mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-23 15:03:03 -05:00
89 lines
4.8 KiB
Plaintext
89 lines
4.8 KiB
Plaintext
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Comment
|
|
|
|
class GCN(BasicNewsRecipe):
|
|
title = u'Gazeta Codziennej Nowiny'
|
|
__author__ = 'fenuks'
|
|
description = u'nowiny24.pl - portal regionalny województwa podkarpackiego.'
|
|
category = 'newspaper'
|
|
language = 'pl'
|
|
encoding = 'iso-8859-2'
|
|
extra_css = 'ul {list-style: none; padding:0; margin:0;}'
|
|
INDEX = 'http://www.nowiny24.pl'
|
|
masthead_url = INDEX + '/images/top_logo.png'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
remove_attributes = ['style']
|
|
preprocess_regexps = [(re.compile(ur'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(ur'Przeczytaj także:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: ''),
|
|
(re.compile(ur'Przeczytaj również:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: ''), (re.compile(ur'Zobacz też:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: '')]
|
|
|
|
keep_only_tags = [dict(id=['article', 'cover', 'photostory'])]
|
|
remove_tags = [dict(id=['articleTags', 'articleMeta', 'boxReadIt', 'articleGalleries', 'articleConnections',
|
|
'ForumArticleComments', 'articleRecommend', 'jedynkiLinks', 'articleGalleryConnections',
|
|
'photostoryConnections', 'articleEpaper', 'articlePoll', 'articleAlarm', 'articleByline']),
|
|
dict(attrs={'class':'articleFunctions'})]
|
|
|
|
feeds = [(u'Wszystkie', u'http://www.nowiny24.pl/rss.xml'),
|
|
(u'Podkarpacie', u'http://www.nowiny24.pl/podkarpacie.xml'),
|
|
(u'Bieszczady', u'http://www.nowiny24.pl/bieszczady.xml'),
|
|
(u'Rzeszów', u'http://www.nowiny24.pl/rzeszow.xml'),
|
|
(u'Przemyśl', u'http://www.nowiny24.pl/przemysl.xml'),
|
|
(u'Leżajsk', u'http://www.nowiny24.pl/lezajsk.xml'),
|
|
(u'Łańcut', u'http://www.nowiny24.pl/lancut.xml'),
|
|
(u'Dębica', u'http://www.nowiny24.pl/debica.xml'),
|
|
(u'Jarosław', u'http://www.nowiny24.pl/jaroslaw.xml'),
|
|
(u'Krosno', u'http://www.nowiny24.pl/krosno.xml'),
|
|
(u'Mielec', u'http://www.nowiny24.pl/mielec.xml'),
|
|
(u'Nisko', u'http://www.nowiny24.pl/nisko.xml'),
|
|
(u'Sanok', u'http://www.nowiny24.pl/sanok.xml'),
|
|
(u'Stalowa Wola', u'http://www.nowiny24.pl/stalowawola.xml'),
|
|
(u'Tarnobrzeg', u'http://www.nowiny24.pl/tarnobrzeg.xml'),
|
|
(u'Sport', u'http://www.nowiny24.pl/sport.xml'),
|
|
(u'Dom', u'http://www.nowiny24.pl/dom.xml'),
|
|
(u'Auto', u'http://www.nowiny24.pl/auto.xml'),
|
|
(u'Praca', u'http://www.nowiny24.pl/praca.xml'),
|
|
(u'Zdrowie', u'http://www.nowiny24.pl/zdrowie.xml'),
|
|
(u'Wywiady', u'http://www.nowiny24.pl/wywiady.xml')]
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup(self.INDEX + '/apps/pbcs.dll/section?Category=JEDYNKI')
|
|
nexturl = self.INDEX + soup.find(id='covers').find('a')['href']
|
|
soup = self.index_to_soup(nexturl)
|
|
self.cover_url = self.INDEX + soup.find(id='cover').find(name='img')['src']
|
|
return getattr(self, 'cover_url', self.cover_url)
|
|
|
|
def append_page(self, soup, appendtag):
|
|
tag = soup.find('span', attrs={'class':'photoNavigationPages'})
|
|
if tag:
|
|
number = int(tag.string.rpartition('/')[-1].replace(' ', ''))
|
|
baseurl = self.INDEX + soup.find(attrs={'class':'photoNavigationNext'})['href'][:-1]
|
|
|
|
for r in appendtag.findAll(attrs={'class':'photoNavigation'}):
|
|
r.extract()
|
|
for nr in range(2, number+1):
|
|
soup2 = self.index_to_soup(baseurl + str(nr))
|
|
pagetext = soup2.find(id='photoContainer')
|
|
if pagetext:
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
pagetext = soup2.find(attrs={'class':'photoMeta'})
|
|
if pagetext:
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
pagetext = soup2.find(attrs={'class':'photoStoryText'})
|
|
if pagetext:
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
|
|
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
|