]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/americastestkitchen.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
13 class AmericasTestKitchenIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
16 'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party',
17 'md5': 'b861c3e365ac38ad319cfd509c30577f',
20 'title': 'Summer Dinner Party',
22 'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec',
23 'thumbnail': r
're:^https?://.*\.jpg',
24 'timestamp': 1497285541,
25 'upload_date': '20170612',
26 'uploader_id': 'roger.metcalf@americastestkitchen.com',
27 'release_date': '20170617',
28 'series': "America's Test Kitchen",
30 'episode': 'Summer Dinner Party',
34 'skip_download': True,
37 'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
38 'only_matching': True,
41 def _real_extract(self
, url
):
42 video_id
= self
._match
_id
(url
)
44 webpage
= self
._download
_webpage
(url
, video_id
)
46 video_data
= self
._parse
_json
(
48 r
'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
49 webpage
, 'initial context'),
54 (lambda x
: x
['episodeDetail']['content']['data'],
55 lambda x
: x
['videoDetail']['content']['data']), dict)
56 ep_meta
= ep_data
.get('full_video', {})
58 zype_id
= ep_meta
.get('zype_id')
60 embed_url
= 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id
63 partner_id
= self
._search
_regex
(
64 r
'src=["\'](?
:https?
:)?
//(?
:[^
/]+\
.)kaltura\
.com
/(?
:[^
/]+/)*(?
:p|partner_id
)/(\d
+)',
65 webpage, 'kaltura partner
id')
66 external_id = ep_data.get('external_id
') or ep_meta['external_id
']
67 embed_url = 'kaltura
:%s:%s' % (partner_id, external_id)
70 title = ep_data.get('title
') or ep_meta.get('title
')
71 description = clean_html(ep_meta.get('episode_description
') or ep_data.get(
72 'description
') or ep_meta.get('description
'))
73 thumbnail = try_get(ep_meta, lambda x: x['photo
']['image_url
'])
74 release_date = unified_strdate(ep_data.get('aired_at
'))
76 season_number = int_or_none(ep_meta.get('season_number
'))
77 episode = ep_meta.get('title
')
78 episode_number = int_or_none(ep_meta.get('episode_number
'))
81 '_type
': 'url_transparent
',
85 'description
': description,
86 'thumbnail
': thumbnail,
87 'release_date
': release_date,
88 'series
': "America's Test Kitchen
",
89 'season_number': season_number,
91 'episode_number': episode_number,