]>
jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/webofstories.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
13 class WebOfStoriesIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)'
15 _VIDEO_DOMAIN
= 'http://eu-mobile.webofstories.com/'
16 _GREAT_LIFE_STREAMER
= 'rtmp://eu-cdn1.webofstories.com/cfx/st/'
17 _USER_STREAMER
= 'rtmp://eu-users.webofstories.com/cfx/st/'
19 'url': 'http://www.webofstories.com/play/hans.bethe/71',
20 'md5': '373e4dd915f60cfe3116322642ddf364',
24 'title': 'The temperature of the sun',
25 'thumbnail': r
're:^https?://.*\.jpg$',
26 'description': 'Hans Bethe talks about calculating the temperature of the sun',
30 'url': 'http://www.webofstories.com/play/55908',
31 'md5': '2985a698e1fe3211022422c4b5ed962c',
35 'title': 'The story of Gemmata obscuriglobus',
36 'thumbnail': r
're:^https?://.*\.jpg$',
37 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
42 # malformed og:title meta
43 'url': 'http://www.webofstories.com/play/54215?o=MS',
47 'title': '"A Leg to Stand On"',
48 'thumbnail': r
're:^https?://.*\.jpg$',
49 'description': 'Oliver Sacks talks about the death and resurrection of a limb',
53 'skip_download': True,
57 def _real_extract(self
, url
):
58 video_id
= self
._match
_id
(url
)
60 webpage
= self
._download
_webpage
(url
, video_id
)
61 # Sometimes og:title meta is malformed
62 title
= self
._og
_search
_title
(webpage
, default
=None) or self
._html
_search
_regex
(
63 r
'(?s)<strong>Title:\s*</strong>(.+?)<', webpage
, 'title')
64 description
= self
._html
_search
_meta
('description', webpage
)
65 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
67 embed_params
= [s
.strip(" \r\n\t'") for s
in self
._search
_regex
(
68 r
'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
69 webpage
, 'embed params').split(',')]
72 _
, speaker_id
, story_id
, story_duration
,
73 speaker_type
, great_life
, _thumbnail
, _has_subtitles
,
74 story_filename
, _story_order
) = embed_params
76 is_great_life_series
= great_life
== 'true'
77 duration
= int_or_none(story_duration
)
79 # URL building, see: http://www.webofstories.com/scripts/player.js
81 if speaker_type
.lower() == 'ms':
82 ms_prefix
= 'mini_sites/'
84 if is_great_life_series
:
85 mp4_url
= '{0:}lives/{1:}/{2:}.mp4'.format(
86 self
._VIDEO
_DOMAIN
, speaker_id
, story_filename
)
88 streamer
= self
._GREAT
_LIFE
_STREAMER
89 play_path
= 'stories/{0:}/{1:}'.format(
90 speaker_id
, story_filename
)
92 mp4_url
= '{0:}{1:}{2:}/{3:}.mp4'.format(
93 self
._VIDEO
_DOMAIN
, ms_prefix
, speaker_id
, story_filename
)
95 streamer
= self
._USER
_STREAMER
96 play_path
= 'mp4:{0:}{1:}/{2}.mp4'.format(
97 ms_prefix
, speaker_id
, story_filename
)
100 'format_id': 'mp4_sd',
103 'format_id': 'rtmp_sd',
107 'play_path': play_path
,
110 self
._sort
_formats
(formats
)
116 'thumbnail': thumbnail
,
117 'description': description
,
118 'duration': duration
,
122 class WebOfStoriesPlaylistIE(InfoExtractor
):
123 _VALID_URL
= r
'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
125 'url': 'http://www.webofstories.com/playAll/donald.knuth',
127 'id': 'donald.knuth',
128 'title': 'Donald Knuth (Scientist)',
130 'playlist_mincount': 97,
133 def _real_extract(self
, url
):
134 playlist_id
= self
._match
_id
(url
)
136 webpage
= self
._download
_webpage
(url
, playlist_id
)
140 'http://www.webofstories.com/play/%s' % video_id
,
141 'WebOfStories', video_id
=video_id
)
142 for video_id
in orderedSet(re
.findall(r
'\bid=["\']td_(\d
+)', webpage))
145 title = self._search_regex(
146 r'<div
id="speakerName">\s
*<span
>([^
<]+)</span
>',
147 webpage, 'speaker
', default=None)
149 field = self._search_regex(
150 r'<span
id="primaryField">([^
<]+)</span
>',
151 webpage, 'field
', default=None)
153 title += ' (%s)' % field
156 title = self._search_regex(
157 r'<title
>Play\s
+all\s
+stories\s
*-\s
*([^
<]+)\s
*-\s
*Web\s
+of\s
+Stories
</title
>',
160 return self.playlist_result(entries, playlist_id, title)