calibre/recipes/pure_pc.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

46 lines
1.9 KiB
Plaintext

import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class PurePC(BasicNewsRecipe):
title = u'PurePC'
oldest_article = 7
max_articles_per_feed = 100
__author__ = 'fenuks'
description = u'Artykuły, aktualności, sprzęt, forum, chłodzenie, modding, urządzenia mobilne - wszystko w jednym miejscu.'
category = 'IT'
language = 'pl'
masthead_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg'
cover_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg'
extra_css = '.wykres_logo {float: left; margin-right: 5px;}'
no_stylesheets = True
keep_only_tags = [dict(id='content')]
remove_tags_after = dict(attrs={'class': 'fivestar-widget'})
remove_tags = [dict(id='navigator'), dict(
attrs={'class': ['box-tools', 'fivestar-widget', 'PageMenuList']})]
feeds = [(u'Wiadomo\u015bci', u'http://www.purepc.pl/node/feed')]
def append_page(self, soup, appendtag):
lasturl = appendtag.find(attrs={'class': 'pager-last'})
if lasturl:
regex = re.search('(.+?2C)(\d+)', lasturl.a['href'])
baseurl = regex.group(1).replace('?page=0%2C', '?page=1%2C')
baseurl = 'http://www.purepc.pl' + baseurl
nr = int(regex.group(2))
for page_nr in range(1, nr + 1):
soup2 = self.index_to_soup(baseurl + str(page_nr))
pagetext = soup2.find(attrs={'class': 'article'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class': ['PageMenuList', 'pager', 'fivestar-widget']}):
r.extract()
comments = appendtag.findAll(
text=lambda text: isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup