mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-10-31 10:37:00 -04:00
44 lines
2.0 KiB
Python
44 lines
2.0 KiB
Python
import re
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Dobreprogramy_pl(BasicNewsRecipe):
|
|
title = 'Dobreprogramy.pl'
|
|
__author__ = u'fenuks & Tomasz Długosz'
|
|
__licence__ = 'GPL v3'
|
|
category = 'IT'
|
|
masthead_url = 'http://static.dpcdn.pl/css/Black/Images/header_logo_napis_fullVersion.png'
|
|
cover_url = 'http://userlogos.org/files/logos/Karmody/dobreprogramy_01.png'
|
|
description = u'Aktualności i blogi z dobreprogramy.pl'
|
|
encoding = 'utf-8'
|
|
index = 'http://www.dobreprogramy.pl/'
|
|
no_stylesheets = True
|
|
language = 'pl'
|
|
extra_css = '.title {font-size:22px;}, h1 { font-size:130% }'
|
|
oldest_article = 8
|
|
max_articles_per_feed = 100
|
|
remove_attrs = ['style', 'width', 'height']
|
|
preprocess_regexps = [(re.compile(
|
|
type(u'')(r'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>')), lambda match: '')]
|
|
keep_only_tags = [dict(name='h1'), dict(
|
|
attrs={'class': ['entry single']}), dict(id='phContent_divArticle')]
|
|
remove_tags = [dict(attrs={'class': ['newsOptions', 'noPrint', 'komentarze', 'tags font-heading-master', 'social nested-grid grid-margin-px15-top clearfix no-mobile', 'page-info text-h4 font-heading grid-margin-px15-top color-annotation clearfix', 'series grid-margin-px30-top']}), dict(id='komentarze'), dict(id='phContent_ctl02_sBreadcrumb'), dict(name='iframe')] # noqa: E501
|
|
|
|
feeds = [(u'Aktualności', 'http://feeds.feedburner.com/dobreprogramy/Aktualnosci'),
|
|
('Blogi', 'http://feeds.feedburner.com/dobreprogramy/BlogCzytelnikow')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for a in soup('a', href=True):
|
|
if 'http://' not in a['href'] and 'https://' not in a['href']:
|
|
a['href'] = self.index + a['href']
|
|
for r in soup.findAll('iframe'):
|
|
r.parent.extract()
|
|
return soup
|
|
|
|
def postprocess_html(self, soup, first_fetch):
|
|
for r in soup.findAll('span', text=''):
|
|
if not r.string:
|
|
r.extract()
|
|
return soup
|