yt_dlp/extractor/piapro.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_urlparse
   3 from ..utils import (
   4     ExtractorError,
   5     parse_duration,
   6     parse_filesize,
   7     str_to_int,
   8     unified_timestamp,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class PiaproIE(InfoExtractor):
  14     _NETRC_MACHINE = 'piapro'
  15     _VALID_URL = r'https?://piapro\.jp/t/(?P<id>\w+)/?'
  16     _TESTS = [{
  17         'url': 'https://piapro.jp/t/NXYR',
  18         'md5': 'a9d52f27d13bafab7ee34116a7dcfa77',
  19         'info_dict': {
  20             'id': 'NXYR',
  21             'ext': 'mp3',
  22             'uploader': 'wowaka',
  23             'uploader_id': 'wowaka',
  24             'title': '裏表ラバーズ',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26         }
  27     }, {
  28         'note': 'There are break lines in description, mandating (?s) flag',
  29         'url': 'https://piapro.jp/t/9cSd',
  30         'md5': '952bb6d1e8de95050206408a87790676',
  31         'info_dict': {
  32             'id': '9cSd',
  33             'ext': 'mp3',
  34             'title': '青に溶けた風船 / 初音ミク',
  35             'description': 'md5:d395a9bd151447631a5a1460bc7f9132',
  36             'uploader': 'シアン・キノ',
  37             'uploader_id': 'cyankino',
  38         }
  39     }]
  40
  41     _login_status = False
  42
  43     def _perform_login(self, username, password):
  44         login_ok = True
  45         login_form_strs = {
  46             '_username': username,
  47             '_password': password,
  48             '_remember_me': 'on',
  49             'login': 'ログイン'
  50         }
  51         self._request_webpage('https://piapro.jp/login/', None)
  52         urlh = self._request_webpage(
  53             'https://piapro.jp/login/exe', None,
  54             note='Logging in', errnote='Unable to log in',
  55             data=urlencode_postdata(login_form_strs))
  56         if urlh is False:
  57             login_ok = False
  58         else:
  59             parts = compat_urlparse.urlparse(urlh.geturl())
  60             if parts.path != '/':
  61                 login_ok = False
  62         if not login_ok:
  63             self.report_warning(
  64                 'unable to log in: bad username or password')
  65         self._login_status = login_ok
  66
  67     def _real_extract(self, url):
  68         video_id = self._match_id(url)
  69         webpage = self._download_webpage(url, video_id)
  70
  71         category_id = self._search_regex(r'categoryId=(.+)">', webpage, 'category ID')
  72         if category_id not in ('1', '2', '21', '22', '23', '24', '25'):
  73             raise ExtractorError('The URL does not contain audio.', expected=True)
  74
  75         str_duration, str_filesize = self._search_regex(
  76             r'サイズ：</span>(.+?)/\(([0-9,]+?[KMG]?B)）', webpage, 'duration and size',
  77             group=(1, 2), default=(None, None))
  78         str_viewcount = self._search_regex(r'閲覧数：</span>([0-9,]+)\s+', webpage, 'view count', fatal=False)
  79
  80         uploader_id, uploader = self._search_regex(
  81             r'<a\s+class="cd_user-name"\s+href="/(.*)">([^<]+)さん<', webpage, 'uploader',
  82             group=(1, 2), default=(None, None))
  83         content_id = self._search_regex(r'contentId\:\'(.+)\'', webpage, 'content ID')
  84         create_date = self._search_regex(r'createDate\:\'(.+)\'', webpage, 'timestamp')
  85
  86         player_webpage = self._download_webpage(
  87             f'https://piapro.jp/html5_player_popup/?id={content_id}&cdate={create_date}',
  88             video_id, note='Downloading player webpage')
  89
  90         return {
  91             'id': video_id,
  92             'title': self._html_search_regex(r'<h1\s+class="cd_works-title">(.+?)</h1>', webpage, 'title', fatal=False),
  93             'description': self._html_search_regex(r'(?s)<p\s+class="cd_dtl_cap">(.+?)</p>\s*<div', webpage, 'description', fatal=False),
  94             'uploader': uploader,
  95             'uploader_id': uploader_id,
  96             'timestamp': unified_timestamp(create_date, False),
  97             'duration': parse_duration(str_duration),
  98             'view_count': str_to_int(str_viewcount),
  99             'thumbnail': self._html_search_meta('twitter:image', webpage),
 100
 101             'filesize_approx': parse_filesize(str_filesize.replace(',', '')),
 102             'url': self._search_regex(r'mp3:\s*\'(.*?)\'\}', player_webpage, 'url'),
 103             'ext': 'mp3',
 104             'vcodec': 'none',
 105         }