yt_dlp/extractor/piapro.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     clean_html,
   7     get_element_by_class,
   8     parse_duration,
   9     parse_filesize,
  10     str_to_int,
  11     unified_timestamp,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class PiaproIE(InfoExtractor):
  17     _NETRC_MACHINE = 'piapro'
  18     _VALID_URL = r'https?://piapro\.jp/(?:t|content)/(?P<id>[\w-]+)/?'
  19     _TESTS = [{
  20         'url': 'https://piapro.jp/t/NXYR',
  21         'md5': 'f7c0f760913fb1d44a1c45a4af793909',
  22         'info_dict': {
  23             'id': 'NXYR',
  24             'ext': 'mp3',
  25             'uploader': 'wowaka',
  26             'uploader_id': 'wowaka',
  27             'title': '裏表ラバーズ',
  28             'description': 'http://www.nicovideo.jp/watch/sm8082467',
  29             'duration': 189.0,
  30             'timestamp': 1251785475,
  31             'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
  32             'upload_date': '20090901',
  33             'view_count': int,
  34         },
  35     }, {
  36         'note': 'There are break lines in description, mandating (?s) flag',
  37         'url': 'https://piapro.jp/t/9cSd',
  38         'md5': '952bb6d1e8de95050206408a87790676',
  39         'info_dict': {
  40             'id': '9cSd',
  41             'ext': 'mp3',
  42             'title': '青に溶けた風船 / 初音ミク',
  43             'description': 'md5:d395a9bd151447631a5a1460bc7f9132',
  44             'uploader': 'シアン・キノ',
  45             'duration': 229.0,
  46             'timestamp': 1644030039,
  47             'upload_date': '20220205',
  48             'view_count': int,
  49             'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
  50             'uploader_id': 'cyankino',
  51         },
  52     }, {
  53         'url': 'https://piapro.jp/content/hcw0z3a169wtemz6',
  54         'only_matching': True,
  55     }, {
  56         'url': 'https://piapro.jp/t/-SO-',
  57         'only_matching': True,
  58     }]
  59
  60     _login_status = False
  61
  62     def _perform_login(self, username, password):
  63         login_ok = True
  64         login_form_strs = {
  65             '_username': username,
  66             '_password': password,
  67             '_remember_me': 'on',
  68             'login': 'ログイン',
  69         }
  70         self._request_webpage('https://piapro.jp/login/', None)
  71         urlh = self._request_webpage(
  72             'https://piapro.jp/login/exe', None,
  73             note='Logging in', errnote='Unable to log in',
  74             data=urlencode_postdata(login_form_strs))
  75         if urlh is False:
  76             login_ok = False
  77         else:
  78             parts = urllib.parse.urlparse(urlh.url)
  79             if parts.path != '/':
  80                 login_ok = False
  81         if not login_ok:
  82             self.report_warning(
  83                 'unable to log in: bad username or password')
  84         self._login_status = login_ok
  85
  86     def _real_extract(self, url):
  87         video_id = self._match_id(url)
  88         webpage = self._download_webpage(url, video_id)
  89
  90         category_id = self._search_regex(r'categoryId=(.+)">', webpage, 'category ID')
  91         if category_id not in ('1', '2', '21', '22', '23', '24', '25'):
  92             raise ExtractorError('The URL does not contain audio.', expected=True)
  93
  94         def extract_info(name, description):
  95             return self._search_regex(rf'{name}[：:]\s*([\d\s,:/]+)\s*</p>', webpage, description, default=None)
  96
  97         return {
  98             'id': video_id,
  99             'title': clean_html(get_element_by_class('contents_title', webpage)),
 100             'description': clean_html(get_element_by_class('contents_description', webpage)),
 101             'uploader': clean_html(get_element_by_class('contents_creator_txt', webpage)),
 102             'uploader_id': self._search_regex(
 103                 r'<a\s+href="/([^"]+)"', get_element_by_class('contents_creator', webpage), 'uploader id', default=None),
 104             'timestamp': unified_timestamp(extract_info('投稿日', 'timestamp'), False),
 105             'duration': parse_duration(extract_info('長さ', 'duration')),
 106             'view_count': str_to_int(extract_info('閲覧数', 'view count')),
 107             'thumbnail': self._html_search_meta('twitter:image', webpage),
 108             'filesize_approx': parse_filesize((extract_info('サイズ', 'size') or '').replace(',', '')),
 109             'url': self._search_regex(r'\"url\":\s*\"(.*?)\"', webpage, 'url'),
 110             'ext': 'mp3',
 111             'vcodec': 'none',
 112         }