mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
74 lines
3.2 KiB
Plaintext
74 lines
3.2 KiB
Plaintext
__license__ = 'GPL v3'
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Comment
|
|
|
|
|
|
class cdrinfo(BasicNewsRecipe):
|
|
title = u'CDRinfo.pl'
|
|
__author__ = 'fenuks'
|
|
description = u'Serwis poświęcony archiwizacji danych. Testy i recenzje nagrywarek. Programy do nagrywania płyt. Dyski twarde, dyski SSD i serwery sieciowe NAS. Rankingi dyskow twardych, najszybsze dyski twarde, newsy, artykuły, testy, recenzje, porady, oprogramowanie. Zestawienie nagrywarek, najnowsze biosy do nagrywarek, programy dla dysków twardych.' # noqa
|
|
category = 'it, hardware'
|
|
# publication_type = ''
|
|
language = 'pl'
|
|
# encoding = ''
|
|
# extra_css = ''
|
|
cover_url = 'http://www.cdrinfo.pl/gfx/graph3/top.jpg'
|
|
# masthead_url = ''
|
|
use_embedded_content = False
|
|
oldest_article = 777
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
remove_empty_feeds = True
|
|
remove_javascript = True
|
|
remove_attributes = ['style', 'onmouseover']
|
|
preprocess_regexps = [(re.compile(u'<p[^>]*?>Uprzejmie prosimy o przestrzeganie netykiety.+?www\\.gravatar\\.com</a>\\.</p>', re.DOTALL), lambda match: ''),
|
|
(re.compile(u'<p[^>]*?>.{,2}</p>', re.DOTALL), lambda match: '')]
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
|
|
keep_only_tags = [
|
|
dict(name='input', attrs={'name': 'ref'}), dict(id=['text', 'text2'])]
|
|
remove_tags = [dict(attrs={'class': ['navigation', 'sociable', 'last6news']}), dict(
|
|
name=['hr', 'br']), dict(id='respond')]
|
|
remove_tags_after = dict(id='artnawigacja')
|
|
feeds = [(u'Wiadomości', 'http://feeds.feedburner.com/cdrinfo'),
|
|
(u'Recenzje', 'http://www.cdrinfo.pl/rss/rss_recenzje.php'),
|
|
(u'Konsole', 'http://konsole.cdrinfo.pl/rss/rss_konsole_news.xml'),
|
|
(u'Pliki', 'http://www.cdrinfo.pl/rss/rss_pliki.xml')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
if soup.find(id='artnawigacja'):
|
|
self.append_page(soup, soup.body)
|
|
return soup
|
|
|
|
def append_page(self, soup, appendtag):
|
|
baseurl = 'http://cdrinfo.pl' + \
|
|
soup.find(name='input', attrs={'name': 'ref'})['value'] + '/'
|
|
if baseurl[-2] == '/':
|
|
baseurl = baseurl[:-1]
|
|
tag = soup.find(id='artnawigacja')
|
|
div = tag.find('div', attrs={'align': 'right'})
|
|
while div:
|
|
counter = 0
|
|
while counter < 5:
|
|
try:
|
|
soup2 = self.index_to_soup(baseurl + div.a['href'])
|
|
break
|
|
except:
|
|
counter += 1
|
|
tag2 = soup2.find(id='artnawigacja')
|
|
div = tag2.find('div', attrs={'align': 'right'})
|
|
pagetext = soup2.find(attrs={'class': 'art'})
|
|
comments = pagetext.findAll(
|
|
text=lambda text: isinstance(text, Comment))
|
|
for comment in comments:
|
|
comment.extract()
|
|
for r in soup2.findAll(attrs={'class': 'star-rating'}):
|
|
r.extract()
|
|
for r in soup2.findAll(attrs={'class': 'star-rating2'}):
|
|
r.extract()
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
tag.extract()
|