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[\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'(?: