0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
yt-dlp/youtube_dl/extractor/thisav.py
Yen Chi Hsuan d8dbf8707d
[thisav] Improve title extraction (closes #10682)
I didn't add a test case as the one in #10682 looks like a copyrighted
product.
2016-09-18 18:35:38 +08:00

67 lines
2.3 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import re
from .jwplatform import JWPlatformBaseIE
from ..utils import remove_end
class ThisAVIE(JWPlatformBaseIE):
_VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
_TESTS = [{
'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
'md5': '0480f1ef3932d901f0e0e719f188f19b',
'info_dict': {
'id': '47734',
'ext': 'flv',
'title': '高樹マリア - Just fit',
'uploader': 'dj7970',
'uploader_id': 'dj7970'
}
}, {
'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
'md5': 'ba90c076bd0f80203679e5b60bf523ee',
'info_dict': {
'id': '242352',
'ext': 'mp4',
'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
'uploader': 'cybersluts',
'uploader_id': 'cybersluts',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'),
' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
video_url = self._html_search_regex(
r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
if video_url:
info_dict = {
'formats': [{
'url': video_url,
}],
}
else:
info_dict = self._extract_jwplayer_data(
webpage, video_id, require_title=False)
uploader = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
webpage, 'uploader name', fatal=False)
uploader_id = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
webpage, 'uploader id', fatal=False)
info_dict.update({
'id': video_id,
'uploader': uploader,
'uploader_id': uploader_id,
'title': title,
})
return info_dict