ytdl/youtube_dl/extractor/thvideo.py

85 lines
3.0 KiB
Python
Raw Normal View History

2014-09-21 11:21:29 +02:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate
)
class THVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
2014-09-21 11:21:29 +02:00
_TEST = {
'url': 'http://thvideo.tv/v/th1987/',
'md5': 'fa107b1f73817e325e9433505a70db50',
'info_dict': {
'id': '1987',
'ext': 'mp4',
'title': '【动画】秘封活动记录 The Sealed Esoteric History.分镜稿预览',
'display_id': 'th1987',
'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg',
'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...',
'upload_date': '20140722'
}
}
def _real_extract(self, url):
2014-09-29 00:38:37 +02:00
video_id = self._match_id(url)
2014-09-21 11:21:29 +02:00
# extract download link from mobile player page
2014-09-21 16:32:38 +02:00
webpage_player = self._download_webpage(
'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id),
video_id, note='Downloading video source page')
video_url = self._html_search_regex(
r'<source src="(.*?)" type', webpage_player, 'video url')
2014-09-21 11:21:29 +02:00
# extract video info from main page
2014-09-21 16:32:38 +02:00
webpage = self._download_webpage(
'http://thvideo.tv/v/th%s' % (video_id), video_id)
2014-09-21 11:21:29 +02:00
title = self._og_search_title(webpage)
display_id = 'th%s' % video_id
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
2014-09-21 16:32:38 +02:00
upload_date = unified_strdate(self._html_search_regex(
r'span itemprop="datePublished" content="(.*?)">', webpage,
'upload date', fatal=False))
2014-09-21 11:21:29 +02:00
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
'display_id': display_id,
'thumbnail': thumbnail,
'description': description,
'upload_date': upload_date
2014-09-21 16:32:38 +02:00
}
2014-09-28 21:36:55 +02:00
class THVideoPlaylistIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)'
_TEST = {
'url': 'http://thvideo.tv/mylist2',
'info_dict': {
'id': '2',
'title': '幻想万華鏡',
},
'playlist_mincount': 23,
}
def _real_extract(self, url):
2014-09-29 00:38:37 +02:00
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
list_title = self._html_search_regex(
r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title',
fatal=False)
2014-09-28 21:36:55 +02:00
entries = [
self.url_result('http://thvideo.tv/v/th' + id, 'THVideo')
for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)]
2014-09-29 00:38:37 +02:00
return self.playlist_result(entries, playlist_id, list_title)