Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-26 18:34:32 +01:00
Code Issues Releases Wiki Activity

[democracynow] Improve extraction

Browse Source
This commit is contained in:
Sergey M․ 2016-04-08 22:27:27 +06:00
parent a134426d61
commit 18da24634c
1 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
youtube_dl/extractor/democracynow.py
View File

@ -38,17 +38,32 @@ class DemocracynowIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
description = self._og_search_description(webpage, default=None)
json_data = self._parse_json(self._search_regex( json_data = self._parse_json(self._search_regex(
r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'), r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
display_id) display_id)
video_id = None
title = json_data['title']
formats = [] formats = []
default_lang = 'en' video_id = None
for key in ('file', 'audio', 'video', 'high_res_video'):
media_url = json_data.get(key, '')
if not media_url:
continue
media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
formats.append({
'url': media_url,
'vcodec': 'none' if key == 'audio' else None,
})
self._sort_formats(formats)
default_lang = 'en'
subtitles = {} subtitles = {}
def add_subtitle_item(lang, info_dict): def add_subtitle_item(lang, info_dict):
@ -68,22 +83,13 @@ class DemocracynowIE(InfoExtractor):
'url': compat_urlparse.urljoin(url, subtitle_item['url']), 'url': compat_urlparse.urljoin(url, subtitle_item['url']),
}) })
for key in ('file', 'audio', 'video'): description = self._og_search_description(webpage, default=None)
media_url = json_data.get(key, '')
if not media_url:
continue
media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
formats.append({
'url': media_url,
})
self._sort_formats(formats)
return { return {
'id': video_id or display_id, 'id': video_id or display_id,
'title': json_data['title'], 'title': title,
'description': description, 'description': description,
'thumbnail': json_data.get('image'),
'subtitles': subtitles, 'subtitles': subtitles,
'formats': formats, 'formats': formats,
} }