import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( determine_ext, dict_get, int_or_none, unified_timestamp, str_or_none, strip_or_none, try_get, ) class SVTBaseIE(InfoExtractor): _GEO_COUNTRIES = ['SE'] def _extract_video(self, video_info, video_id): is_live = dict_get(video_info, ('live', 'simulcast'), default=False) m3u8_protocol = 'm3u8' if is_live else 'm3u8_native' formats = [] subtitles = {} for vr in video_info['videoReferences']: player_type = vr.get('playerType') or vr.get('format') vurl = vr['url'] ext = determine_ext(vurl) if ext == 'm3u8': fmts, subs = self._extract_m3u8_formats_and_subtitles( vurl, video_id, ext='mp4', entry_protocol=m3u8_protocol, m3u8_id=player_type, fatal=False) formats.extend(fmts) self._merge_subtitles(subs, target=subtitles) elif ext == 'f4m': formats.extend(self._extract_f4m_formats( vurl + '?hdcore=3.3.0', video_id, f4m_id=player_type, fatal=False)) elif ext == 'mpd': fmts, subs = self._extract_mpd_formats_and_subtitles( vurl, video_id, mpd_id=player_type, fatal=False) formats.extend(fmts) self._merge_subtitles(subs, target=subtitles) else: formats.append({ 'format_id': player_type, 'url': vurl, }) rights = try_get(video_info, lambda x: x['rights'], dict) or {} if not formats and rights.get('geoBlockedSweden'): self.raise_geo_restricted( 'This video is only available in Sweden', countries=self._GEO_COUNTRIES, metadata_available=True) self._sort_formats(formats) subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences')) if isinstance(subtitle_references, list): for sr in subtitle_references: subtitle_url = sr.get('url') subtitle_lang = sr.get('language', 'sv') if subtitle_url: sub = { 'url': subtitle_url, } if determine_ext(subtitle_url) == 'm3u8': # XXX: no way of testing, is it ever hit? sub['ext'] = 'vtt' subtitles.setdefault(subtitle_lang, []).append(sub) title = video_info.get('title') series = video_info.get('programTitle') season_number = int_or_none(video_info.get('season')) episode = video_info.get('episodeTitle') episode_number = int_or_none(video_info.get('episodeNumber')) timestamp = unified_timestamp(rights.get('validFrom')) duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration'))) age_limit = None adult = dict_get( video_info, ('inappropriateForChildren', 'blockedForChildren'), skip_false_values=False) if adult is not None: age_limit = 18 if adult else 0 return { 'id': video_id, 'title': title, 'formats': formats, 'subtitles': subtitles, 'duration': duration, 'timestamp': timestamp, 'age_limit': age_limit, 'series': series, 'season_number': season_number, 'episode': episode, 'episode_number': episode_number, 'is_live': is_live, } class SVTIE(SVTBaseIE): _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P\d+)&.*?\barticleId=(?P\d+)' _TEST = { 'url': 'http://www.svt.se/wd?widgetId=23991§ionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false', 'md5': '33e9a5d8f646523ce0868ecfb0eed77d', 'info_dict': { 'id': '2900353', 'ext': 'mp4', 'title': 'Stjärnorna skojar till det - under SVT-intervjun', 'duration': 27, 'age_limit': 0, }, } @staticmethod def _extract_url(webpage): mobj = re.search( r'(?: