aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/democracynow.py
blob: 824b8e2c5c6251960f26fdb049f9d033c9f00a45 (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
# coding: utf-8
from __future__ import unicode_literals

import re
import os.path

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    url_basename,
    remove_start,
)


class DemocracynowIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
    IE_NAME = 'democracynow'
    _TESTS = [{
        'url': 'http://www.democracynow.org/shows/2015/7/3',
        'info_dict': {
            'id': '2015-0703-001',
            'ext': 'mp4',
            'title': 'July 03, 2015 - Democracy Now!',
            'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
        },
    }, {
        'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
        'info_dict': {
            'id': '2015-0703-001',
            'ext': 'mp4',
            'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
            'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
        },
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)
        description = self._og_search_description(webpage)

        js = self._parse_json(self._search_regex(
            r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
            display_id)
        video_id = None
        formats = []

        default_lang = 'en'

        subtitles = {}

        def add_subtitle_item(lang, info_dict):
            if lang not in subtitles:
                subtitles[lang] = []
            subtitles[lang].append(info_dict)

        # chapter_file are not subtitles
        if 'caption_file' in js:
            add_subtitle_item(default_lang, {
                'url': compat_urlparse.urljoin(url, js['caption_file']),
            })

        for subtitle_item in js.get('captions', []):
            lang = subtitle_item.get('language', '').lower() or default_lang
            add_subtitle_item(lang, {
                'url': compat_urlparse.urljoin(url, subtitle_item['url']),
            })

        for key in ('file', 'audio', 'video'):
            media_url = js.get(key, '')
            if not media_url:
                continue
            media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
            video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
            formats.append({
                'url': media_url,
            })

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': js.get('title'),
            'description': description,
            'subtitles': subtitles,
            'formats': formats,
        }