aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/escapist.py
blob: b45c1dbd07650d9717408591c7b20077bf62475e (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
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
)
from ..utils import (
    ExtractorError,
    js_to_json,
)


class EscapistIE(InfoExtractor):
    _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
    _TEST = {
        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
        'info_dict': {
            'id': '6618',
            'ext': 'mp4',
            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
            'uploader_id': 'the-escapist-presents',
            'uploader': 'The Escapist Presents',
            'title': "Breaking Down Baldur's Gate",
            'thumbnail': 're:^https?://.*\.jpg$',
        }
    }

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

        uploader_id = self._html_search_regex(
            r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
            webpage, 'uploader ID', fatal=False)
        uploader = self._html_search_regex(
            r"<h1\s+class='headline'>(.*?)</a>",
            webpage, 'uploader', fatal=False)
        description = self._html_search_meta('description', webpage)

        raw_title = self._html_search_meta('title', webpage, fatal=True)
        title = raw_title.partition(' : ')[2]

        config_url = compat_urllib_parse.unquote(self._html_search_regex(
            r'''(?x)
            (?:
                <param\s+name="flashvars".*?\s+value="config=|
                flashvars=&quot;config=
            )
            (https?://[^"&]+)
            ''',
            webpage, 'config URL'))

        formats = []
        ad_formats = []

        def _add_format(name, cfgurl, quality):
            config = self._download_json(
                cfgurl, video_id,
                'Downloading ' + name + ' configuration',
                'Unable to download ' + name + ' configuration',
                transform_source=js_to_json)

            playlist = config['playlist']
            for p in playlist:
                if p.get('eventCategory') == 'Video':
                    ar = formats
                elif p.get('eventCategory') == 'Video Postroll':
                    ar = ad_formats
                else:
                    continue

                ar.append({
                    'url': p['url'],
                    'format_id': name,
                    'quality': quality,
                })

        _add_format('normal', config_url, quality=0)
        hq_url = (config_url +
                  ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
        try:
            _add_format('hq', hq_url, quality=1)
        except ExtractorError:
            pass  # That's fine, we'll just use normal quality
        self._sort_formats(formats)

        res = {
            'id': video_id,
            'formats': formats,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'title': title,
            'thumbnail': self._og_search_thumbnail(webpage),
            'description': description,
        }

        if self._downloader.params.get('include_ads') and ad_formats:
            self._sort_formats(ad_formats)
            ad_res = {
                'id': '%s-ad' % video_id,
                'title': '%s (Postroll)' % title,
                'formats': ad_formats,
            }
            return {
                '_type': 'playlist',
                'entries': [res, ad_res],
                'title': title,
                'id': video_id,
            }

        return res