aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/niconico.py
blob: a48df7f6218be27bd3a083f00da4ec8efb3d9309 (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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
# encoding: utf-8
from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_request,
    compat_urlparse,
)
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_duration,
    unified_strdate,
)


class NiconicoIE(InfoExtractor):
    IE_NAME = 'niconico'
    IE_DESC = 'ニコニコ動画'

    _TEST = {
        'url': 'http://www.nicovideo.jp/watch/sm22312215',
        'md5': 'd1a75c0823e2f629128c43e1212760f9',
        'info_dict': {
            'id': 'sm22312215',
            'ext': 'mp4',
            'title': 'Big Buck Bunny',
            'uploader': 'takuya0301',
            'uploader_id': '2698420',
            'upload_date': '20131123',
            'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
            'duration': 33,
        },
        'params': {
            'username': 'ydl.niconico@gmail.com',
            'password': 'youtube-dl',
        },
    }

    _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
    _NETRC_MACHINE = 'niconico'
    # Determine whether the downloader used authentication to download video
    _AUTHENTICATED = False

    def _real_initialize(self):
        self._login()

    def _login(self):
        (username, password) = self._get_login_info()
        # No authentication to be performed
        if not username:
            return True

        # Log in
        login_form_strs = {
            'mail': username,
            'password': password,
        }
        # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
        # chokes on unicode
        login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
        login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
        request = compat_urllib_request.Request(
            'https://secure.nicovideo.jp/secure/login', login_data)
        login_results = self._download_webpage(
            request, None, note='Logging in', errnote='Unable to log in')
        if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
            self._downloader.report_warning('unable to log in: bad username or password')
            return False
        # Successful login
        self._AUTHENTICATED = True
        return True

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

        # Get video webpage. We are not actually interested in it, but need
        # the cookies in order to be able to download the info webpage
        self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)

        video_info = self._download_xml(
            'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
            note='Downloading video info page')

        if self._AUTHENTICATED:
            # Get flv info
            flv_info_webpage = self._download_webpage(
                'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
                video_id, 'Downloading flv info')
        else:
            # Get external player info
            ext_player_info = self._download_webpage(
                'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
            thumb_play_key = self._search_regex(
                r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
            # Get flv info
            flv_info_data = compat_urllib_parse.urlencode({
                'k': thumb_play_key,
                'v': video_id
            })
            flv_info_request = compat_urllib_request.Request(
                'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
                {'Content-Type': 'application/x-www-form-urlencoded'})
            flv_info_webpage = self._download_webpage(
                flv_info_request, video_id,
                note='Downloading flv info', errnote='Unable to download flv info')

        if 'deleted=' in flv_info_webpage:
            raise ExtractorError('The video has been deleted.',
                                 expected=True)
        video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]

        # Start extracting information
        title = video_info.find('.//title').text
        extension = video_info.find('.//movie_type').text
        video_format = extension.upper()
        thumbnail = video_info.find('.//thumbnail_url').text
        description = video_info.find('.//description').text
        upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
        view_count = int_or_none(video_info.find('.//view_counter').text)
        comment_count = int_or_none(video_info.find('.//comment_num').text)
        duration = parse_duration(video_info.find('.//length').text)
        webpage_url = video_info.find('.//watch_url').text

        if video_info.find('.//ch_id') is not None:
            uploader_id = video_info.find('.//ch_id').text
            uploader = video_info.find('.//ch_name').text
        elif video_info.find('.//user_id') is not None:
            uploader_id = video_info.find('.//user_id').text
            uploader = video_info.find('.//user_nickname').text
        else:
            uploader_id = uploader = None

        return {
            'id': video_id,
            'url': video_real_url,
            'title': title,
            'ext': extension,
            'format': video_format,
            'thumbnail': thumbnail,
            'description': description,
            'uploader': uploader,
            'upload_date': upload_date,
            'uploader_id': uploader_id,
            'view_count': view_count,
            'comment_count': comment_count,
            'duration': duration,
            'webpage_url': webpage_url,
        }


class NiconicoPlaylistIE(InfoExtractor):
    _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'

    _TEST = {
        'url': 'http://www.nicovideo.jp/mylist/27411728',
        'info_dict': {
            'id': '27411728',
            'title': 'AKB48のオールナイトニッポン',
        },
        'playlist_mincount': 225,
    }

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

        entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
                                          webpage, 'entries')
        entries = json.loads(entries_json)
        entries = [{
            '_type': 'url',
            'ie_key': NiconicoIE.ie_key(),
            'url': ('http://www.nicovideo.jp/watch/%s' %
                    entry['item_data']['video_id']),
        } for entry in entries]

        return {
            '_type': 'playlist',
            'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
            'id': list_id,
            'entries': entries,
        }