jon1scr
/
yt-dlc
forked from minhngoc25a/yt-dlc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[openload] Use original host during extraction (closes #18211)

This commit is contained in:
Sergey M․ 2018-11-17 16:59:20 +07:00
parent 0919cd4d01
commit d0058c76d5
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 19 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
youtube_dl/extractor/openload.py
View File

@ -243,7 +243,18 @@ class PhantomJSwrapper(object):
class OpenloadIE(InfoExtractor): class OpenloadIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' _VALID_URL = r'''(?x)
https?://
(?P<host>
(?:www\.)?
(?:
openload\.(?:co|io|link)|
oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun)
)
)/
(?:f|embed)/
(?P<id>[a-zA-Z0-9-_]+)
'''
_TESTS = [{ _TESTS = [{
'url': 'https://openload.co/f/kUEfGclsU9o', 'url': 'https://openload.co/f/kUEfGclsU9o',
@ -334,8 +345,11 @@ class OpenloadIE(InfoExtractor):
webpage) webpage)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
url_pattern = 'https://openload.co/%%s/%s/' % video_id host = mobj.group('host')
video_id = mobj.group('id')
url_pattern = 'https://%s/%%s/%s/' % (host, video_id)
headers = { headers = {
'User-Agent': self._USER_AGENT, 'User-Agent': self._USER_AGENT,
} }
@ -368,7 +382,7 @@ class OpenloadIE(InfoExtractor):
r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage, r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage,
'stream URL')) 'stream URL'))
video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id video_url = 'https://%s/stream/%s?mime=true' % (host, decoded_id)
title = self._og_search_title(webpage, default=None) or self._search_regex( title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage, r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@ -379,7 +393,7 @@ class OpenloadIE(InfoExtractor):
entry = entries[0] if entries else {} entry = entries[0] if entries else {}
subtitles = entry.get('subtitles') subtitles = entry.get('subtitles')
info_dict = { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
@ -388,4 +402,3 @@ class OpenloadIE(InfoExtractor):
'subtitles': subtitles, 'subtitles': subtitles,
'http_headers': headers, 'http_headers': headers,
} }
return info_dict