X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..d2e1a98478a93d5d191b83a9aa545df270ebf323:/youtube_dl/extractor/nrk.py diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 3a6a788..1e4cfa2 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -4,9 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( ExtractorError, - int_or_none, + float_or_none, + parse_duration, unified_strdate, ) @@ -72,20 +74,20 @@ class NRKIE(InfoExtractor): class NRKTVIE(InfoExtractor): - _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P[a-z]{4}\d{8})' + _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 = [ { - 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/muhh48000314/23-05-2014', - 'md5': '7b96112fbae1faf09a6f9ae1aff6cb84', + 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', + 'md5': 'adf2c5454fa2bf032f47a9f8fb351342', 'info_dict': { - 'id': 'muhh48000314', + 'id': 'MUHH48000314', 'ext': 'flv', 'title': '20 spørsmål', 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'upload_date': '20140523', 'duration': 1741.52, - } + }, }, { 'url': 'http://tv.nrk.no/program/mdfp15000514', @@ -97,43 +99,156 @@ class NRKTVIE(InfoExtractor): 'description': 'md5:654c12511f035aed1e42bdf5db3b206a', 'upload_date': '20140524', 'duration': 4605.0, - } + }, + }, + { + # single playlist video + 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + 'skip': 'Only works from Norway', }, + { + 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', + 'playlist': [ + { + 'md5': '9480285eff92d64f06e02a5367970a7a', + 'info_dict': { + 'id': 'MSPO40010515-part1', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + }, + { + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + }, + }, + ], + 'info_dict': { + 'id': 'MSPO40010515', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'upload_date': '20150106', + 'duration': 6947.5199999999995, + }, + 'skip': 'Only works from Norway', + } ] + def _seconds2str(self, s): + return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000) + + 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._seconds2str(begin) + endtime = self._seconds2str(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) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + part_id = mobj.group('part_id') + baseurl = mobj.group('baseurl') - page = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_meta( + 'title', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') - title = self._html_search_meta('title', page, 'title') - description = self._html_search_meta('description', page, 'description') - thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False) - upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False)) - duration = self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False) - if duration: - duration = float(duration) + thumbnail = self._html_search_regex( + r'data-posterimage="([^"]+)"', + webpage, 'thumbnail', fatal=False) + upload_date = unified_strdate(self._html_search_meta( + 'rightsfrom', webpage, 'upload date', fatal=False)) + duration = float_or_none(self._html_search_regex( + r'data-duration="([^"]+)"', + webpage, 'duration', fatal=False)) + + # playlist + parts = re.findall( + r']+data-argument="([^"]+)">([^<]+)', webpage) + if parts: + entries = [] + for current_part_id, stream_url, part_title in parts: + if part_id and current_part_id != part_id: + continue + video_part_id = '%s-part%s' % (video_id, current_part_id) + formats = self._extract_f4m(stream_url, video_part_id) + entries.append({ + 'id': video_part_id, + 'title': part_title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + }) + if part_id: + if entries: + return entries[0] + else: + playlist = self.playlist_result(entries, video_id, title, description) + playlist.update({ + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + }) + return playlist formats = [] - f4m_url = re.search(r'data-media="([^"]+)"', page) + f4m_url = re.search(r'data-media="([^"]+)"', webpage) if f4m_url: - formats.append({ - 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', - 'format_id': 'f4m', - 'ext': 'flv', - }) + formats.extend(self._extract_f4m(f4m_url.group(1), video_id)) - m3u8_url = re.search(r'data-hls-media="([^"]+)"', page) + m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage) if m3u8_url: - formats.append({ - 'url': m3u8_url.group(1), - 'format_id': 'm3u8', - }) - + 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, @@ -142,4 +257,5 @@ class NRKTVIE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, - } \ No newline at end of file + 'subtitles': subtitles, + }