diff options
Diffstat (limited to 'youtube_dl/extractor/nbc.py')
| -rw-r--r-- | youtube_dl/extractor/nbc.py | 24 |
1 files changed, 24 insertions, 0 deletions
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index ff750de3f..1a63ab56a 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -6,6 +6,30 @@ from .common import InfoExtractor from ..utils import find_xpath_attr, compat_str +class NBCIE(InfoExtractor): + _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)' + + _TEST = { + 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', + 'md5': '54d0fbc33e0b853a65d7b4de5c06d64e', + 'info_dict': { + 'id': 'u1RInQZRN7QJ', + 'ext': 'flv', + 'title': 'I Am a Firefighter', + 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url') + if theplatform_url.startswith('//'): + theplatform_url = 'http:' + theplatform_url + return self.url_result(theplatform_url) + + class NBCNewsIE(InfoExtractor): _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)' |