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|content)/(?P<id>\w+)/?'
  16     _TESTS = [{
  17         'url': 'https://piapro.jp/t/NXYR',
  18         'md5': 'f7c0f760913fb1d44a1c45a4af793909',
  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             'description': 'http://www.nicovideo.jp/watch/sm8082467',
  26             'duration': 189.0,
  27             'timestamp': 1251785475,
  28             'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
  29             'upload_date': '20090901',
  30             'view_count': int,
  31         }
  32     }, {
  33         'note': 'There are break lines in description, mandating (?s) flag',
  34         'url': 'https://piapro.jp/t/9cSd',
  35         'md5': '952bb6d1e8de95050206408a87790676',
  36         'info_dict': {
  37             'id': '9cSd',
  38             'ext': 'mp3',
  39             'title': '青に溶けた風船 / 初音ミク',
  40             'description': 'md5:d395a9bd151447631a5a1460bc7f9132',
  41             'uploader': 'シアン・キノ',
  42             'duration': 229.0,
  43             'timestamp': 1644030039,
  44             'upload_date': '20220205',
  45             'view_count': int,
  46             'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
  47             'uploader_id': 'cyankino',
  48         }
  49     }, {
  50         'url': 'https://piapro.jp/content/hcw0z3a169wtemz6',
  51         'only_matching': True
  52     }]
  53
  54     _login_status = False
  55
  56     def _perform_login(self, username, password):
  57         login_ok = True
  58         login_form_strs = {
  59             '_username': username,
  60             '_password': password,
  61             '_remember_me': 'on',
  62             'login': 'ログイン'
  63         }
  64         self._request_webpage('https://piapro.jp/login/', None)
  65         urlh = self._request_webpage(
  66             'https://piapro.jp/login/exe', None,
  67             note='Logging in', errnote='Unable to log in',
  68             data=urlencode_postdata(login_form_strs))
  69         if urlh is False:
  70             login_ok = False
  71         else:
  72             parts = compat_urlparse.urlparse(urlh.url)
  73             if parts.path != '/':
  74                 login_ok = False
  75         if not login_ok:
  76             self.report_warning(
  77                 'unable to log in: bad username or password')
  78         self._login_status = login_ok
  79
  80     def _real_extract(self, url):
  81         video_id = self._match_id(url)
  82         webpage = self._download_webpage(url, video_id)
  83
  84         category_id = self._search_regex(r'categoryId=(.+)">', webpage, 'category ID')
  85         if category_id not in ('1', '2', '21', '22', '23', '24', '25'):
  86             raise ExtractorError('The URL does not contain audio.', expected=True)
  87
  88         str_duration, str_filesize = self._search_regex(
  89             r'サイズ：</span>(.+?)/\(([0-9,]+?[KMG]?B)）', webpage, 'duration and size',
  90             group=(1, 2), default=(None, None))
  91         str_viewcount = self._search_regex(r'閲覧数：</span>([0-9,]+)\s+', webpage, 'view count', fatal=False)
  92
  93         uploader_id, uploader = self._search_regex(
  94             r'<a\s+class="cd_user-name"\s+href="/(.*)">([^<]+)さん<', webpage, 'uploader',
  95             group=(1, 2), default=(None, None))
  96         content_id = self._search_regex(r'contentId\:\'(.+)\'', webpage, 'content ID')
  97         create_date = self._search_regex(r'createDate\:\'(.+)\'', webpage, 'timestamp')
  98
  99         player_webpage = self._download_webpage(
 100             f'https://piapro.jp/html5_player_popup/?id={content_id}&cdate={create_date}',
 101             video_id, note='Downloading player webpage')
 102
 103         return {
 104             'id': video_id,
 105             'title': self._html_search_regex(r'<h1\s+class="cd_works-title">(.+?)</h1>', webpage, 'title', fatal=False),
 106             'description': self._html_search_regex(r'(?s)<p\s+class="cd_dtl_cap">(.+?)</p>\s*<div', webpage, 'description', fatal=False),
 107             'uploader': uploader,
 108             'uploader_id': uploader_id,
 109             'timestamp': unified_timestamp(create_date, False),
 110             'duration': parse_duration(str_duration),
 111             'view_count': str_to_int(str_viewcount),
 112             'thumbnail': self._html_search_meta('twitter:image', webpage),
 113
 114             'filesize_approx': parse_filesize(str_filesize.replace(',', '')),
 115             'url': self._search_regex(r'mp3:\s*\'(.*?)\'\}', player_webpage, 'url'),
 116             'ext': 'mp3',
 117             'vcodec': 'none',
 118         }