mirror/yt-dlc
1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-23 16:26:40 +00:00
Code Issues Releases Wiki Activity

[veehd] Improve extraction

Browse source
This commit is contained in:
Sergey M․ 2015-01-11 16:20:16 +06:00
parent 6a5fa75490
commit a798e64c15
1 changed files with 27 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/extractor/veehd.py
View file

@ -47,17 +47,34 @@ class VeeHDIE(InfoExtractor):
self._download_webpage(player_url, video_id, 'Requesting player page') self._download_webpage(player_url, video_id, 'Requesting player page')
player_page = self._download_webpage( player_page = self._download_webpage(
player_url, video_id, 'Downloading player page') player_url, video_id, 'Downloading player page')
config_json = self._search_regex(
r'value=\'config=({.+?})\'', player_page, 'config json')
config = json.loads(config_json)
config_json = self._search_regex(
r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
if config_json:
config = json.loads(config_json)
video_url = compat_urlparse.unquote(config['clip']['url']) video_url = compat_urlparse.unquote(config['clip']['url'])
else:
iframe_src = self._search_regex(
r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
iframe_url = 'http://veehd.com/%s' % iframe_src
self._download_webpage(iframe_url, video_id, 'Requesting iframe page')
iframe_page = self._download_webpage(
iframe_url, video_id, 'Downloading iframe page')
video_url = self._search_regex(
r"file\s*:\s*'([^']+)'", iframe_page, 'video url')
title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>', uploader_id = self._html_search_regex(
r'<a href="/profile/\d+">(.+?)</a>',
webpage, 'uploader') webpage, 'uploader')
thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"', thumbnail = self._search_regex(
r'<img id="veehdpreview" src="(.+?)"',
webpage, 'thumbnail') webpage, 'thumbnail')
description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul', description = self._html_search_regex(
r'<td class="infodropdown".*?<div>(.*?)<ul',
webpage, 'description', flags=re.DOTALL) webpage, 'description', flags=re.DOTALL)
return { return {