yt-dlp/youtube_dl/extractor/vidto.py

58 lines
1.6 KiB
Python
Raw Normal View History

2015-10-14 09:11:52 +00:00
# coding: utf-8
from __future__ import unicode_literals
import time
from .common import InfoExtractor
from ..utils import (
encode_dict,
remove_end,
urlencode_postdata,
2015-10-14 09:11:52 +00:00
)
from ..compat import compat_urllib_request
2015-10-14 09:11:52 +00:00
class VidtoIE(InfoExtractor):
IE_NAME = 'vidto'
IE_DESC = 'VidTo.me'
_VALID_URL = r'https?://(?:www\.)?vidto\.me/(?P<id>[0-9a-zA-Z]+)\.html'
_TEST = {
'url': 'http://vidto.me/ku5glz52nqe1.html',
'info_dict': {
'id': 'ku5glz52nqe1',
'ext': 'mp4',
'title': 'test'
2015-10-14 09:11:52 +00:00
}
}
def _real_extract(self, url):
2015-10-17 17:35:41 +00:00
video_id = self._match_id(url)
2015-10-14 09:11:52 +00:00
page = self._download_webpage(
'http://vidto.me/%s.html' % video_id, video_id, 'Downloading video page')
2015-10-14 09:11:52 +00:00
title = remove_end(self._html_search_regex(
r'<Title>\s*([^<]+)\s*</Title>', page, 'title'), ' - Vidto')
2015-10-17 17:35:41 +00:00
hidden_fields = self._hidden_inputs(page)
2015-10-14 09:11:52 +00:00
self.to_screen('Waiting for countdown...')
2015-10-14 09:11:52 +00:00
time.sleep(7)
req = compat_urllib_request.Request(
url, urlencode_postdata(encode_dict(hidden_fields)))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
2015-10-14 09:11:52 +00:00
post_result = self._download_webpage(
2015-10-17 17:35:41 +00:00
req, video_id,
note='Proceed to video...', errnote='unable to proceed')
2015-10-14 09:11:52 +00:00
file_link = self._search_regex(
r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)', post_result, 'file_link')
2015-10-14 09:11:52 +00:00
return {
'id': video_id,
'url': file_link,
'title': title,
}