aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/condenast.py
blob: 6f92ae2ed0cd1383f66d21b3a9274be151ca32b2 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_parse_urlparse,
    compat_urlparse,
)
from ..utils import (
    orderedSet,
    remove_end,
)


class CondeNastIE(InfoExtractor):
    """
    Condé Nast is a media group, some of its sites use a custom HTML5 player
    that works the same in all of them.
    """

    # The keys are the supported sites and the values are the name to be shown
    # to the user and in the extractor description.
    _SITES = {
        'allure': 'Allure',
        'architecturaldigest': 'Architectural Digest',
        'arstechnica': 'Ars Technica',
        'bonappetit': 'Bon Appétit',
        'brides': 'Brides',
        'cnevids': 'Condé Nast',
        'cntraveler': 'Condé Nast Traveler',
        'details': 'Details',
        'epicurious': 'Epicurious',
        'glamour': 'Glamour',
        'golfdigest': 'Golf Digest',
        'gq': 'GQ',
        'newyorker': 'The New Yorker',
        'self': 'SELF',
        'teenvogue': 'Teen Vogue',
        'vanityfair': 'Vanity Fair',
        'vogue': 'Vogue',
        'wired': 'WIRED',
        'wmagazine': 'W Magazine',
    }

    _VALID_URL = r'http://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
    IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))

    EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed(?:js)?)/.+?' % '|'.join(_SITES.keys())

    _TESTS = [{
        'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
        'md5': '1921f713ed48aabd715691f774c451f7',
        'info_dict': {
            'id': '5171b343c2b4c00dd0c1ccb3',
            'ext': 'mp4',
            'title': '3D Printed Speakers Lit With LED',
            'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
        }
    }, {
        # JS embed
        'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js',
        'md5': 'f1a6f9cafb7083bab74a710f65d08999',
        'info_dict': {
            'id': '55f9cf8b61646d1acf00000c',
            'ext': 'mp4',
            'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
        }
    }]

    def _extract_series(self, url, webpage):
        title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
                                        webpage, 'series title', flags=re.DOTALL)
        url_object = compat_urllib_parse_urlparse(url)
        base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
        m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
                              webpage, flags=re.DOTALL)
        paths = orderedSet(m.group(1) for m in m_paths)
        build_url = lambda path: compat_urlparse.urljoin(base_url, path)
        entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
        return self.playlist_result(entries, playlist_title=title)

    def _extract_video(self, webpage, url_type):
        if url_type != 'embed':
            description = self._html_search_regex(
                [
                    r'<div class="cne-video-description">(.+?)</div>',
                    r'<div class="video-post-content">(.+?)</div>',
                ],
                webpage, 'description', fatal=False, flags=re.DOTALL)
        else:
            description = None
        params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
                                    'player params', flags=re.DOTALL)
        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
        data = compat_urllib_parse.urlencode({'videoId': video_id,
                                              'playerId': player_id,
                                              'target': target,
                                              })
        base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
                                           webpage, 'base info url',
                                           default='http://player.cnevids.com/player/loader.js?')
        info_url = base_info_url + data
        info_page = self._download_webpage(info_url, video_id,
                                           'Downloading video info')
        video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info')
        video_info = self._parse_json(video_info, video_id)

        formats = [{
            'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
            'url': fdata['src'],
            'ext': fdata['type'].split('/')[-1],
            'quality': 1 if fdata['quality'] == 'high' else 0,
        } for fdata in video_info['sources'][0]]
        self._sort_formats(formats)

        return {
            'id': video_id,
            'formats': formats,
            'title': video_info['title'],
            'thumbnail': video_info['poster_frame'],
            'description': description,
        }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        site = mobj.group('site')
        url_type = mobj.group('type')
        item_id = mobj.group('id')

        # Convert JS embed to regular embed
        if url_type == 'embedjs':
            parsed_url = compat_urlparse.urlparse(url)
            url = compat_urlparse.urlunparse(parsed_url._replace(
                path=remove_end(parsed_url.path, '.js').replace('/embedjs/', '/embed/')))
            url_type = 'embed'

        self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site])
        webpage = self._download_webpage(url, item_id)

        if url_type == 'series':
            return self._extract_series(url, webpage)
        else:
            return self._extract_video(webpage, url_type)