1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-22 15:57:23 +00:00

[drtuber] Extract display_id

This commit is contained in:
Sergey M․ 2014-09-02 20:39:16 +07:00
parent eade1d7eab
commit 1bf8cf5c2c

View file

@ -7,7 +7,7 @@ from ..utils import str_to_int
class DrTuberIE(InfoExtractor): class DrTuberIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)' _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
_TEST = { _TEST = {
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd', 'md5': '93e680cf2536ad0dfb7e74d94a89facd',
@ -27,8 +27,9 @@ class DrTuberIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
video_url = self._html_search_regex( video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL') r'<source src="([^"]+)"', webpage, 'video URL')
@ -56,6 +57,7 @@ class DrTuberIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'url': video_url, 'url': video_url,
'title': title, 'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,