Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/played.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import os.path
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     compat_urllib_parse,
  11     compat_urllib_request,
  12 )
  13
  14
  15 class PlayedIE(InfoExtractor):
  16     IE_NAME = 'played.to'
  17     _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
  18
  19     _TEST = {
  20         'url': 'http://played.to/j2f2sfiiukgt',
  21         'md5': 'c2bd75a368e82980e7257bf500c00637',
  22         'info_dict': {
  23             'id': 'j2f2sfiiukgt',
  24             'ext': 'flv',
  25             'title': 'youtube-dl_test_video.mp4',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         orig_webpage = self._download_webpage(url, video_id)
  33
  34         m_error = re.search(
  35             r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
  36         if m_error:
  37             raise ExtractorError(m_error.group('msg'), expected=True)
  38
  39         fields = re.findall(
  40             r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
  41         data = dict(fields)
  42
  43         self._sleep(2, video_id)
  44
  45         post = compat_urllib_parse.urlencode(data)
  46         headers = {
  47             b'Content-Type': b'application/x-www-form-urlencoded',
  48         }
  49         req = compat_urllib_request.Request(url, post, headers)
  50         webpage = self._download_webpage(
  51             req, video_id, note='Downloading video page ...')
  52
  53         title = os.path.splitext(data['fname'])[0]
  54
  55         video_url = self._search_regex(
  56             r'file: "?(.+?)",', webpage, 'video URL')
  57
  58         return {
  59             'id': video_id,
  60             'title': title,
  61             'url': video_url,
  62         }