]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/liveleak.py
debian/control: Add recommends on aria2 | wget | curl to use external downloaders.
[youtubedl] / youtube_dl / extractor / liveleak.py
1 from __future__ import unicode_literals
2
3 import json
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import int_or_none
8
9
10 class LiveLeakIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
12 _TESTS = [{
13 'url': 'http://www.liveleak.com/view?i=757_1364311680',
14 'md5': '50f79e05ba149149c1b4ea961223d5b3',
15 'info_dict': {
16 'id': '757_1364311680',
17 'ext': 'flv',
18 'description': 'extremely bad day for this guy..!',
19 'uploader': 'ljfriel2',
20 'title': 'Most unlucky car accident'
21 }
22 }, {
23 'url': 'http://www.liveleak.com/view?i=f93_1390833151',
24 'md5': 'b13a29626183c9d33944e6a04f41aafc',
25 'info_dict': {
26 'id': 'f93_1390833151',
27 'ext': 'mp4',
28 'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
29 'uploader': 'ARD_Stinkt',
30 'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
31 }
32 }, {
33 'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
34 'md5': '42c6d97d54f1db107958760788c5f48f',
35 'info_dict': {
36 'id': '4f7_1392687779',
37 'ext': 'mp4',
38 'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing... I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
39 'uploader': 'CapObveus',
40 'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
41 'age_limit': 18,
42 }
43 }]
44
45 def _real_extract(self, url):
46 video_id = self._match_id(url)
47 webpage = self._download_webpage(url, video_id)
48
49 video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
50 video_description = self._og_search_description(webpage)
51 video_uploader = self._html_search_regex(
52 r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
53 age_limit = int_or_none(self._search_regex(
54 r'you confirm that you are ([0-9]+) years and over.',
55 webpage, 'age limit', default=None))
56
57 sources_raw = self._search_regex(
58 r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
59 if sources_raw is None:
60 alt_source = self._search_regex(
61 r'(file: ".*?"),', webpage, 'video URL', default=None)
62 if alt_source:
63 sources_raw = '[{ %s}]' % alt_source
64 else:
65 # Maybe an embed?
66 embed_url = self._search_regex(
67 r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
68 webpage, 'embed URL')
69 return {
70 '_type': 'url_transparent',
71 'url': embed_url,
72 'id': video_id,
73 'title': video_title,
74 'description': video_description,
75 'uploader': video_uploader,
76 'age_limit': age_limit,
77 }
78
79 sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
80 sources = json.loads(sources_json)
81
82 formats = [{
83 'format_id': '%s' % i,
84 'format_note': s.get('label'),
85 'url': s['file'],
86 } for i, s in enumerate(sources)]
87 for i, s in enumerate(sources):
88 orig_url = s['file'].replace('.h264_base.mp4', '')
89 if s['file'] != orig_url:
90 formats.append({
91 'format_id': 'original-%s' % i,
92 'format_note': s.get('label'),
93 'url': orig_url,
94 'preference': 1,
95 })
96 self._sort_formats(formats)
97
98 return {
99 'id': video_id,
100 'title': video_title,
101 'description': video_description,
102 'uploader': video_uploader,
103 'formats': formats,
104 'age_limit': age_limit,
105 }