0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-04 04:07:26 +00:00
yt-dlp/yt_dlp/extractor/theintercept.py

46 lines
1.7 KiB
Python
Raw Normal View History

2015-12-21 01:26:37 +00:00
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
2015-12-21 01:26:37 +00:00
)
2015-12-23 21:36:53 +00:00
2015-12-21 01:26:37 +00:00
class TheInterceptIE(InfoExtractor):
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://theintercept\.com/fieldofvision/(?P<id>[^/?#]+)'
2015-12-21 01:26:37 +00:00
_TESTS = [{
'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
2015-12-23 21:36:53 +00:00
'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',
2015-12-21 01:26:37 +00:00
'info_dict': {
2015-12-23 21:36:53 +00:00
'id': '46214',
2015-12-21 01:26:37 +00:00
'ext': 'mp4',
'title': '#ThisIsACoup Episode Four: Surrender or Die',
'description': 'md5:74dd27f0e2fbd50817829f97eaa33140',
2015-12-23 21:36:53 +00:00
'timestamp': 1450429239,
'upload_date': '20151218',
'comment_count': int,
},
2015-12-21 01:26:37 +00:00
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2015-12-23 21:36:53 +00:00
json_data = self._parse_json(self._search_regex(
r'initialStoreTree\s*=\s*(?P<json_data>{.+})', webpage,
'initialStoreTree'), display_id)
2015-12-21 01:26:37 +00:00
for post in json_data['resources']['posts'].values():
if post['slug'] == display_id:
2015-12-23 21:36:53 +00:00
return {
'_type': 'url_transparent',
'url': 'jwplatform:{}'.format(post['fov_videoid']),
'id': str(post['ID']),
2015-12-23 21:36:53 +00:00
'display_id': display_id,
'title': post['title'],
'description': post.get('excerpt'),
'timestamp': parse_iso8601(post.get('date')),
'comment_count': int_or_none(post.get('comments_number')),
}
raise ExtractorError('Unable to find the current post')