From 5a6d1da442579fc06e458406dba0f8b60102dc1c Mon Sep 17 00:00:00 2001 From: motophil Date: Sun, 19 Mar 2017 12:54:02 +0100 Subject: [PATCH] [gaskrank] Fix extraction --- youtube_dl/extractor/gaskrank.py | 38 ++++++++------------------------ 1 file changed, 9 insertions(+), 29 deletions(-) diff --git a/youtube_dl/extractor/gaskrank.py b/youtube_dl/extractor/gaskrank.py index 36ba7d8cf..baf513665 100644 --- a/youtube_dl/extractor/gaskrank.py +++ b/youtube_dl/extractor/gaskrank.py @@ -6,7 +6,6 @@ from .common import InfoExtractor from ..utils import ( float_or_none, int_or_none, - js_to_json, unified_strdate, ) @@ -49,19 +48,12 @@ class GaskrankIE(InfoExtractor): def _real_extract(self, url): """extract information from gaskrank.tv""" - def fix_json(code): - """Removes trailing comma in json: {{},} --> {{}}""" - return re.sub(r',\s*}', r'}', js_to_json(code)) display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) categories = [re.match(self._VALID_URL, url).group('categories')] - title = self._search_regex( - r'movieName\s*:\s*\'([^\']*)\'', - webpage, 'title') - thumbnail = self._search_regex( - r'poster\s*:\s*\'([^\']*)\'', - webpage, 'thumbnail', default=None) + title = self._og_search_title(webpage, default=None) or self._html_search_meta( + 'title', webpage, fatal=True) mobj = re.search( r'Video von:\s*(?P[^|]*?)\s*\|\s*vom:\s*(?P[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])', @@ -89,29 +81,14 @@ class GaskrankIE(InfoExtractor): if average_rating: average_rating = float_or_none(average_rating.replace(',', '.')) - playlist = self._parse_json( - self._search_regex( - r'playlist\s*:\s*\[([^\]]*)\]', - webpage, 'playlist', default='{}'), - display_id, transform_source=fix_json, fatal=False) - video_id = self._search_regex( r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4', - playlist.get('0').get('src'), 'video id') + webpage, 'video id') - formats = [] - for key in playlist: - formats.append({ - 'url': playlist[key]['src'], - 'format_id': key, - 'quality': playlist[key].get('quality')}) - self._sort_formats(formats, field_preference=['format_id']) - - return { + entry = self._parse_html5_media_entries(url, webpage, video_id)[0] + entry.update({ 'id': video_id, 'title': title, - 'formats': formats, - 'thumbnail': thumbnail, 'categories': categories, 'display_id': display_id, 'uploader_id': uploader_id, @@ -120,4 +97,7 @@ class GaskrankIE(InfoExtractor): 'tags': tags, 'view_count': view_count, 'average_rating': average_rating, - } + }) + self._sort_formats(entry['formats']) + + return entry