X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0652569e481a8cf0995a00635ef62143fa779add..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/ruutu.py diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index 4e22628..f984040 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -5,68 +5,82 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_urlparse from ..utils import ( determine_ext, + ExtractorError, int_or_none, + xpath_attr, xpath_text, ) class RuutuIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P\d+)' _TESTS = [ { - 'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi', + 'url': 'http://www.ruutu.fi/video/2058907', 'md5': 'ab2093f39be1ca8581963451b3c0234f', 'info_dict': { 'id': '2058907', - 'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi', 'ext': 'mp4', 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!', 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 114, 'age_limit': 0, }, }, { - 'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa', + 'url': 'http://www.ruutu.fi/video/2057306', 'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9', 'info_dict': { 'id': '2057306', - 'display_id': 'superpesis-katso-koko-kausi-ruudussa', 'ext': 'mp4', 'title': 'Superpesis: katso koko kausi Ruudussa', - 'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77', - 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 40, 'age_limit': 0, }, }, + { + 'url': 'http://www.supla.fi/supla/2231370', + 'md5': 'df14e782d49a2c0df03d3be2a54ef949', + 'info_dict': { + 'id': '2231370', + 'ext': 'mp4', + 'title': 'Osa 1: Mikael Jungner', + 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe', + 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 0, + }, + }, + # Episode where is "NOT-USED", but has other + # downloadable sources available. + { + 'url': 'http://www.ruutu.fi/video/3193728', + 'only_matching': True, + }, + { + # audio podcast + 'url': 'https://www.supla.fi/supla/3382410', + 'md5': 'b9d7155fed37b2ebf6021d74c4b8e908', + 'info_dict': { + 'id': '3382410', + 'ext': 'mp3', + 'title': 'Mikä ihmeen poltergeist?', + 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52', + 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 0, + }, + 'expected_warnings': ['HTTP Error 502: Bad Gateway'], + } ] def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - r'data-media-id="(\d+)"', webpage, 'media id') - - video_xml_url = None - - media_data = self._search_regex( - r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage, - 'media data', default=None) - if media_data: - media_json = self._parse_json(media_data, display_id, fatal=False) - if media_json: - xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl') - if xml_url: - video_xml_url = xml_url.replace('{ID}', video_id) - - if not video_xml_url: - video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id + video_id = self._match_id(url) - video_xml = self._download_xml(video_xml_url, video_id) + video_xml = self._download_xml( + 'https://gatling.nelonenmedia.fi/media-xml-cache', video_id, + query={'id': video_id}) formats = [] processed_urls = [] @@ -77,16 +91,29 @@ class RuutuIE(InfoExtractor): extract_formats(child) elif child.tag.endswith('File'): video_url = child.text - if not video_url or video_url in processed_urls or 'NOT_USED' in video_url: - return + if (not video_url or video_url in processed_urls + or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))): + continue processed_urls.append(video_url) ext = determine_ext(video_url) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id='hls')) + video_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) elif ext == 'f4m': formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id='hds')) + video_url, video_id, f4m_id='hds', fatal=False)) + elif ext == 'mpd': + # video-only and audio-only streams are of different + # duration resulting in out of sync issue + continue + formats.extend(self._extract_mpd_formats( + video_url, video_id, mpd_id='dash', fatal=False)) + elif ext == 'mp3' or child.tag == 'AudioMediaFile': + formats.append({ + 'format_id': 'audio', + 'url': video_url, + 'vcodec': 'none', + }) else: proto = compat_urllib_parse_urlparse(video_url).scheme if not child.tag.startswith('HTTP') and proto != 'rtmp': @@ -94,9 +121,12 @@ class RuutuIE(InfoExtractor): preference = -1 if proto == 'rtmp' else 1 label = child.get('label') tbr = int_or_none(child.get('bitrate')) - width, height = [int_or_none(x) for x in child.get('resolution', '').split('x')] + format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto + if not self._is_valid_url(video_url, video_id, format_id): + continue + width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]] formats.append({ - 'format_id': '%s-%s' % (proto, label if label else tbr), + 'format_id': format_id, 'url': video_url, 'width': width, 'height': height, @@ -105,14 +135,18 @@ class RuutuIE(InfoExtractor): }) extract_formats(video_xml.find('./Clip')) + + drm = xpath_text(video_xml, './Clip/DRM', default=None) + if not formats and drm: + raise ExtractorError('This video is DRM protected.', expected=True) + self._sort_formats(formats) return { 'id': video_id, - 'display_id': display_id, - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True), + 'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'), + 'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'), 'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')), 'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')), 'formats': formats,