X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a070911bf98c751e4425008f1335cc57c86d30fc..fe979149c83b5a935f7d28baf75848a9137316fd:/youtube_dl/extractor/drtv.py?ds=sidebyside diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index c44adb1..2d74ff8 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,33 +1,46 @@ +# coding: utf-8 from __future__ import unicode_literals -from .subtitles import SubtitlesInfoExtractor -from .common import ExtractorError -from ..utils import parse_iso8601 +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) -class DRTVIE(SubtitlesInfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P[\da-z-]+)(?:[/#?]|$)' +class DRTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P[\da-z-]+)(?:[/#?]|$)' _TEST = { - 'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8', - 'md5': '4a7e1dd65cdb2643500a3f753c942f25', + 'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5', + 'md5': 'dc515a9ab50577fa14cc4e4b0265168f', 'info_dict': { - 'id': 'partiets-mand-7-8', + 'id': 'panisk-paske-5', 'ext': 'mp4', - 'title': 'Partiets mand (7:8)', - 'description': 'md5:a684b90a8f9336cd4aab94b7647d7862', - 'timestamp': 1403047940, - 'upload_date': '20140617', - 'duration': 1299.040, + 'title': 'Panisk Påske (5)', + 'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c', + 'timestamp': 1426984612, + 'upload_date': '20150322', + 'duration': 1455, }, } def _real_extract(self, url): video_id = self._match_id(url) - programcard = self._download_json( - 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON') + webpage = self._download_webpage(url, video_id) + + if '>Programmet er ikke længere tilgængeligt' in webpage: + raise ExtractorError( + 'Video %s is not available' % video_id, expected=True) + + video_id = self._search_regex( + r'data-(?:material-identifier|episode-slug)="([^"]+)"', + webpage, 'video id') + programcard = self._download_json( + 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, + video_id, 'Downloading video JSON') data = programcard['Data'][0] title = data['Title'] @@ -48,23 +61,41 @@ class DRTVIE(SubtitlesInfoExtractor): elif asset['Kind'] == 'VideoResource': duration = asset['DurationInMilliseconds'] / 1000.0 restricted_to_denmark = asset['RestrictedToDenmark'] + spoken_subtitles = asset['Target'] == 'SpokenSubtitles' for link in asset['Links']: - target = link['Target'] uri = link['Uri'] - formats.append({ - 'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri, - 'format_id': target, - 'ext': link['FileFormat'], - 'preference': -1 if target == 'HDS' else -2, - }) + target = link['Target'] + format_id = target + preference = None + if spoken_subtitles: + preference = -1 + format_id += '-spoken-subtitles' + if target == 'HDS': + formats.extend(self._extract_f4m_formats( + uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43', + video_id, preference, f4m_id=format_id)) + elif target == 'HLS': + formats.extend(self._extract_m3u8_formats( + uri, video_id, 'mp4', preference=preference, + m3u8_id=format_id)) + else: + bitrate = link.get('Bitrate') + if bitrate: + format_id += '-%s' % bitrate + formats.append({ + 'url': uri, + 'format_id': format_id, + 'tbr': bitrate, + 'ext': link.get('FileFormat'), + }) subtitles_list = asset.get('SubtitlesList') if isinstance(subtitles_list, list): LANGS = { - 'Danish': 'dk', + 'Danish': 'da', } for subs in subtitles_list: lang = subs['Language'] - subtitles[LANGS.get(lang, lang)] = subs['Uri'] + subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}] if not formats and restricted_to_denmark: raise ExtractorError( @@ -72,10 +103,6 @@ class DRTVIE(SubtitlesInfoExtractor): self._sort_formats(formats) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return - return { 'id': video_id, 'title': title, @@ -84,5 +111,5 @@ class DRTVIE(SubtitlesInfoExtractor): 'timestamp': timestamp, 'duration': duration, 'formats': formats, - 'subtitles': self.extract_subtitles(video_id, subtitles), + 'subtitles': subtitles, }