diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-04-06 06:03:31 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-04-06 06:03:58 +0700 |
commit | 85e787f51d914c82309045fc87c1ac6bd6540023 (patch) | |
tree | 8ce71b96ad6dbc7bb753a2a832cca271ce0cf417 /youtube_dl | |
parent | 2a9e1e453ac1543426637d45bd59afe2783dc923 (diff) |
[cbsnews] Add support for cbsnews.com (Closes #2691)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/cbsnews.py | 87 |
2 files changed, 88 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 65d97d94f..eec8bff16 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -32,6 +32,7 @@ from .canal13cl import Canal13clIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE +from .cbsnews import CBSNewsIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py new file mode 100644 index 000000000..0bce7937f --- /dev/null +++ b/youtube_dl/extractor/cbsnews.py @@ -0,0 +1,87 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor + + +class CBSNewsIE(InfoExtractor): + IE_DESC = 'CBS News' + _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)' + + _TESTS = [ + { + 'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/', + 'info_dict': { + 'id': 'tesla-and-spacex-elon-musks-industrial-empire', + 'ext': 'flv', + 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire', + 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg', + 'duration': 791, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', + 'info_dict': { + 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', + 'ext': 'flv', + 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', + 'thumbnail': 'http://cbsnews2.cbsistatic.com/hub/i/r/2014/04/04/0c9fbc66-576b-41ca-8069-02d122060dd2/thumbnail/140x90/6dad7a502f88875ceac38202984b6d58/en-0404-werner-replace-640x360.jpg', + 'duration': 205, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_info = json.loads(self._html_search_regex( + r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'', + webpage, 'video JSON info')) + + item = video_info['item'] if 'item' in video_info else video_info + title = item.get('articleTitle') or item.get('hed') + duration = item.get('duration') + thumbnail = item.get('mediaImage') or item.get('thumbnail') + + formats = [] + for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']: + uri = item.get('media' + format_id + 'URI') + if not uri: + continue + fmt = { + 'url': uri, + 'format_id': format_id, + } + if uri.startswith('rtmp'): + fmt.update({ + 'app': 'ondemand?auth=cbs', + 'play_path': 'mp4:' + uri.split('<break>')[-1], + 'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf', + 'page_url': 'http://www.cbsnews.com', + 'ext': 'flv', + }) + elif uri.endswith('.m3u8'): + fmt['ext'] = 'mp4' + formats.append(fmt) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + }
\ No newline at end of file |