X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/f19349c26118065acbe21509383c63465df794fe..aa7f83c9a137a3249223340ed281b086a1c28496:/youtube_dl/extractor/ruutu.py diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index e417bf6..6c09df2 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_urlparse from ..utils import ( determine_ext, + ExtractorError, int_or_none, xpath_attr, xpath_text, @@ -12,7 +13,7 @@ from ..utils import ( class RuutuIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ruutu\.fi/video/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P\d+)' _TESTS = [ { 'url': 'http://www.ruutu.fi/video/2058907', @@ -22,7 +23,7 @@ class RuutuIE(InfoExtractor): '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, }, @@ -34,12 +35,24 @@ class RuutuIE(InfoExtractor): 'id': '2057306', 'ext': 'mp4', 'title': 'Superpesis: katso koko kausi Ruudussa', - 'description': 'md5:da2736052fef3b2bd5e0005e63c25eac', - '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, + }, + }, ] def _real_extract(self, url): @@ -63,15 +76,17 @@ class RuutuIE(InfoExtractor): processed_urls.append(video_url) ext = determine_ext(video_url) if ext == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) elif ext == 'f4m': - f4m_formats = self._extract_f4m_formats( - video_url, video_id, f4m_id='hds', fatal=False) - if f4m_formats: - formats.extend(f4m_formats) + formats.extend(self._extract_f4m_formats( + 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)) else: proto = compat_urllib_parse_urlparse(video_url).scheme if not child.tag.startswith('HTTP') and proto != 'rtmp': @@ -79,9 +94,12 @@ class RuutuIE(InfoExtractor): preference = -1 if proto == 'rtmp' else 1 label = child.get('label') tbr = int_or_none(child.get('bitrate')) + 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, @@ -90,6 +108,11 @@ 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 {