R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[Gaskrank] Add new extractor - requested fixes

Browse Source
This commit is contained in:
motophil 2017-01-21 13:47:52 +01:00
parent 274f73b9df
commit 015e4edad0
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/gaskrank.py
View File

@ -1,13 +1,13 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from re import sub import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import js_to_json from ..utils import js_to_json
class GaskrankIE(InfoExtractor): class GaskrankIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv(?:/[^/]+)+/(?P<id>[^/]+).htm' _VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv(?:/[^/]+)+/(?P<id>[^/]+)\.htm'
_TEST = { _TEST = {
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm', 'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '200e28a405f6919b914a83f8adfc5739', 'md5': '200e28a405f6919b914a83f8adfc5739',
@ -21,24 +21,24 @@ class GaskrankIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
def fix_json(code): def fix_json(code):
return sub(r'}[\s]*?,[\s]*?}', r'}}', js_to_json(code)) return re.sub(r'}[\s]*?,[\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)
video_id = self._search_regex(r'https?://movies.gaskrank.tv/([^-]*?).mp4', webpage, 'video id') video_id = self._search_regex(r'https?://movies\.gaskrank\.tv/([^-]*?)\.mp4', webpage, 'video id')
categories = self._search_regex(r'https?://(?:www\.)?gaskrank\.tv/tv(?:/([^/]+))+/[^/]+.htm', url, 'categories') categories = self._search_regex(r'https?://(?:www\.)?gaskrank\.tv/tv(?:/([^/]+))+/[^/]+\.htm', url, 'categories', default=None)
title = self._search_regex(r'movieName[\s\S]*?\'([^\']*?)\'', webpage, 'config', default='{}') title = self._search_regex(r'movieName[^\']*?\'([^\']*?)\'', webpage, 'title')
thumbnail = self._search_regex(r'poster[\s\S]*?\'([^\']*?)\'', webpage, 'config', default='{}') thumbnail = self._search_regex(r'poster[^\']*?\'([^\']*?)\'', webpage, 'thumbnail', default=None)
playlist = self._parse_json( playlist = self._parse_json(
self._search_regex(r'playlist:[\s\S]*?\[([\s\S]*?)]', webpage, 'config', default='{}'), self._search_regex(r'playlist:[\s\S]*?\[([\s\S]*?)]', webpage, 'playlist', default='{}'),
video_id, transform_source=fix_json, fatal=False) video_id, transform_source=fix_json, fatal=False)
formats = [] formats = []
for key in playlist: for key in sorted(playlist):
formats.append({ formats.append({
'url': playlist[key]['src'], 'url': playlist[key]['src'],
'format_id': key, 'format_id': key,
'quality': playlist[key]['quality'], 'quality': playlist[key].get('quality'),
'resolution': playlist[key]['quality']}) 'resolution': playlist[key].get('quality')})
return { return {
'id': video_id, 'id': video_id,