diff options
author | Entropy <0fiscalentropy@users.noreply.github.com> | 2017-04-07 21:52:48 +0200 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2017-04-08 19:54:04 +0700 |
commit | 5f3e0b69efa8ae80f536fb54ace4bb4d9c667d2e (patch) | |
tree | 5f92e5052e119a76241dd20e592b79ede72c6caf | |
parent | 28b674ca238fbae29f2ee7bc85202fa2f115a876 (diff) |
[TheSun] Add new extractor
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/thesun.py | 27 |
2 files changed, 28 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 72728d919..01865479c 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -983,6 +983,7 @@ from .theplatform import ( from .thescene import TheSceneIE from .thesixtyone import TheSixtyOneIE from .thestar import TheStarIE +from .thesun import TheSunIE from .theweatherchannel import TheWeatherChannelIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py new file mode 100644 index 000000000..7f96bf8c9 --- /dev/null +++ b/youtube_dl/extractor/thesun.py @@ -0,0 +1,27 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from .ooyala import OoyalaIE + + +class TheSunIE(InfoExtractor): + _VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/\w+/(?P<id>\d+)/[\w-]' + _TEST = { + 'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/', + 'md5': '5667123b24f25f43f4c4f381ef34c5c2', + 'info_dict': { + 'id': 'h4OXN0NzE6rv6ObkEifKcNA-gYUw4xFf', + 'ext': 'mp4', + 'title': 'Katy Perry and Orlando Bloom shut down split rumours with cute Thanksgiving video', + 'description': 'Still going strong', + 'duration': 31.28, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + ooyala_id = self._search_regex(r'id\s*=\s*"thesun-ooyala-player-([^"]+)"', webpage, 'ooyala id') + + return OoyalaIE._build_url_result(ooyala_id) |