]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/stitcher.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
14 class StitcherIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
17 'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
18 'md5': '391dd4e021e6edeb7b8e68fbf2e9e940',
22 'title': 'Machine Learning Mastery and Cancer Clusters',
23 'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3',
25 'thumbnail': r
're:^https?://.*\.jpg',
28 'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
31 'display_id': 'the-rare-hourlong-comedy-plus',
33 'title': "The CW's 'Crazy Ex-Girlfriend'",
34 'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17',
36 'thumbnail': r
're:^https?://.*\.jpg',
39 'skip_download': True,
43 'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true',
44 'only_matching': True,
46 'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true',
47 'only_matching': True,
50 def _real_extract(self
, url
):
51 mobj
= re
.match(self
._VALID
_URL
, url
)
52 audio_id
= mobj
.group('id')
53 display_id
= mobj
.group('display_id') or audio_id
55 webpage
= self
._download
_webpage
(url
, display_id
)
57 episode
= self
._parse
_json
(
58 js_to_json(self
._search
_regex
(
59 r
'(?s)var\s+stitcher(?:Config)?\s*=\s*({.+?});\n', webpage
, 'episode config')),
60 display_id
)['config']['episode']
62 title
= unescapeHTML(episode
['title'])
64 'url': episode
[episode_key
],
65 'ext': determine_ext(episode
[episode_key
]) or 'mp3',
67 } for episode_key
in ('episodeURL',) if episode
.get(episode_key
)]
68 description
= self
._search
_regex
(
69 r
'Episode Info:\s*</span>([^<]+)<', webpage
, 'description', fatal
=False)
70 duration
= int_or_none(episode
.get('duration'))
71 thumbnail
= episode
.get('episodeImage')
75 'display_id': display_id
,
77 'description': description
,
79 'thumbnail': thumbnail
,