diff options
author | Remita Amine <remitamine@gmail.com> | 2016-10-26 10:07:35 +0100 |
---|---|---|
committer | Remita Amine <remitamine@gmail.com> | 2016-10-26 10:07:35 +0100 |
commit | 777d90dc28a6864c52d40c533b2f6dcc5c637582 (patch) | |
tree | cbf6f07137ec73d44d4425e6e22d3ef53da4f850 | |
parent | 3791d84acce7f03a50cb11b76d9a4302cf087b60 (diff) |
[rentv] Add new extractor(closes #10620)
-rw-r--r-- | youtube_dl/extractor/extractors.py | 4 | ||||
-rw-r--r-- | youtube_dl/extractor/rentv.py | 56 |
2 files changed, 60 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 432c56af2..c6ac4753e 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -745,6 +745,10 @@ from .rbmaradio import RBMARadioIE from .rds import RDSIE from .redtube import RedTubeIE from .regiotv import RegioTVIE +from .rentv import ( + RENTVIE, + RENTVArticleIE, +) from .restudy import RestudyIE from .reuters import ReutersIE from .reverbnation import ReverbNationIE diff --git a/youtube_dl/extractor/rentv.py b/youtube_dl/extractor/rentv.py new file mode 100644 index 000000000..dfba2f487 --- /dev/null +++ b/youtube_dl/extractor/rentv.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .jwplatform import JWPlatformBaseIE +from ..compat import compat_str + + +class RENTVIE(JWPlatformBaseIE): + _VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P<id>\d+)' + _TEST = { + 'url': 'http://ren.tv/video/epizod/118577', + 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb', + 'info_dict': { + 'id': '118577', + 'ext': 'mp4', + 'title': 'Документальный спецпроект: "Промывка мозгов. Технологии XXI века"' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage('http://ren.tv/player/' + video_id, video_id) + jw_config = self._parse_json(self._search_regex( + r'config\s*=\s*({.+});', webpage, 'jw config'), video_id) + return self._parse_jwplayer_data(jw_config, video_id, m3u8_id='hls') + + +class RENTVArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ren\.tv/novosti/\d{4}-\d{2}-\d{2}/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'http://ren.tv/novosti/2016-10-26/video-mikroavtobus-popavshiy-v-dtp-s-gruzovikami-v-podmoskove-prevratilsya-v', + 'md5': 'ebd63c4680b167693745ab91343df1d6', + 'info_dict': { + 'id': '136472', + 'ext': 'mp4', + 'title': 'Видео: микроавтобус, попавший в ДТП с грузовиками в Подмосковье, превратился в груду металла', + 'description': 'Жертвами столкновения двух фур и микроавтобуса, по последним данным, стали семь человек.', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + drupal_settings = self._parse_json(self._search_regex( + r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', + webpage, 'drupal settings'), display_id) + + entries = [] + for config_profile in drupal_settings.get('ren_jwplayer', {}).values(): + media_id = config_profile.get('mediaid') + if not media_id: + continue + media_id = compat_str(media_id) + entries.append(self.url_result('rentv:' + media_id, 'RENTV', media_id)) + return self.playlist_result(entries, display_id) |