Raphaël G. Git Repositories - youtubedl/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     _TEST = {
  18         'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
  19         'md5': 'd1451b6302da7215485837aaea882c4c',
  20         'info_dict': {
  21             'id': 'D21B4746E9-F01462F0FF',
  22             'ext': 'mp4',
  23             'title': 'Birds.mp4',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
  33             raise ExtractorError('Video %s does not exist' % video_id,
  34                                  expected=True)
  35
  36         fields = dict(re.findall(r'''(?x)type="hidden"\s+
  37             name="(.+?)"\s+
  38             value="(.*?)"
  39             ''', webpage))
  40         post = compat_urllib_parse.urlencode(fields)
  41         req = compat_urllib_request.Request(url, post)
  42         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  43         webpage = self._download_webpage(
  44             req, video_id, 'Downloading video page')
  45
  46         url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
  47         title = self._html_search_regex(
  48             r'<span.+title="([^"]+)">', webpage, 'title')
  49         thumbnail = self._html_search_regex(
  50             r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
  51             webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
  52
  53         formats = [{
  54             'format_id': 'sd',
  55             'url': url,
  56             'ext': determine_ext(title),
  57         }]
  58         self._sort_formats(formats)
  59
  60         return {
  61             'id': video_id,
  62             'title': title,
  63             'thumbnail': thumbnail,
  64             'formats': formats,
  65         }