1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 20:48:04 +01:00
youtube-dl/youtube_dl/extractor/thisav.py

48 lines
1.6 KiB
Python
Raw Normal View History

2014-11-23 20:41:03 +01:00
# coding: utf-8
from __future__ import unicode_literals
2013-07-17 11:16:53 +02:00
import re
from .common import InfoExtractor
from ..utils import determine_ext
2013-07-17 11:16:53 +02:00
class ThisAVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
_TEST = {
'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'
2013-07-17 11:16:53 +02:00
}
}
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 = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
2013-07-17 11:16:53 +02:00
video_url = self._html_search_regex(
r"addVariable\('file','([^']+)'\);", webpage, 'video url')
2013-07-17 11:16:53 +02:00
uploader = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
webpage, 'uploader name', fatal=False)
2013-07-17 11:16:53 +02:00
uploader_id = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
webpage, 'uploader id', fatal=False)
2013-07-17 11:16:53 +02:00
ext = determine_ext(video_url)
2014-11-23 20:41:03 +01:00
2013-07-17 11:16:53 +02:00
return {
2014-11-23 21:20:46 +01:00
'id': video_id,
'url': video_url,
'uploader': uploader,
2013-07-17 11:16:53 +02:00
'uploader_id': uploader_id,
2014-11-23 21:20:46 +01:00
'title': title,
'ext': ext,
2013-07-17 11:16:53 +02:00
}