from .common import InfoExtractor from ..utils import ( ExtractorError, clean_html, extract_attributes, get_element_by_class, get_element_html_by_class, multipart_encode, unified_timestamp, url_or_none, ) from ..utils.traversal import traverse_obj class PiaLiveIE(InfoExtractor): PLAYER_ROOT_URL = 'https://player.pia-live.jp/' PIA_LIVE_API_URL = 'https://api.pia-live.jp' API_KEY = 'kfds)FKFps-dms9e' _VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P[\w-]+)' _TESTS = [ { 'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krUDqGOwN4d61dCWQYOd6CTxl4hjya9dsfEZGsM4uGOUdax60lEI4twsXGXf7crmz8Gk__GhupTrWxA7RFRVt76', 'info_dict': { 'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84', 'display_id': '2431867_001', 'title': 'こながめでたい日2024の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)', 'live_status': 'was_live', 'comment_count': int, }, 'params': { 'getcomments': True, 'skip_download': True, 'ignore_no_formats_error': True, }, 'skip': 'The video is no longer available', }, { 'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krJdu0GVBVbVy01IwpJ6J3qBEm3d9TCTt1d0eWpsZGj7DrOjVOmS7GAWGwyscMgiThopJvzgWC4H5b-7XQjAfRZ', 'info_dict': { 'id': '9ce8b8ba-f6d1-4d1f-83a0-18c3148ded93', 'display_id': '2431867_002', 'title': 'こながめでたい日2024の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)', 'live_status': 'was_live', 'comment_count': int, }, 'params': { 'getcomments': True, 'skip_download': True, 'ignore_no_formats_error': True, }, 'skip': 'The video is no longer available', }, ] def _extract_vars(self, variable, html): return self._search_regex( rf'(?:var|const|let)\s+{variable}\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', html, f'variable {variable}', group='value') def _real_extract(self, url): video_key = self._match_id(url) webpage = self._download_webpage(url, video_key) program_code = self._extract_vars('programCode', webpage) article_code = self._extract_vars('articleCode', webpage) title = self._html_extract_title(webpage) if get_element_html_by_class('play-end', webpage): raise ExtractorError('The video is no longer available', expected=True, video_id=program_code) if start_info := clean_html(get_element_by_class('play-waiting__date', webpage)): date, time = self._search_regex( r'(?P\d{4}/\d{1,2}/\d{1,2})\([月火水木金土日]\)(?P