]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/theonion.py
10239c906201e460ed288386709dffc5b7f6efbc
[youtubedl] / 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
8
9 class TheOnionIE(InfoExtractor):
10 _VALID_URL = r'https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<id>[0-9]+)/?'
11 _TEST = {
12 'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/',
13 'md5': '19eaa9a39cf9b9804d982e654dc791ee',
14 'info_dict': {
15 'id': '2133',
16 'ext': 'mp4',
17 'title': 'Man Wearing M&M Jacket Apparently Made In God\'s Image',
18 'description': 'md5:cc12448686b5600baae9261d3e180910',
19 'thumbnail': 're:^https?://.*\.jpg\?\d+$',
20 }
21 }
22
23 def _real_extract(self, url):
24 display_id = self._match_id(url)
25 webpage = self._download_webpage(url, display_id)
26
27 video_id = self._search_regex(
28 r'"videoId":\s(\d+),', webpage, 'video ID')
29 title = self._og_search_title(webpage)
30 description = self._og_search_description(webpage)
31 thumbnail = self._og_search_thumbnail(webpage)
32
33 sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage)
34 formats = []
35 for src, type_ in sources:
36 if type_ == 'video/mp4':
37 formats.append({
38 'format_id': 'mp4_sd',
39 'preference': 1,
40 'url': src,
41 })
42 elif type_ == 'video/webm':
43 formats.append({
44 'format_id': 'webm_sd',
45 'preference': 0,
46 'url': src,
47 })
48 elif type_ == 'application/x-mpegURL':
49 formats.extend(
50 self._extract_m3u8_formats(src, display_id, preference=-1))
51 else:
52 self.report_warning(
53 'Encountered unexpected format: %s' % type_)
54 self._sort_formats(formats)
55
56 return {
57 'id': video_id,
58 'display_id': display_id,
59 'title': title,
60 'formats': formats,
61 'thumbnail': thumbnail,
62 'description': description,
63 }