mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-11-23 22:26:53 +01:00
[miaopai] Add new extractor
This commit is contained in:
parent
4809490108
commit
95be19d436
@ -471,6 +471,7 @@ from .metacafe import MetacafeIE
|
||||
from .metacritic import MetacriticIE
|
||||
from .mgoon import MgoonIE
|
||||
from .mgtv import MGTVIE
|
||||
from .miaopai import MiaoPaiIE
|
||||
from .microsoftvirtualacademy import (
|
||||
MicrosoftVirtualAcademyIE,
|
||||
MicrosoftVirtualAcademyCourseIE,
|
||||
|
44
youtube_dl/extractor/miaopai.py
Normal file
44
youtube_dl/extractor/miaopai.py
Normal file
@ -0,0 +1,44 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import sanitized_Request
|
||||
|
||||
|
||||
class MiaoPaiIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+).htm'
|
||||
_TEST = {
|
||||
'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
|
||||
'md5': '095ed3f1cd96b821add957bdc29f845b',
|
||||
'info_dict': {
|
||||
'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
|
||||
'ext': 'mp4',
|
||||
'title': '西游记音乐会的秒拍视频',
|
||||
'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
|
||||
}
|
||||
}
|
||||
|
||||
_USER_AGENT_IPAD = 'User-Agent:Mozilla/5.0 ' \
|
||||
'(iPad; CPU OS 9_1 like Mac OS X) ' \
|
||||
'AppleWebKit/601.1.46 (KHTML, like Gecko) ' \
|
||||
'Version/9.0 Mobile/13B143 Safari/601.1'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
request = sanitized_Request(url)
|
||||
request.add_header('User-Agent', self._USER_AGENT_IPAD)
|
||||
webpage = self._download_webpage(request, video_id)
|
||||
|
||||
title = self._html_search_regex(r'<title>([^<]*)</title>',
|
||||
webpage,
|
||||
'title')
|
||||
regex = r"""<div *class=['"]video_img[^>]*data-url=['"]([^'"]*\.jpg)['"]"""
|
||||
thumbnail = self._html_search_regex(regex, webpage, '')
|
||||
regex = r"""<video *[^>]*src=['"]([^'"]*)['"]""",
|
||||
video_url = self._html_search_regex(regex, webpage, '')
|
||||
|
||||
return {'id': video_id,
|
||||
'title': title,
|
||||
'url': video_url,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
Loading…
Reference in New Issue
Block a user