diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 15 | ||||
| -rw-r--r-- | youtube_dl/extractor/tvc.py | 109 | 
3 files changed, 128 insertions, 0 deletions
| diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 680d27d2d..18b1c5e54 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -584,6 +584,10 @@ from .tv2 import (      TV2ArticleIE,  )  from .tv4 import TV4IE +from .tvc import ( +    TVCIE, +    TVCArticleIE, +)  from .tvigle import TvigleIE  from .tvp import TvpIE, TvpSeriesIE  from .tvplay import TVPlayIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 75526384f..6be9e6329 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -34,6 +34,7 @@ from .brightcove import BrightcoveIE  from .nbc import NBCSportsVPlayerIE  from .ooyala import OoyalaIE  from .rutv import RUTVIE +from .tvc import TVCIE  from .sportbox import SportBoxEmbedIE  from .smotri import SmotriIE  from .condenast import CondeNastIE @@ -291,6 +292,15 @@ class GenericIE(InfoExtractor):                  'skip_download': True,              },          }, +        # TVC embed +        { +            'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/', +            'info_dict': { +                'id': '55304', +                'ext': 'mp4', +                'title': 'Дошкольное воспитание', +            }, +        },          # SportBox embed          {              'url': 'http://www.vestifinance.ru/articles/25753', @@ -1301,6 +1311,11 @@ class GenericIE(InfoExtractor):          if rutv_url:              return self.url_result(rutv_url, 'RUTV') +        # Look for embedded TVC player +        rutv_url = TVCIE._extract_url(webpage) +        if rutv_url: +            return self.url_result(rutv_url, 'TVC') +          # Look for embedded SportBox player          sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)          if sportbox_urls: diff --git a/youtube_dl/extractor/tvc.py b/youtube_dl/extractor/tvc.py new file mode 100644 index 000000000..6b5d80aee --- /dev/null +++ b/youtube_dl/extractor/tvc.py @@ -0,0 +1,109 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( +    clean_html, +    int_or_none, +) + + +class TVCIE(InfoExtractor): +    _VALID_URL = r'http://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)' +    _TEST = { +        'url': 'http://www.tvc.ru/video/iframe/id/74622/isPlay/false/id_stat/channel/?acc_video_id=/channel/brand/id/17/show/episodes/episode_id/39702', +        'md5': 'bbc5ff531d1e90e856f60fc4b3afd708', +        'info_dict': { +            'id': '74622', +            'ext': 'mp4', +            'title': 'События. "События". Эфир от 22.05.2015 14:30', +            'thumbnail': 're:^https?://.*\.jpg$', +            'duration': 1122, +        }, +    } + +    @classmethod +    def _extract_url(cls, webpage): +        mobj = re.search( +            r'<iframe[^>]+?src=(["\'])(?P<url>(?:http://)?(?:www\.)?tvc\.ru/video/iframe/id/[^"]+)\1', webpage) +        if mobj: +            return mobj.group('url') + +    def _real_extract(self, url): +        video_id = self._match_id(url) + +        video = self._download_json( +            'http://www.tvc.ru/video/json/id/%s' % video_id, video_id) + +        formats = [] +        for info in video.get('path', {}).get('quality', []): +            video_url = info.get('url') +            if not video_url: +                continue +            format_id = self._search_regex( +                r'cdnvideo/([^/]+?)(?:-[^/]+?)?/', video_url, +                'format id', default=None) +            formats.append({ +                'url': video_url, +                'format_id': format_id, +                'width': int_or_none(info.get('width')), +                'height': int_or_none(info.get('height')), +                'tbr': int_or_none(info.get('bitrate')), +            }) +        self._sort_formats(formats) + +        return { +            'id': video_id, +            'title': video['title'], +            'thumbnail': video.get('picture'), +            'duration': int_or_none(video.get('duration')), +            'formats': formats, +        } + + +class TVCArticleIE(InfoExtractor): +    _VALID_URL = r'http://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)' +    _TESTS = [{ +        'url': 'http://www.tvc.ru/channel/brand/id/29/show/episodes/episode_id/39702/', +        'info_dict': { +            'id': '74622', +            'ext': 'mp4', +            'title': 'События. "События". Эфир от 22.05.2015 14:30', +            'description': 'md5:ad7aa7db22903f983e687b8a3e98c6dd', +            'thumbnail': 're:^https?://.*\.jpg$', +            'duration': 1122, +        }, +    }, { +        'url': 'http://www.tvc.ru/news/show/id/69944', +        'info_dict': { +            'id': '75399', +            'ext': 'mp4', +            'title': 'Эксперты: в столице встал вопрос о максимально безопасных остановках', +            'description': 'md5:f2098f71e21f309e89f69b525fd9846e', +            'thumbnail': 're:^https?://.*\.jpg$', +            'duration': 278, +        }, +    }, { +        'url': 'http://www.tvc.ru/channel/brand/id/47/show/episodes#', +        'info_dict': { +            'id': '2185', +            'ext': 'mp4', +            'title': 'Ещё не поздно. Эфир от 03.08.2013', +            'description': 'md5:51fae9f3f8cfe67abce014e428e5b027', +            'thumbnail': 're:^https?://.*\.jpg$', +            'duration': 3316, +        }, +    }] + +    def _real_extract(self, url): +        webpage = self._download_webpage(url, self._match_id(url)) +        return { +            '_type': 'url_transparent', +            'ie_key': 'TVC', +            'url': self._og_search_video_url(webpage), +            'title': clean_html(self._og_search_title(webpage)), +            'description': clean_html(self._og_search_description(webpage)), +            'thumbnail': self._og_search_thumbnail(webpage), +        } | 
