aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/liveleak.py
blob: 246aac576a2c6b275ed38ef614eb7a569b9e2ffb (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import int_or_none


class LiveLeakIE(InfoExtractor):
    _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
    _TESTS = [{
        'url': 'http://www.liveleak.com/view?i=757_1364311680',
        'md5': '0813c2430bea7a46bf13acf3406992f4',
        'info_dict': {
            'id': '757_1364311680',
            'ext': 'mp4',
            'description': 'extremely bad day for this guy..!',
            'uploader': 'ljfriel2',
            'title': 'Most unlucky car accident',
            'thumbnail': r're:^https?://.*\.jpg$'
        }
    }, {
        'url': 'http://www.liveleak.com/view?i=f93_1390833151',
        'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
        'info_dict': {
            'id': 'f93_1390833151',
            'ext': 'mp4',
            'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
            'uploader': 'ARD_Stinkt',
            'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
            'thumbnail': r're:^https?://.*\.jpg$'
        }
    }, {
        # Prochan embed
        'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
        'md5': '42c6d97d54f1db107958760788c5f48f',
        'info_dict': {
            'id': '4f7_1392687779',
            'ext': 'mp4',
            '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.",
            'uploader': 'CapObveus',
            'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
            'age_limit': 18,
        },
        'skip': 'Video is dead',
    }, {
        # Covers https://github.com/rg3/youtube-dl/pull/5983
        # Multiple resolutions
        'url': 'http://www.liveleak.com/view?i=801_1409392012',
        'md5': 'c3a449dbaca5c0d1825caecd52a57d7b',
        'info_dict': {
            'id': '801_1409392012',
            'ext': 'mp4',
            'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.',
            'uploader': 'bony333',
            'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
            'thumbnail': r're:^https?://.*\.jpg$'
        }
    }, {
        # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521
        'url': 'http://m.liveleak.com/view?i=763_1473349649',
        'add_ie': ['Youtube'],
        'info_dict': {
            'id': '763_1473349649',
            'ext': 'mp4',
            'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty',
            'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.',
            'uploader': 'Ziz',
            'upload_date': '20160908',
            'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw'
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://www.liveleak.com/view?i=677_1439397581',
        'info_dict': {
            'id': '677_1439397581',
            'title': 'Fuel Depot in China Explosion caught on video',
        },
        'playlist_count': 3,
    }]

    @staticmethod
    def _extract_urls(webpage):
        return re.findall(
            r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"',
            webpage)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
        video_description = self._og_search_description(webpage)
        video_uploader = self._html_search_regex(
            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
        age_limit = int_or_none(self._search_regex(
            r'you confirm that you are ([0-9]+) years and over.',
            webpage, 'age limit', default=None))
        video_thumbnail = self._og_search_thumbnail(webpage)

        entries = self._parse_html5_media_entries(url, webpage, video_id)
        if not entries:
            # Maybe an embed?
            embed_url = self._search_regex(
                r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
                webpage, 'embed URL')
            return {
                '_type': 'url_transparent',
                'url': embed_url,
                'id': video_id,
                'title': video_title,
                'description': video_description,
                'uploader': video_uploader,
                'age_limit': age_limit,
            }

        for idx, info_dict in enumerate(entries):
            for a_format in info_dict['formats']:
                if not a_format.get('height'):
                    a_format['height'] = int_or_none(self._search_regex(
                        r'([0-9]+)p\.mp4', a_format['url'], 'height label',
                        default=None))

            self._sort_formats(info_dict['formats'])

            # Don't append entry ID for one-video pages to keep backward compatibility
            if len(entries) > 1:
                info_dict['id'] = '%s_%s' % (video_id, idx + 1)
            else:
                info_dict['id'] = video_id

            info_dict.update({
                'title': video_title,
                'description': video_description,
                'uploader': video_uploader,
                'age_limit': age_limit,
                'thumbnail': video_thumbnail,
            })

        return self.playlist_result(entries, video_id, video_title)


class LiveLeakEmbedIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)'

    # See generic.py for actual test cases
    _TESTS = [{
        'url': 'https://www.liveleak.com/ll_embed?i=874_1459135191',
        'only_matching': True,
    }, {
        'url': 'https://www.liveleak.com/ll_embed?f=ab065df993c1',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        kind, video_id = mobj.group('kind', 'id')

        if kind == 'f':
            webpage = self._download_webpage(url, video_id)
            liveleak_url = self._search_regex(
                r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
                webpage, 'LiveLeak URL', group='url')
        elif kind == 'i':
            liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id

        return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())