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     determine_ext,
   9     ExtractorError,
  10     sanitized_Request,
  11     urlencode_postdata,
  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/86D1CE8462-576CAAE416',
  19         'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
  20         'info_dict': {
  21             'id': '86D1CE8462-576CAAE416',
  22             'ext': 'mp4',
  23             'title': 'oceans.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         chash_pattern = r'\$\("#chash"\)\.val\("(.+)"\+\$\("#chash"\)'
  37         chash = self._html_search_regex(chash_pattern, webpage, "chash")
  38         fields = self._hidden_inputs(webpage)
  39         k = list(fields)[0]
  40         fields[k] = chash + fields[k]
  41
  42         post = urlencode_postdata(fields)
  43         req = sanitized_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_pattern = r'<a href="(http://www\.promptfile\.com/file/[^"]+)'
  49         url = self._html_search_regex(url_pattern, webpage, 'URL')
  50         title = self._html_search_regex(
  51             r'<span.+title="([^"]+)">', webpage, 'title')
  52         thumbnail = self._html_search_regex(
  53             r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
  54             webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
  55
  56         formats = [{
  57             'format_id': 'sd',
  58             'url': url,
  59             'ext': determine_ext(title),
  60         }]
  61         self._sort_formats(formats)
  62
  63         return {
  64             'id': video_id,
  65             'title': title,
  66             'thumbnail': thumbnail,
  67             'formats': formats,
  68         }