calibre/recipes/picoboard_pl.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

37 lines
1.5 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
class Pikoboard(BasicNewsRecipe):
title = u'Pikoboard.pl'
__author__ = 'fenuks'
description = u'Portal poświęcony takim urządzeniom jak: Raspberry Pi, XBMC, ODROID-X, BeagleBoard czy CuBox. Systemy operacyjne, modyfikacje oraz obudowy i innego rodzaju dodatki.' # noqa
category = 'IT, open source, Linux, Raspberry Pi'
language = 'pl'
cover_url = 'http://picoboard.pl/wp-content/themes/portal/img/logo.jpg'
extra_css = 'img.alignleft {float: left; margin-right: 5px;}'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
use_embedded_content = False
keep_only_tags = [dict(id=['dzial', 'posts'])]
remove_tags = [dict(attrs={'class': 'post-comments'})]
remove_tags_after = dict(attrs={'class': 'entry clr'})
feeds = [(u'Newsy', u'http://picoboard.pl/feed/atom/'),
(u'Artyku\u0142y', u'http://picoboard.pl/category/artykuly/feed/')]
def append_page(self, soup, appendtag):
tag = appendtag.find(attrs={'id': 'paginacja'})
if tag:
for nexturl in tag.findAll('a'):
soup2 = self.index_to_soup(nexturl['href'])
pagetext = soup2.find(attrs={'class': 'entry clr'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'id': 'paginacja'}):
r.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup