]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/aenetworks.py
1376dd70fc78d0e8d8f56276ec5f25e719d08d55
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
12 from ..compat
import (
17 class AENetworksBaseIE(InfoExtractor
):
18 def theplatform_url_result(self
, theplatform_url
, video_id
, query
):
20 '_type': 'url_transparent',
23 update_url_query(theplatform_url
, query
),
29 'force_smil_url': True
31 'ie_key': 'ThePlatform',
35 class AENetworksIE(AENetworksBaseIE
):
36 IE_NAME
= 'aenetworks'
37 IE_DESC
= 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
38 _VALID_URL
= r
'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/shows/(?P<id>[^/]+(?:/[^/]+){0,2})'
40 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
41 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
45 'title': 'Winter Is Coming',
46 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
47 'timestamp': 1338306241,
48 'upload_date': '20120529',
49 'uploader': 'AENE-NEW',
51 'add_ie': ['ThePlatform'],
53 'url': 'http://www.history.com/shows/ancient-aliens/season-1',
57 'playlist_mincount': 5,
59 'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
62 'title': 'Atlanta Plastic',
64 'playlist_mincount': 2,
66 'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
69 'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
72 'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
76 def _real_extract(self
, url
):
77 display_id
= self
._match
_id
(url
)
78 webpage
= self
._download
_webpage
(url
, display_id
)
79 url_parts
= display_id
.split('/')
80 url_parts_len
= len(url_parts
)
81 if url_parts_len
== 1:
83 for season_url_path
in re
.findall(r
'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts
[0], webpage
):
84 entries
.append(self
.url_result(
85 compat_urlparse
.urljoin(url
, season_url_path
), 'AENetworks'))
86 return self
.playlist_result(
87 entries
, self
._html
_search
_meta
('aetn:SeriesId', webpage
),
88 self
._html
_search
_meta
('aetn:SeriesTitle', webpage
))
89 elif url_parts_len
== 2:
91 for episode_item
in re
.findall(r
'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage
):
92 episode_attributes
= extract_attributes(episode_item
)
93 episode_url
= compat_urlparse
.urljoin(
94 url
, episode_attributes
['data-canonical'])
95 entries
.append(self
.url_result(
96 episode_url
, 'AENetworks',
97 episode_attributes
['data-videoid']))
98 return self
.playlist_result(
99 entries
, self
._html
_search
_meta
('aetn:SeasonId', webpage
))
101 video_id
= self
._html
_search
_meta
('aetn:VideoID', webpage
)
102 media_url
= self
._search
_regex
(
103 r
"media_url\s*=\s*'([^']+)'", webpage
, 'video url')
105 info
= self
._search
_json
_ld
(webpage
, video_id
, fatal
=False)
106 info
.update(self
.theplatform_url_result(
107 media_url
, video_id
, {
109 'assetTypes': 'medium_video_s3'
114 class HistoryTopicIE(AENetworksBaseIE
):
115 IE_NAME
= 'history:topic'
116 IE_DESC
= 'History.com Topic'
117 _VALID_URL
= r
'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)/videos(?:/(?P<display_id>[^/?#]+))?'
119 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
123 'title': "Bet You Didn't Know: Valentine's Day",
124 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
125 'timestamp': 1375819729,
126 'upload_date': '20130806',
127 'uploader': 'AENE-NEW',
131 'skip_download': True,
133 'add_ie': ['ThePlatform'],
135 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
138 'id': 'world-war-i-history',
140 'playlist_mincount': 24,
142 'url': 'http://www.history.com/topics/world-war-i-history/videos',
143 'only_matching': True,
146 def _real_extract(self
, url
):
147 topic_id
, display_id
= re
.match(self
._VALID
_URL
, url
).groups()
149 webpage
= self
._download
_webpage
(url
, display_id
)
150 release_url
, video_id
= re
.search(r
"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage
).groups()
151 release_url
= unescapeHTML(release_url
)
153 return self
.theplatform_url_result(
154 release_url
, video_id
, {
159 webpage
= self
._download
_webpage
(url
, topic_id
)
161 for episode_item
in re
.findall(r
'<a.+?data-release-url="[^"]+"[^>]*>', webpage
):
162 video_attributes
= extract_attributes(episode_item
)
163 entries
.append(self
.theplatform_url_result(
164 video_attributes
['data-release-url'], video_attributes
['data-id'], {
168 return self
.playlist_result(entries
, topic_id
)