[gaskrank] Fix extraction

This commit is contained in:
motophil 2017-03-19 12:54:02 +01:00 committed by Sergey M․
parent 703751add4
commit 5a6d1da442
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

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,
) )
@ -49,19 +48,12 @@ 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._og_search_title(webpage, default=None) or self._html_search_meta(
r'movieName\s*:\s*\'([^\']*)\'', 'title', webpage, fatal=True)
webpage, 'title')
thumbnail = self._search_regex(
r'poster\s*:\s*\'([^\']*)\'',
webpage, 'thumbnail', default=None)
mobj = re.search( mobj = re.search(
r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])', r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[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: 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')
formats = [] entry = self._parse_html5_media_entries(url, webpage, video_id)[0]
for key in playlist: entry.update({
formats.append({
'url': playlist[key]['src'],
'format_id': key,
'quality': playlist[key].get('quality')})
self._sort_formats(formats, field_preference=['format_id'])
return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'formats': formats,
'thumbnail': thumbnail,
'categories': categories, 'categories': categories,
'display_id': display_id, 'display_id': display_id,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
@ -120,4 +97,7 @@ class GaskrankIE(InfoExtractor):
'tags': tags, 'tags': tags,
'view_count': view_count, 'view_count': view_count,
'average_rating': average_rating, 'average_rating': average_rating,
} })
self._sort_formats(entry['formats'])
return entry