Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-19 10:22:52 +08:00
Code Issues Releases Wiki Activity

[Gaskrank] fix for broken site.

Browse Source
This commit is contained in:
motophil 2017-03-19 12:54:02 +01:00
parent 2aec7256ae
commit 9b3cd96034
1 changed files with 13 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/gaskrank.py
View File

@ -6,7 +6,6 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
float_or_none, float_or_none,
int_or_none, int_or_none,
js_to_json,
unified_strdate, unified_strdate,
) )
@ -49,18 +48,15 @@ class GaskrankIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
"""extract information from gaskrank.tv""" """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) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
categories = [re.match(self._VALID_URL, url).group('categories')] categories = [re.match(self._VALID_URL, url).group('categories')]
title = self._search_regex( title = self._search_regex(
r'movieName\s*:\s*\'([^\']*)\'', r'<meta[^>]+itemprop\s*=\s*"name"[^>]+content\s*=\s*"([^"]+)"',
webpage, 'title') webpage, 'title')
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'poster\s*:\s*\'([^\']*)\'', r'<meta[^>]+itemprop\s*=\s*"thumbnail"[^>]+content\s*=\s*"([^"]+)"',
webpage, 'thumbnail', default=None) webpage, 'thumbnail', default=None)
mobj = re.search( mobj = re.search(
@ -89,23 +85,22 @@ class GaskrankIE(InfoExtractor):
if average_rating: if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.')) 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( video_id = self._search_regex(
r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4', r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4',
playlist.get('0').get('src'), 'video id') webpage, 'video id')
playlist = re.findall(
r'<source([^>]+)',
webpage)
formats = [] formats = []
for key in playlist: for entry in playlist:
url = self._search_regex(r'src\s*=\s*"([^"]+)"', entry, 'url')
label = self._search_regex(r'label\s*=\s*"([^"]+)"', entry, 'label')
formats.append({ formats.append({
'url': playlist[key]['src'], 'url': url,
'format_id': key, 'format_id': label,
'quality': playlist[key].get('quality')}) 'quality': label})
self._sort_formats(formats, field_preference=['format_id'])
return { return {
'id': video_id, 'id': video_id,