]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/thvideo.py
Merge remote-tracking branch 'diffycat/thvideo'
[yt-dlp.git] / youtube_dl / extractor / thvideo.py
CommitLineData
72e450c5
AL
1# coding: utf-8
2from __future__ import unicode_literals
3
4import re
5
6from .common import InfoExtractor
7from ..utils import (
8 unified_strdate
9)
10
11
12class THVideoIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?thvideo\.tv/v/th(?P<id>[0-9]+)'
14 _TEST = {
15 'url': 'http://thvideo.tv/v/th1987/',
16 'md5': 'fa107b1f73817e325e9433505a70db50',
17 'info_dict': {
18 'id': '1987',
19 'ext': 'mp4',
20 'title': '【动画】秘封活动记录 ~ The Sealed Esoteric History.分镜稿预览',
21 'display_id': 'th1987',
22 'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg',
23 'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 ~ The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...',
24 'upload_date': '20140722'
25 }
26 }
27
28 def _real_extract(self, url):
29 mobj = re.match(self._VALID_URL, url)
30 video_id = mobj.group('id')
31
32 # extract download link from mobile player page
33 webpage_player = self._download_webpage('http://thvideo.tv/mobile.php?cid=%s-0' % video_id, video_id)
34 video_url = self._html_search_regex(r'<source src="(.*?)" type', webpage_player, 'video url')
35
36 # extract video info from main page
37 webpage = self._download_webpage(url, video_id)
38 title = self._og_search_title(webpage)
39 display_id = 'th%s' % video_id
40 thumbnail = self._og_search_thumbnail(webpage)
41 description = self._og_search_description(webpage)
42 upload_date_raw = self._html_search_regex(r'span itemprop="datePublished" content="(.*?)">', webpage,
43 'upload date', fatal=False)
44 upload_date = unified_strdate(upload_date_raw)
45
46 return {
47 'id': video_id,
48 'ext': 'mp4',
49 'url': video_url,
50 'title': title,
51 'display_id': display_id,
52 'thumbnail': thumbnail,
53 'description': description,
54 'upload_date': upload_date
55 }