' % video_data['data-video-id'] - if video_data.get('data-token-required') == 'true': - token_fetch_options = self._parse_json(video_data.get('data-token-fetch-options', '{}'), video_id, fatal=False) or {} - token_fetch_url = token_fetch_options.get('url') - if token_fetch_url: - embed_token = self._download_webpage(urljoin(url, token_fetch_url), video_id, fatal=False) - if embed_token: - video_url = smuggle_url(video_url, {'embed_token': embed_token.strip('"')}) - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': video_url, - 'title': self._og_search_title(webpage), - 'description': strip_or_none(self._og_search_description(webpage)), - 'ie_key': 'Ooyala', - }