_ Git - youtube-dl/blob - youtube_dl/extractor/promptfile.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     determine_ext,
  10     compat_urllib_parse,
  11     compat_urllib_request,
  12 )
  13
  14
  15 class PromptFileIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
  17     _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
  18     _TEST = {
  19         'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
  20         'md5': 'd1451b6302da7215485837aaea882c4c',
  21         'info_dict': {
  22             'id': 'D21B4746E9-F01462F0FF',
  23             'ext': 'mp4',
  24             'title': 'Birds.mp4',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         webpage = self._download_webpage(url, video_id)
  33
  34         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
  35             raise ExtractorError('Video %s does not exist' % video_id,
  36                                  expected=True)
  37
  38         fields = dict(re.findall(r'''(?x)type="hidden"\s+
  39             name="(.+?)"\s+
  40             value="(.*?)"
  41             ''', webpage))
  42         post = compat_urllib_parse.urlencode(fields)
  43         req = compat_urllib_request.Request(url, post)
  44         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  45         webpage = self._download_webpage(
  46             req, video_id, 'Downloading video page')
  47
  48         url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
  49         title = self._html_search_regex(
  50             r'<span.+title="([^"]+)">', webpage, 'title')
  51         thumbnail = self._html_search_regex(
  52             r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
  53             webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
  54
  55         formats = [{
  56             'format_id': 'sd',
  57             'url': url,
  58             'ext': determine_ext(title),
  59         }]
  60         self._sort_formats(formats)
  61
  62         return {
  63             'id': video_id,
  64             'title': title,
  65             'thumbnail': thumbnail,
  66             'formats': formats,
  67         }