calibre/recipes/in4_pl.recipe
2019-03-22 23:47:49 +05:30

54 lines
2.1 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.ebooks.BeautifulSoup import Comment
class in4(BasicNewsRecipe):
title = u'IN4.pl'
oldest_article = 7
max_articles_per_feed = 100
__author__ = 'fenuks'
description = u'Serwis Informacyjny - Aktualnosci, recenzje'
category = 'IT'
language = 'pl'
index = 'http://www.in4.pl/'
no_stylesheets = True
remove_empty_feeds = True
preprocess_regexps = [
(re.compile(u'<a title="translate into.*?</a>', re.DOTALL), lambda match: '')]
keep_only_tags = [dict(name='div', attrs={'class': 'left_alone'})]
remove_tags_after = dict(name='img', attrs={'title': 'komentarze'})
remove_tags = [dict(name='img', attrs={'title': 'komentarze'})]
feeds = [(u'Wiadomo\u015bci', u'http://www.in4.pl/rss.php'), (u'Recenzje',
u'http://www.in4.pl/rss_recenzje.php'), (u'Mini recenzje', u'http://www.in4.pl/rss_mini.php')]
def append_page(self, soup, appendtag):
a = soup.findAll('a')
nexturl = None
for i in a:
if i.string and 'następna str' in i.string:
nexturl = 'http://www.in4.pl/' + i['href']
i.extract()
while nexturl:
soup2 = self.index_to_soup(nexturl)
pagetext = soup2.find(id='news')
comments = pagetext.findAll(
text=lambda text: isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
nexturl = None
tag = soup2.findAll('a')
for z in tag:
if z.string and u'następna str' in z.string:
nexturl = 'http://www.in4.pl/' + z['href']
break
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
for a in soup.findAll('a', href=True):
if 'http://' not in a['href'] and 'https://' not in a['href']:
a['href'] = self.index + a['href']
return soup