summaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/bambuser.py
blob: 34f1b3d83614d97aaf3a07794a5672768a0939ef (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
from __future__ import unicode_literals

import re
import itertools

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    float_or_none,
    int_or_none,
    sanitized_Request,
    urlencode_postdata,
)


class BambuserIE(InfoExtractor):
    IE_NAME = 'bambuser'
    _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
    _API_KEY = '005f64509e19a868399060af746a00aa'
    _LOGIN_URL = 'https://bambuser.com/user'
    _NETRC_MACHINE = 'bambuser'

    _TEST = {
        'url': 'http://bambuser.com/v/4050584',
        # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
        # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
        'info_dict': {
            'id': '4050584',
            'ext': 'flv',
            'title': 'Education engineering days - lightning talks',
            'duration': 3741,
            'uploader': 'pixelversity',
            'uploader_id': '344706',
            'timestamp': 1382976692,
            'upload_date': '20131028',
            'view_count': int,
        },
        'params': {
            # It doesn't respect the 'Range' header, it would download the whole video
            # caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59
            'skip_download': True,
        },
    }

    def _login(self):
        username, password = self._get_login_info()
        if username is None:
            return

        login_form = {
            'form_id': 'user_login',
            'op': 'Log in',
            'name': username,
            'pass': password,
        }

        request = sanitized_Request(
            self._LOGIN_URL, urlencode_postdata(login_form))
        request.add_header('Referer', self._LOGIN_URL)
        response = self._download_webpage(
            request, None, 'Logging in')

        login_error = self._html_search_regex(
            r'(?s)<div class="messages error">(.+?)</div>',
            response, 'login error', default=None)
        if login_error:
            raise ExtractorError(
                'Unable to login: %s' % login_error, expected=True)

    def _real_initialize(self):
        self._login()

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

        info = self._download_json(
            'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s'
            % (self._API_KEY, video_id), video_id)

        error = info.get('error')
        if error:
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, error), expected=True)

        result = info['result']

        return {
            'id': video_id,
            'title': result['title'],
            'url': result['url'],
            'thumbnail': result.get('preview'),
            'duration': int_or_none(result.get('length')),
            'uploader': result.get('username'),
            'uploader_id': compat_str(result.get('owner', {}).get('uid')),
            'timestamp': int_or_none(result.get('created')),
            'fps': float_or_none(result.get('framerate')),
            'view_count': int_or_none(result.get('views_total')),
            'comment_count': int_or_none(result.get('comment_count')),
        }


class BambuserChannelIE(InfoExtractor):
    IE_NAME = 'bambuser:channel'
    _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
    # The maximum number we can get with each request
    _STEP = 50
    _TEST = {
        'url': 'http://bambuser.com/channel/pixelversity',
        'info_dict': {
            'title': 'pixelversity',
        },
        'playlist_mincount': 60,
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user = mobj.group('user')
        urls = []
        last_id = ''
        for i in itertools.count(1):
            req_url = (
                'http://bambuser.com/xhr-api/index.php?username={user}'
                '&sort=created&access_mode=0%2C1%2C2&limit={count}'
                '&method=broadcast&format=json&vid_older_than={last}'
            ).format(user=user, count=self._STEP, last=last_id)
            req = sanitized_Request(req_url)
            # Without setting this header, we wouldn't get any result
            req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
            data = self._download_json(
                req, user, 'Downloading page %d' % i)
            results = data['result']
            if not results:
                break
            last_id = results[-1]['vid']
            urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)

        return {
            '_type': 'playlist',
            'title': user,
            'entries': urls,
        }