aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/thisamericanlife.py
diff options
context:
space:
mode:
authorEric Wong <eric@taedium.com>2015-06-15 09:35:48 -0700
committerSergey M․ <dstftw@gmail.com>2015-07-04 05:12:20 +0600
commite41840c522fa09a08812c6e6724063f955426f21 (patch)
tree6765b2658785eca6f3339bc2e7e1f6d6e2ff4ab5 /youtube_dl/extractor/thisamericanlife.py
parent2a46a27e6c704f7b99242243747fa7d8ac68cefc (diff)
[thisamericanlife] get info from <meta> tags
Diffstat (limited to 'youtube_dl/extractor/thisamericanlife.py')
-rw-r--r--youtube_dl/extractor/thisamericanlife.py18
1 files changed, 13 insertions, 5 deletions
diff --git a/youtube_dl/extractor/thisamericanlife.py b/youtube_dl/extractor/thisamericanlife.py
index 6118afa1a..300884c1d 100644
--- a/youtube_dl/extractor/thisamericanlife.py
+++ b/youtube_dl/extractor/thisamericanlife.py
@@ -6,6 +6,7 @@ from .common import InfoExtractor
class ThisAmericanLifeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/radio-archives/episode/(?P<id>\d+)'
+
_TEST = {
'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one',
'md5': '5cda28076c9f9d1fd0b0f5cff5959948',
@@ -14,19 +15,26 @@ class ThisAmericanLifeIE(InfoExtractor):
'title': '487: Harper High School, Part One',
'url' : 'http://stream.thisamericanlife.org/487/stream/487_64k.m3u8',
'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):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(r'<h1[^>]*>(.*?)</h1>', webpage, 'title')
- media_url = 'http://stream.thisamericanlife.org/' + video_id + '/stream/' + video_id + '_64k.m3u8'
+ # TODO check to see if there's a free mp3. if so, download that, otherwise get the m3u8 stream.
return {
'id': video_id,
- 'title': title,
- 'url': media_url,
+ 'title': self._html_search_regex(r'<meta property="twitter:title" content="(.*?)"', webpage, 'title'),
+ 'url': 'http://stream.thisamericanlife.org/' + video_id + '/stream/' + video_id + '_64k.m3u8',
'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'),
}