]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/theintercept.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
5 from ..compat
import compat_str
13 class TheInterceptIE(InfoExtractor
):
14 _VALID_URL
= r
'https://theintercept.com/fieldofvision/(?P<id>[^/?#]+)'
16 'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
17 'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',
21 'title': '#ThisIsACoup – Episode Four: Surrender or Die',
22 'description': 'md5:74dd27f0e2fbd50817829f97eaa33140',
23 'timestamp': 1450429239,
24 'upload_date': '20151218',
29 def _real_extract(self
, url
):
30 display_id
= self
._match
_id
(url
)
31 webpage
= self
._download
_webpage
(url
, display_id
)
33 json_data
= self
._parse
_json
(self
._search
_regex
(
34 r
'initialStoreTree\s*=\s*(?P<json_data>{.+})', webpage
,
35 'initialStoreTree'), display_id
)
37 for post
in json_data
['resources']['posts'].values():
38 if post
['slug'] == display_id
:
40 '_type': 'url_transparent',
41 'url': 'jwplatform:%s' % post
['fov_videoid'],
42 'id': compat_str(post
['ID']),
43 'display_id': display_id
,
44 'title': post
['title'],
45 'description': post
.get('excerpt'),
46 'timestamp': parse_iso8601(post
.get('date')),
47 'comment_count': int_or_none(post
.get('comments_number')),
49 raise ExtractorError('Unable to find the current post')