youtube-dl/youtube_dl/extractor/theintercept.py

50 lines
1.8 KiB
Python
Raw Normal View History

2016-10-02 20:39:18 +09:00
# coding: utf-8
2015-12-21 10:26:37 +09:00
from __future__ import unicode_literals
from .common import InfoExtractor
2015-12-24 06:36:53 +09:00
from ..compat import compat_str
2015-12-21 10:26:37 +09:00
from ..utils import (
2015-12-24 06:36:53 +09:00
parse_iso8601,
int_or_none,
2015-12-21 10:26:37 +09:00
ExtractorError,
)
2015-12-24 06:36:53 +09:00
2015-12-21 10:26:37 +09:00
class TheInterceptIE(InfoExtractor):
2016-09-08 20:29:05 +09:00
_VALID_URL = r'https?://theintercept\.com/fieldofvision/(?P<id>[^/?#]+)'
2015-12-21 10:26:37 +09:00
_TESTS = [{
'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
2015-12-24 06:36:53 +09:00
'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',
2015-12-21 10:26:37 +09:00
'info_dict': {
2015-12-24 06:36:53 +09:00
'id': '46214',
2015-12-21 10:26:37 +09:00
'ext': 'mp4',
'title': '#ThisIsACoup Episode Four: Surrender or Die',
'description': 'md5:74dd27f0e2fbd50817829f97eaa33140',
2015-12-24 06:36:53 +09:00
'timestamp': 1450429239,
'upload_date': '20151218',
'comment_count': int,
2015-12-21 10:26:37 +09:00
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2015-12-24 06:36:53 +09:00
json_data = self._parse_json(self._search_regex(
r'initialStoreTree\s*=\s*(?P<json_data>{.+})', webpage,
'initialStoreTree'), display_id)
2015-12-21 10:26:37 +09:00
for post in json_data['resources']['posts'].values():
if post['slug'] == display_id:
2015-12-24 06:36:53 +09:00
return {
'_type': 'url_transparent',
'url': 'jwplatform:%s' % post['fov_videoid'],
'id': compat_str(post['ID']),
'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')