X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnrk.py;h=e91d3a248ec3367af8b7e9a8f60be0d503877481;hb=a09141548aa31db7c7d9457b10f5c84e6e32beba;hp=321ce5ce707c7006ad1a8f5979e01afab1bddd23;hpb=43bc88903d0665c42f205bddd0a2f5017581e8be;p=youtube-dl diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 321ce5ce7..e91d3a248 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -4,54 +4,58 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( ExtractorError, float_or_none, + parse_duration, unified_strdate, ) class NRKIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P[\dA-F]{16})' + _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P\d+)' _TESTS = [ { - 'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/', - 'md5': 'a6eac35052f3b242bb6bb7f43aed5886', + 'url': 'http://www.nrk.no/video/PS*150533', + 'md5': 'bccd850baebefe23b56d708a113229c2', 'info_dict': { 'id': '150533', 'ext': 'flv', 'title': 'Dompap og andre fugler i Piip-Show', - 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f' + 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', + 'duration': 263, } }, { - 'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/', - 'md5': '3471f2a51718195164e88f46bf427668', + 'url': 'http://www.nrk.no/video/PS*154915', + 'md5': '0b1493ba1aae7d9579a5ad5531bc395a', 'info_dict': { 'id': '154915', 'ext': 'flv', 'title': 'Slik høres internett ut når du er blind', 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', + 'duration': 20, } }, ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage(url, video_id) - - video_id = self._html_search_regex(r'
', page, 'video id') + video_id = self._match_id(url) data = self._download_json( - 'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON') + 'http://v8.psapi.nrk.no/mediaelement/%s' % video_id, + video_id, 'Downloading media JSON') if data['usageRights']['isGeoBlocked']: - raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True) + raise ExtractorError( + 'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', + expected=True) + + video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81' - video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124' + duration = parse_duration(data.get('duration')) images = data.get('images') if images: @@ -67,12 +71,53 @@ class NRKIE(InfoExtractor): 'ext': 'flv', 'title': data['title'], 'description': data['description'], + 'duration': duration, 'thumbnail': thumbnail, } +class NRKPlaylistIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P[^/]+)' + + _TESTS = [{ + 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', + 'info_dict': { + 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763', + 'title': 'Gjenopplev den historiske solformørkelsen', + 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed', + }, + 'playlist_count': 2, + }, { + 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449', + 'info_dict': { + 'id': 'rivertonprisen-til-karin-fossum-1.12266449', + 'title': 'Rivertonprisen til Karin Fossum', + 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', + }, + 'playlist_count': 5, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('nrk:%s' % video_id, 'NRK') + for video_id in re.findall( + r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"', + webpage) + ] + + playlist_title = self._og_search_title(webpage) + playlist_description = self._og_search_description(webpage) + + return self.playlist_result( + entries, playlist_id, playlist_title, playlist_description) + + class NRKTVIE(InfoExtractor): - _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P\d+))?' + _VALID_URL = r'(?Phttp://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P\d+))?' _TESTS = [ { @@ -147,6 +192,30 @@ class NRKTVIE(InfoExtractor): } ] + def _debug_print(self, txt): + if self._downloader.params.get('verbose', False): + self.to_screen('[debug] %s' % txt) + + def _get_subtitles(self, subtitlesurl, video_id, baseurl): + url = "%s%s" % (baseurl, subtitlesurl) + self._debug_print('%s: Subtitle url: %s' % (video_id, url)) + captions = self._download_xml( + url, video_id, 'Downloading subtitles', + transform_source=lambda s: s.replace(r'
', '\r\n')) + lang = captions.get('lang', 'no') + ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}')) + srt = '' + for pos, p in enumerate(ps): + begin = parse_duration(p.get('begin')) + duration = parse_duration(p.get('dur')) + starttime = self._subtitles_timecode(begin) + endtime = self._subtitles_timecode(begin + duration) + srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text) + return {lang: [ + {'ext': 'ttml', 'url': url}, + {'ext': 'srt', 'data': srt}, + ]} + def _extract_f4m(self, manifest_url, video_id): return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id) @@ -154,6 +223,7 @@ class NRKTVIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') part_id = mobj.group('part_id') + baseurl = mobj.group('baseurl') webpage = self._download_webpage(url, video_id) @@ -210,9 +280,15 @@ class NRKTVIE(InfoExtractor): m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage) if m3u8_url: formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4')) - self._sort_formats(formats) + subtitles_url = self._html_search_regex( + r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"', + webpage, 'subtitle URL', default=None) + subtitles = None + if subtitles_url: + subtitles = self.extract_subtitles(subtitles_url, video_id, baseurl) + return { 'id': video_id, 'title': title, @@ -221,4 +297,5 @@ class NRKTVIE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, + 'subtitles': subtitles, }