Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/theonion.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 ExtractorError
   8
   9
  10 class TheOnionIE(InfoExtractor):
  11     _VALID_URL = r'(?x)https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<article_id>[0-9]+)/?'
  12     _TEST = {
  13         'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/',
  14         'md5': '19eaa9a39cf9b9804d982e654dc791ee',
  15         'info_dict': {
  16             'id': '2133',
  17             'ext': 'mp4',
  18             'title': 'Man Wearing M&M Jacket Apparently Made In God\'s Image',
  19             'description': 'md5:cc12448686b5600baae9261d3e180910',
  20             'thumbnail': 're:^https?://.*\.jpg\?\d+$',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         article_id = mobj.group('article_id')
  27
  28         webpage = self._download_webpage(url, article_id)
  29
  30         video_id = self._search_regex(
  31             r'"videoId":\s(\d+),', webpage, 'video ID')
  32         title = self._og_search_title(webpage)
  33         description = self._og_search_description(webpage)
  34         thumbnail = self._og_search_thumbnail(webpage)
  35
  36         sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage)
  37         if not sources:
  38             raise ExtractorError(
  39                 'No sources found for video %s' % video_id, expected=True)
  40
  41         formats = []
  42         for src, type_ in sources:
  43             if type_ == 'video/mp4':
  44                 formats.append({
  45                     'format_id': 'mp4_sd',
  46                     'preference': 1,
  47                     'url': src,
  48                 })
  49             elif type_ == 'video/webm':
  50                 formats.append({
  51                     'format_id': 'webm_sd',
  52                     'preference': 0,
  53                     'url': src,
  54                 })
  55             elif type_ == 'application/x-mpegURL':
  56                 formats.extend(
  57                     self._extract_m3u8_formats(src, video_id, preference=-1))
  58             else:
  59                 self.report_warning(
  60                     'Encountered unexpected format: %s' % type_)
  61
  62         self._sort_formats(formats)
  63
  64         return {
  65             'id': video_id,
  66             'title': title,
  67             'formats': formats,
  68             'thumbnail': thumbnail,
  69             'description': description,
  70         }