2 from __future__ import unicode_literals
5 from .common import InfoExtractor
8 class DemocracynowIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?democracynow.org/?(?P<id>[^\?]*)'
10 IE_NAME = 'democracynow'
12 'url': 'http://www.democracynow.org/shows/2015/7/3',
14 'id': '2015-0703-001',
16 'title': 'July 03, 2015 - Democracy Now!',
17 'description': 'A daily independent global news hour with Amy Goodman & Juan Gonz\xe1lez "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
18 'uploader': 'Democracy Now',
22 'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
24 'id': '2015-0703-001',
26 'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
27 'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
28 'uploader': 'Democracy Now',
33 def _real_extract(self, url):
34 display_id = self._match_id(url)
35 base_host = re.search(r'^(.+?://[^/]+)', url).group(1)
38 webpage = self._download_webpage(url, display_id)
39 description = self._og_search_description(webpage)
41 jstr = self._search_regex(r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json')
42 js = self._parse_json(jstr, display_id)
46 for key in ('caption_file', '.......'):
47 # ....... = pending vtt support that doesn't clobber srt 'chapter_file':
49 if url == '' or url is None:
51 if not re.match(r'^https?://', url):
53 ext = re.search(r'\.([^\.]+)$', url).group(1)
58 for key in ('file', 'audio', 'video'):
60 if url == '' or url is None:
62 if not re.match(r'^https?://', url):
64 purl = re.search(r'/(?P<dir>[^/]+)/(?:dn)?(?P<fn>[^/]+?)\.(?P<ext>[^\.\?]+)(?P<hasparams>\?|$)', url)
66 video_id = purl.group('fn')
67 if js.get('start') is not None:
68 url += '&' if purl.group('hasparams') == '?' else '?'
69 url = url + 'start=' + str(js.get('start'))
71 'format_id': purl.group('dir'),
72 'ext': purl.group('ext'),
75 self._sort_formats(formats)
78 'title': js.get('title'),
79 'description': description,
80 'uploader': 'Democracy Now',
81 'subtitles': subtitles,