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     urlencode_postdata,
  11 )
  12
  13
  14 class PromptFileIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
  16     _TEST = {
  17         'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416',
  18         'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
  19         'info_dict': {
  20             'id': '86D1CE8462-576CAAE416',
  21             'ext': 'mp4',
  22             'title': 'oceans.mp4',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
  32             raise ExtractorError('Video %s does not exist' % video_id,
  33                                  expected=True)
  34
  35         chash = self._search_regex(
  36             r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash')
  37         fields = self._hidden_inputs(webpage)
  38         keys = list(fields.keys())
  39         chash_key = keys[0] if len(keys) == 1 else next(
  40             key for key in keys if key.startswith('cha'))
  41         fields[chash_key] = chash + fields[chash_key]
  42
  43         webpage = self._download_webpage(
  44             url, video_id, 'Downloading video page',
  45             data=urlencode_postdata(fields),
  46             headers={'Content-type': 'application/x-www-form-urlencoded'})
  47
  48         video_url = self._search_regex(
  49             (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File',
  50              r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'),
  51             webpage, 'video url', group='url')
  52         title = self._html_search_regex(
  53             r'<span.+title="([^"]+)">', webpage, 'title')
  54         thumbnail = self._html_search_regex(
  55             r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
  56             webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
  57
  58         formats = [{
  59             'format_id': 'sd',
  60             'url': video_url,
  61             'ext': determine_ext(title),
  62         }]
  63         self._sort_formats(formats)
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'thumbnail': thumbnail,
  69             'formats': formats,
  70         }