w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[thisamericanlife] get info from <meta> tags

Browse source
This commit is contained in:
Eric Wong 2015-06-15 09:35:48 -07:00 committed by Sergey M․
parent 2a46a27e6c
commit e41840c522
1 changed files with 13 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/extractor/thisamericanlife.py
View file

@ -6,6 +6,7 @@ from .common import InfoExtractor
class ThisAmericanLifeIE(InfoExtractor): class ThisAmericanLifeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/radio-archives/episode/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/radio-archives/episode/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one', 'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one',
'md5': '5cda28076c9f9d1fd0b0f5cff5959948', 'md5': '5cda28076c9f9d1fd0b0f5cff5959948',
@ -14,19 +15,26 @@ class ThisAmericanLifeIE(InfoExtractor):
'title': '487: Harper High School, Part One', 'title': '487: Harper High School, Part One',
'url' : 'http://stream.thisamericanlife.org/487/stream/487_64k.m3u8', 'url' : 'http://stream.thisamericanlife.org/487/stream/487_64k.m3u8',
'ext': 'aac', 'ext': 'aac',
} 'thumbnail': 'http://www.thisamericanlife.org/sites/default/files/imagecache/large_square/episodes/487_lg_2.jpg',
'description': 'We spent five months at Harper High School in Chicago, where last year alone 29 current and recent students were shot. 29. We went to get a sense of what it means to live in the midst of all this gun violence, how teens and adults navigate a world of funerals and Homecoming dances.',
},
'params': {
# m38u download
'skip_download': True,
},
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1[^>]*>(.*?)</h1>', webpage, 'title') # TODO check to see if there's a free mp3. if so, download that, otherwise get the m3u8 stream.
media_url = 'http://stream.thisamericanlife.org/' + video_id + '/stream/' + video_id + '_64k.m3u8'
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': self._html_search_regex(r'<meta property="twitter:title" content="(.*?)"', webpage, 'title'),
'url': media_url, 'url': 'http://stream.thisamericanlife.org/' + video_id + '/stream/' + video_id + '_64k.m3u8',
'ext': 'aac', 'ext': 'aac',
'thumbnail': self._html_search_regex(r'<meta property="og:image" content="(.*?)"', webpage, 'thumbnail'),
'description': self._html_search_regex(r'<meta name="description" content="(.*?)"', webpage, 'description'),
} }