[gaskrank] Add new extractor (#11685)

* [gaskrank] Add new extractor

* [gaskrank] Add new extractor - fixes as requested

* [gaskrank] Add new extractor - style fix

* [Gaskrank] Add new extractor - requested fixes

* [Gaskrank] Add new extractor - fix md5 checksum

* [gaskrank] Add new extractor - more requested fixes

* [Gaskrank] Add new extractor - fixed all but one quantified code issues

* [Gaskrank] add new extractor - more fields extracted, added second test

* [Gaskrank] Add new extractor - requested fixes.

* [Gaskrank] Add new extractor - requested changes.

* [Gaskrank] Add new extractor - final(?) fixes.
This commit is contained in:
motophil 2017-02-05 17:19:37 +01:00 committed by Yen Chi Hsuan
parent 019f4c0371
commit e705755739
2 changed files with 122 additions and 0 deletions

View File

@ -349,6 +349,7 @@
from .gamersyde import GamersydeIE from .gamersyde import GamersydeIE
from .gamespot import GameSpotIE from .gamespot import GameSpotIE
from .gamestar import GameStarIE from .gamestar import GameStarIE
from .gaskrank import GaskrankIE
from .gazeta import GazetaIE from .gazeta import GazetaIE
from .gdcvault import GDCVaultIE from .gdcvault import GDCVaultIE
from .generic import GenericIE from .generic import GenericIE

View File

@ -0,0 +1,121 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import float_or_none
from ..utils import int_or_none
from ..utils import js_to_json
from ..utils import unified_strdate
class GaskrankIE(InfoExtractor):
"""InfoExtractor for gaskrank.tv"""
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.html?'
_TESTS = [
{
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
'info_dict': {
'id': '201601/26955',
'ext': 'mp4',
'title': 'Strike! Einparken können nur Männer - Flurschaden hält sich in Grenzen *lol*',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['motorrad-fun'],
'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden',
'uploader_id': 'Bikefun',
'upload_date': '20170110',
'uploader_url': None,
}
},
{
'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
'info_dict': {
'id': '201106/15920',
'ext': 'mp4',
'title': 'Isle of Man - Michael Dunlop vs Guy Martin - schwindelig kucken',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['racing'],
'display_id': 'isle-of-man-tt-2011-michael-du-15920',
'uploader_id': 'IOM',
'upload_date': '20160506',
'uploader_url': 'www.iomtt.com',
}
}
]
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)
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])',
webpage)
if mobj is not None:
uploader_id = mobj.groupdict().get('uploader_id')
upload_date = unified_strdate(mobj.groupdict().get('upload_date'))
uploader_url = self._search_regex(
r'Homepage:\s*<[^>]*>(?P<uploader_url>[^<]*)',
webpage, 'uploader_url', default=None)
tags = re.findall(
r'/tv/tags/[^/]+/"\s*>(?P<tag>[^<]*?)<',
webpage)
view_count = self._search_regex(
r'class\s*=\s*"gkRight"(?:[^>]*>\s*<[^>]*)*icon-eye-open(?:[^>]*>\s*<[^>]*)*>\s*(?P<view_count>[0-9\.]*)',
webpage, 'view_count', default=None)
if view_count:
view_count = int_or_none(view_count.replace('.', ''))
average_rating = self._search_regex(
r'itemprop\s*=\s*"ratingValue"[^>]*>\s*(?P<average_rating>[0-9,]+)',
webpage, 'average_rating')
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')
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 {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'categories': categories,
'display_id': display_id,
'uploader_id': uploader_id,
'upload_date': upload_date,
'uploader_url': uploader_url,
'tags': tags,
'view_count': view_count,
'average_rating': average_rating,
}