calibre/recipes/echo_dnia.recipe
2018-09-10 12:11:29 +05:30

87 lines
4.3 KiB
Plaintext

import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class EchoDnia(BasicNewsRecipe):
title = u'Echo Dnia'
__author__ = 'fenuks'
description = u'Echo Dnia - portal regionalny świętokrzyskiego radomskiego i podkarpackiego. Najnowsze wiadomości z Twojego regionu, galerie, video, mp3.'
category = 'newspaper'
language = 'pl'
encoding = 'iso-8859-2'
extra_css = 'ul {list-style: none; padding:0; margin:0;}'
INDEX = 'http://www.echodnia.eu'
masthead_url = INDEX + '/images/top_logo.png'
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(u'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(u'Przeczytaj także:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''), # noqa
(re.compile(u'Przeczytaj również:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Zobacz też:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: '')] # noqa
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', 'articleZoomText']),
dict(attrs={'class': 'articleFunctions'})]
feeds = [(u'Wszystkie', u'http://www.echodnia.eu/rss.xml'),
(u'Świętokrzyskie', u'http://www.echodnia.eu/swietokrzyskie.xml'),
(u'Radomskie', u'http://www.echodnia.eu/radomskie.xml'),
(u'Podkarpackie', u'http://www.echodnia.eu/podkarpackie.xml'),
(u'Sport \u015bwi\u0119tokrzyski',
u'http://www.echodnia.eu/sport_swi.xml'),
(u'Sport radomski', u'http://www.echodnia.eu/sport_rad.xml'),
(u'Sport podkarpacki', u'http://www.echodnia.eu/sport_pod.xml'),
(u'Pi\u0142ka no\u017cna', u'http://www.echodnia.eu/pilka.xml'),
(u'Praca', u'http://www.echodnia.eu/praca.xml'),
(u'Dom', u'http://www.echodnia.eu/dom.xml'),
(u'Auto', u'http://www.echodnia.eu/auto.xml'),
(u'Zdrowie', u'http://www.echodnia.eu/zdrowie.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('&nbsp;', ''))
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