aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bloomberg.py
blob: 4a88ccd13caf604f3ea892c6784d603434fb06ee (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor


class BloombergIE(InfoExtractor):
    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<id>.+?)\.html'

    _TEST = {
        'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
        # The md5 checksum changes
        'info_dict': {
            'id': 'qurhIVlJSB6hzkVi229d8g',
            'ext': 'flv',
            'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
            'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
        },
    }

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

        f4m_url = self._search_regex(
            r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
            'f4m url')
        title = re.sub(': Video$', '', self._og_search_title(webpage))

        return {
            'id': name.split('-')[-1],
            'title': title,
            'formats': self._extract_f4m_formats(f4m_url, name),
            'description': self._og_search_description(webpage),
            'thumbnail': self._og_search_thumbnail(webpage),
        }