mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
64 lines
3.3 KiB
Plaintext
64 lines
3.3 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
from calibre.ebooks.BeautifulSoup import Comment
|
|
|
|
|
|
class BenchmarkPl(BasicNewsRecipe):
|
|
title = u'Benchmark.pl'
|
|
__author__ = 'fenuks'
|
|
description = u'benchmark.pl, recenzje i testy sprzętu, aktualności, rankingi, sterowniki, porady, opinie'
|
|
masthead_url = 'http://www.benchmark.pl/i/logo-footer.png'
|
|
cover_url = 'http://www.benchmark.pl/i/logo-dark.png'
|
|
category = 'IT'
|
|
language = 'pl'
|
|
oldest_article = 8
|
|
max_articles_per_feed = 100
|
|
extra_css = 'ul {list-style-type: none;}'
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
preprocess_regexps = [(re.compile(u'<h3><span style="font-size: small;"> Zobacz poprzednie <a href="http://www.benchmark.pl/news/zestawienie/grupa_id/135">Opinie dnia:</a></span>.*</body>', # noqa
|
|
re.DOTALL | re.IGNORECASE), lambda match: '</body>'), (re.compile(u'Więcej o .*?</ul>', re.DOTALL | re.IGNORECASE), lambda match: '')] # noqa
|
|
|
|
keep_only_tags = [dict(id=['articleHeader', 'articleGallery']), dict(
|
|
name='div', attrs={'class': ['m_zwykly', 'gallery']}), dict(id='article')]
|
|
remove_tags_after = dict(id='article')
|
|
remove_tags = [dict(name='div', attrs={'class': ['comments', 'body', 'kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery', 'breadcrumb', 'footer', 'moreTopics']}), dict(name='table', attrs={ 'background': 'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width': '210', 'cellspacing': '1', 'cellpadding': '4', 'border': '0', 'align': 'right'})] # noqa
|
|
|
|
INDEX = 'http://www.benchmark.pl'
|
|
feeds = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'),
|
|
(u'Testy i recenzje', u'http://www.benchmark.pl/rss/testy-recenzje-minirecenzje.xml')]
|
|
|
|
def append_page(self, soup, appendtag):
|
|
nexturl = soup.find(attrs={'class': 'next'})
|
|
while nexturl:
|
|
soup2 = self.index_to_soup(nexturl['href'])
|
|
nexturl = soup2.find(attrs={'class': 'next'})
|
|
pagetext = soup2.find(name='div', attrs={'class': 'body'})
|
|
tag = appendtag.find('div', attrs={'class': 'k_ster'})
|
|
if tag:
|
|
tag.extract()
|
|
comments = pagetext.findAll(
|
|
text=lambda text: isinstance(text, Comment))
|
|
for comment in comments:
|
|
comment.extract()
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
if appendtag.find('div', attrs={'class': 'k_ster'}):
|
|
appendtag.find('div', attrs={'class': 'k_ster'}).extract()
|
|
for r in appendtag.findAll(attrs={'class': 'changePage'}):
|
|
r.extract()
|
|
|
|
def preprocess_html(self, soup):
|
|
self.append_page(soup, soup.body)
|
|
for a in soup.findAll('a', href=True):
|
|
if not a['href'].startswith('http'):
|
|
a['href'] = self.INDEX + a['href']
|
|
for r in soup.findAll(attrs={'class': ['comments', 'body']}):
|
|
r.extract()
|
|
tag1 = soup.find(attrs={'class': 'inlineGallery'})
|
|
if tag1:
|
|
for tag in tag1.findAll('li'):
|
|
tag['style'] = 'float: left; margin-right: 10px;'
|
|
tag1.findNext('p')['style'] = 'clear: both;'
|
|
return soup
|