aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/patreon.py
blob: 6f73ed68d8c68f83611943fea54416897db64429 (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    clean_html,
    determine_ext,
    int_or_none,
    parse_iso8601,
)


class PatreonIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://www.patreon.com/creation?hid=743933',
        'md5': 'e25505eec1053a6e6813b8ed369875cc',
        'info_dict': {
            'id': '743933',
            'ext': 'mp3',
            'title': 'Episode 166: David Smalley of Dogma Debate',
            'description': 'md5:713b08b772cd6271b9f3906683cfacdf',
            'uploader': 'Cognitive Dissonance Podcast',
            'thumbnail': 're:^https?://.*$',
            'timestamp': 1406473987,
            'upload_date': '20140727',
        },
    }, {
        'url': 'http://www.patreon.com/creation?hid=754133',
        'md5': '3eb09345bf44bf60451b8b0b81759d0a',
        'info_dict': {
            'id': '754133',
            'ext': 'mp3',
            'title': 'CD 167 Extra',
            'uploader': 'Cognitive Dissonance Podcast',
            'thumbnail': 're:^https?://.*$',
        },
        'skip': 'Patron-only content',
    }, {
        'url': 'https://www.patreon.com/creation?hid=1682498',
        'info_dict': {
            'id': 'SU4fj_aEMVw',
            'ext': 'mp4',
            'title': 'I\'m on Patreon!',
            'uploader': 'TraciJHines',
            'thumbnail': 're:^https?://.*$',
            'upload_date': '20150211',
            'description': 'md5:c5a706b1f687817a3de09db1eb93acd4',
            'uploader_id': 'TraciJHines',
        },
        'params': {
            'noplaylist': True,
            'skip_download': True,
        }
    }, {
        'url': 'https://www.patreon.com/posts/episode-166-of-743933',
        'only_matching': True,
    }, {
        'url': 'https://www.patreon.com/posts/743933',
        'only_matching': True,
    }]

    # Currently Patreon exposes download URL via hidden CSS, so login is not
    # needed. Keeping this commented for when this inevitably changes.
    '''
    def _login(self):
        username, password = self._get_login_info()
        if username is None:
            return

        login_form = {
            'redirectUrl': 'http://www.patreon.com/',
            'email': username,
            'password': password,
        }

        request = sanitized_Request(
            'https://www.patreon.com/processLogin',
            compat_urllib_parse_urlencode(login_form).encode('utf-8')
        )
        login_page = self._download_webpage(request, None, note='Logging in')

        if re.search(r'onLoginFailed', login_page):
            raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)

    def _real_initialize(self):
        self._login()
    '''

    def _real_extract(self, url):
        video_id = self._match_id(url)
        post = self._download_json(
            'https://www.patreon.com/api/posts/' + video_id, video_id)
        attributes = post['data']['attributes']
        title = attributes['title'].strip()
        image = attributes.get('image') or {}
        info = {
            'id': video_id,
            'title': title,
            'description': clean_html(attributes.get('content')),
            'thumbnail': image.get('large_url') or image.get('url'),
            'timestamp': parse_iso8601(attributes.get('published_at')),
            'like_count': int_or_none(attributes.get('like_count')),
            'comment_count': int_or_none(attributes.get('comment_count')),
        }

        for i in post.get('included', []):
            i_type = i.get('type')
            if i_type == 'attachment':
                attachment_attributes = i.get('attributes') or {}
                attachment_url = attachment_attributes.get('url')
                if attachment_url:
                    info.update({
                        'url': attachment_url,
                        'ext': determine_ext(attachment_attributes.get('name'), 'mp3'),
                    })
            elif i_type == 'user':
                user_attributes = i.get('attributes')
                if user_attributes:
                    info.update({
                        'uploader': user_attributes.get('full_name'),
                        'uploader_url': user_attributes.get('url'),
                    })

        if not info.get('url'):
            info.update({
                '_type': 'url',
                'url': attributes['embed']['url'],
            })

        return info