yt_dlp/extractor/piapro.py

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