aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/liveleak.py
blob: a571fa742e32433c3a5ba0591958d4d87237d0c7 (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
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
)


class LiveLeakIE(InfoExtractor):
    _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
    _TEST = {
        'url': 'http://www.liveleak.com/view?i=757_1364311680',
        'file': '757_1364311680.mp4',
        'md5': '0813c2430bea7a46bf13acf3406992f4',
        'info_dict': {
            'description': 'extremely bad day for this guy..!',
            'uploader': 'ljfriel2',
            'title': 'Most unlucky car accident'
        }
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)

        video_id = mobj.group('video_id')
        webpage = self._download_webpage(url, video_id)
        sources_raw = self._search_regex(
            r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs')
        sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
        sources = json.loads(sources_json)

        formats = [{
            'format_note': s.get('label'),
            'url': s['file'],
        } for s in sources]
        self._sort_formats(formats)

        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)

        return {
            'id': video_id,
            'title': video_title,
            'description': video_description,
            'uploader': video_uploader,
            'formats': formats,
        }