mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
35 lines
2.9 KiB
Plaintext
35 lines
2.9 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class GazetaWroclawska(BasicNewsRecipe):
|
|
title = u'Gazeta Wroc\u0142awska'
|
|
__author__ = 'fenuks'
|
|
description = u'Gazeta Regionalna Gazeta Wrocławska. Najnowsze Wiadomości Wrocław, Informacje Wrocław. Czytaj!'
|
|
category = 'newspaper'
|
|
language = 'pl'
|
|
encoding = 'iso-8859-2'
|
|
masthead_url = 'http://s.polskatimes.pl/g/logo_naglowek/gazetawroclawska.png?24'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
#preprocess_regexps = [(re.compile(ur'<b>Czytaj także:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur',<b>Czytaj też:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>Zobacz także:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<center><h4><a.*?</a></h4></center>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>CZYTAJ TEŻ:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>CZYTAJ WIĘCEJ:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>CZYTAJ TAKŻE:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>\* CZYTAJ KONIECZNIE:.*', re.DOTALL), lambda match: '</body>'), (re.compile(ur'<b>Nasze serwisy:</b>.*', re.DOTALL), lambda match: '</body>') ]
|
|
remove_tags_after= dict(attrs={'src':'http://nm.dz.com.pl/dz.png'})
|
|
remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'})]
|
|
|
|
feeds = [(u'Fakty24', u'http://gazetawroclawska.feedsportal.com/c/32980/f/533775/index.rss?201302'), (u'Region', u'http://www.gazetawroclawska.pl/rss/gazetawroclawska_region.xml?201302'), (u'Kultura', u'http://gazetawroclawska.feedsportal.com/c/32980/f/533777/index.rss?201302'), (u'Sport', u'http://gazetawroclawska.feedsportal.com/c/32980/f/533776/index.rss?201302'), (u'Z archiwum', u'http://www.gazetawroclawska.pl/rss/gazetawroclawska_zarchiwum.xml?201302'), (u'M\xf3j reporter', u'http://www.gazetawroclawska.pl/rss/gazetawroclawska_mojreporter.xml?201302'), (u'Historia', u'http://www.gazetawroclawska.pl/rss/gazetawroclawska_historia.xml?201302'), (u'Listy do redakcji', u'http://www.gazetawroclawska.pl/rss/gazetawroclawska_listydoredakcji.xml?201302'), (u'Na drogach', u'http://www.gazetawroclawska.pl/rss/gazetawroclawska_nadrogach.xml?201302')]
|
|
|
|
def print_version(self, url):
|
|
return url.replace('artykul', 'drukuj')
|
|
|
|
def skip_ad_pages(self, soup):
|
|
if 'Advertisement' in soup.title:
|
|
nexturl=soup.find('a')['href']
|
|
return self.index_to_soup(nexturl, raw=True)
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup('http://www.prasa24.pl/gazeta/gazeta-wroclawska/')
|
|
self.cover_url=soup.find(id='pojemnik').img['src']
|
|
return getattr(self, 'cover_url', self.cover_url)
|