Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Delete kurier_galicyjski.recipe

Browse Source
This commit is contained in:
Jony 2020-03-15 14:20:06 +01:00 committed by GitHub
parent eb7908e77c
commit 1b842be5c6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 74 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

74
recipes/kurier_galicyjski.recipe
View File

@ -1,74 +0,0 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup as bs, Comment
class KurierGalicyjski(BasicNewsRecipe):
title = u'Kurier Galicyjski'
__author__ = 'fenuks'
description = u'Kurier Galicyjski - największa gazeta dla Polaków na Ukrainie. Bieżące wydarzenia z życia polskiej mniejszości, historia, kultura, polityka, reportaże.' # noqa
category = 'news'
language = 'pl'
cover_url = 'http://www.duszki.pl/Kurier_galicyjski_bis2_small.gif'
oldest_article = 7
max_articles_per_feed = 100
remove_empty_feeds = True
no_stylesheets = True
keep_only_tags = [dict(attrs={'class': 'item-page'})]
remove_tags = [dict(attrs={'class': 'pagenav'}), dict(attrs={
'style': 'border-top-width: thin; border-top-style: dashed; border-top-color: #CCC; border-bottom-width: thin; border-bottom-style: dashed; border-bottom-color: #CCC; padding-top:5px; padding-bottom:5px; text-align:right; margin-top:10px; height:20px;'})] # noqa
feeds = [
(u'Wydarzenia', u'http://kuriergalicyjski.com/index.php/wydarzenia?format=feed&type=atom'),
(u'Publicystyka', u'http://kuriergalicyjski.com/index.php/niezwykle-historie?format=feed&type=atom'),
(u'Reporta\u017ce', u'http://kuriergalicyjski.com/index.php/report?format=feed&type=atom'),
(u'Rozmowy Kuriera', u'http://kuriergalicyjski.com/index.php/kuriera?format=feed&type=atom'),
(u'Przegl\u0105d prasy', u'http://kuriergalicyjski.com/index.php/2012-01-05-14-08-55?format=feed&type=atom'),
(u'Kultura', u'http://kuriergalicyjski.com/index.php/2011-12-02-14-26-39?format=feed&type=atom'),
(u'Zabytki', u'http://kuriergalicyjski.com/index.php/2011-12-02-14-27-32?format=feed&type=atom'),
(u'Polska-Ukraina', u'http://kuriergalicyjski.com/index.php/pol-ua?format=feed&type=atom'),
(u'Polacy i Ukrai\u0144cy', u'http://kuriergalicyjski.com/index.php/polacy-i-ukr?format=feed&type=atom'),
(u'Niezwyk\u0142e historie', u'http://kuriergalicyjski.com/index.php/niezwykle-historie?format=feed&type=atom'),
(u'Polemiki', u'http://kuriergalicyjski.com/index.php/polemiki?format=feed&type=atom')]
def append_page(self, soup, appendtag):
pager = soup.find(id='article-index')
if pager:
pager = pager.findAll('a')[1:]
if pager:
for a in pager:
nexturl = 'http://www.kuriergalicyjski.com' + a['href']
soup2 = self.index_to_soup(nexturl)
pagetext = soup2.find(attrs={'class': 'item-page'})
if pagetext.h2:
pagetext.h2.extract()
r = pagetext.find(attrs={'class': 'article-info'})
if r:
r.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
pos = len(appendtag.contents)
for r in appendtag.findAll(id='article-index'):
r.extract()
for r in appendtag.findAll(attrs={'class': 'pagenavcounter'}):
r.extract()
for r in appendtag.findAll(attrs={'class': 'pagination'}):
r.extract()
for r in appendtag.findAll(attrs={'class': 'pagenav'}):
r.extract()
for r in appendtag.findAll(attrs={'style': 'border-top-width: thin; border-top-style: dashed; border-top-color: #CCC; border-bottom-width: thin; border-bottom-style: dashed; border-bottom-color: #CCC; padding-top:5px; padding-bottom:5px; text-align:right; margin-top:10px; height:20px;'}): # noqa
r.extract()
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)
for r in soup.findAll(style=True):
del r['style']
for img in soup.findAll(attrs={'class': 'easy_img_caption smartresize'}):
img.insert(len(img.contents) - 1, bs('<br />'))
img.insert(len(img.contents), bs('<br /><br />'))
for a in soup.findAll('a', href=True):
if a['href'].startswith('/'):
a['href'] = 'http://kuriergalicyjski.com' + a['href']
return soup