aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/niconico.py
blob: f268a72d5690a8e96331647bdfa25994fdf51f1b (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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
# coding: utf-8
from __future__ import unicode_literals

import re
import json
import datetime

from .common import InfoExtractor
from ..compat import (
    compat_urlparse,
)
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_duration,
    parse_iso8601,
    sanitized_Request,
    xpath_text,
    determine_ext,
    urlencode_postdata,
)


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

    _TESTS = [{
        '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',
            'timestamp': 1385182762,
            'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
            'duration': 33,
        },
        'skip': 'Requires an account',
    }, {
        # File downloaded with and without credentials are different, so omit
        # the md5 field
        'url': 'http://www.nicovideo.jp/watch/nm14296458',
        'info_dict': {
            'id': 'nm14296458',
            'ext': 'swf',
            'title': '【鏡音リン】Dance on media【オリジナル】take2!',
            'description': 'md5:689f066d74610b3b22e0f1739add0f58',
            'uploader': 'りょうた',
            'uploader_id': '18822557',
            'upload_date': '20110429',
            'timestamp': 1304065916,
            'duration': 209,
        },
        'skip': 'Requires an account',
    }, {
        # 'video exists but is marked as "deleted"
        # md5 is unstable
        'url': 'http://www.nicovideo.jp/watch/sm10000',
        'info_dict': {
            'id': 'sm10000',
            'ext': 'unknown_video',
            'description': 'deleted',
            'title': 'ドラえもんエターナル第3話「決戦第3新東京市」<前編>',
            'upload_date': '20071224',
            'timestamp': int,  # timestamp field has different value if logged in
            'duration': 304,
        },
        'skip': 'Requires an account',
    }, {
        'url': 'http://www.nicovideo.jp/watch/so22543406',
        'info_dict': {
            'id': '1388129933',
            'ext': 'mp4',
            'title': '【第1回】RADIOアニメロミックス ラブライブ!~のぞえりRadio Garden~',
            'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
            'timestamp': 1388851200,
            'upload_date': '20140104',
            'uploader': 'アニメロチャンネル',
            'uploader_id': '312',
        },
        'skip': 'The viewing period of the video you were searching for has expired.',
    }, {
        'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
        'only_matching': True,
    }]

    _VALID_URL = r'https?://(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
    _NETRC_MACHINE = 'niconico'

    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,
        }
        login_data = urlencode_postdata(login_form_strs)
        request = sanitized_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
        return True

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

        # Get video webpage. We are not actually interested in it for normal
        # cases, but need the cookies in order to be able to download the
        # info webpage
        webpage, handle = self._download_webpage_handle(
            'http://www.nicovideo.jp/watch/' + video_id, video_id)
        if video_id.startswith('so'):
            video_id = self._match_id(handle.geturl())

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

        # Get flv info
        flv_info_webpage = self._download_webpage(
            'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
            video_id, 'Downloading flv info')

        flv_info = compat_urlparse.parse_qs(flv_info_webpage)
        if 'url' not in flv_info:
            if 'deleted' in flv_info:
                raise ExtractorError('The video has been deleted.',
                                     expected=True)
            elif 'closed' in flv_info:
                raise ExtractorError('Niconico videos now require logging in',
                                     expected=True)
            else:
                raise ExtractorError('Unable to find video URL')

        video_real_url = flv_info['url'][0]

        # Start extracting information
        title = xpath_text(video_info, './/title')
        if not title:
            title = self._og_search_title(webpage, default=None)
        if not title:
            title = self._html_search_regex(
                r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
                webpage, 'video title')

        watch_api_data_string = self._html_search_regex(
            r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
            webpage, 'watch api data', default=None)
        watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {}
        video_detail = watch_api_data.get('videoDetail', {})

        extension = xpath_text(video_info, './/movie_type')
        if not extension:
            extension = determine_ext(video_real_url)

        thumbnail = (
            xpath_text(video_info, './/thumbnail_url') or
            self._html_search_meta('image', webpage, 'thumbnail', default=None) or
            video_detail.get('thumbnail'))

        description = xpath_text(video_info, './/description')

        timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
        if not timestamp:
            match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
            if match:
                timestamp = parse_iso8601(match.replace('+', ':00+'))
        if not timestamp and video_detail.get('postedAt'):
            timestamp = parse_iso8601(
                video_detail['postedAt'].replace('/', '-'),
                delimiter=' ', timezone=datetime.timedelta(hours=9))

        view_count = int_or_none(xpath_text(video_info, './/view_counter'))
        if not view_count:
            match = self._html_search_regex(
                r'>Views: <strong[^>]*>([^<]+)</strong>',
                webpage, 'view count', default=None)
            if match:
                view_count = int_or_none(match.replace(',', ''))
        view_count = view_count or video_detail.get('viewCount')

        comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
        if not comment_count:
            match = self._html_search_regex(
                r'>Comments: <strong[^>]*>([^<]+)</strong>',
                webpage, 'comment count', default=None)
            if match:
                comment_count = int_or_none(match.replace(',', ''))
        comment_count = comment_count or video_detail.get('commentCount')

        duration = (parse_duration(
            xpath_text(video_info, './/length') or
            self._html_search_meta(
                'video:duration', webpage, 'video duration', default=None)) or
            video_detail.get('length'))

        webpage_url = xpath_text(video_info, './/watch_url') or url

        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_id': 'economy' if video_real_url.endswith('low') else 'normal',
            'thumbnail': thumbnail,
            'description': description,
            'uploader': uploader,
            'timestamp': timestamp,
            '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,
        }