mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
73 lines
2.7 KiB
Plaintext
73 lines
2.7 KiB
Plaintext
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.pecat.co.rs
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Pecat_rs(BasicNewsRecipe):
|
|
title = 'Pecat'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Internet portal slobodne Srbije'
|
|
oldest_article = 15
|
|
max_articles_per_feed = 100
|
|
language = 'sr'
|
|
encoding = 'utf-8'
|
|
no_stylesheets = True
|
|
use_embedded_content = True
|
|
masthead_url = 'http://www.pecat.co.rs/wp-content/themes/zenko-v1/images/logo.jpg'
|
|
publication_type = 'magazine'
|
|
extra_css = """
|
|
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
|
|
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
|
|
body{font-family: Arial,Helvetica,sans1,sans-serif}
|
|
img{display: block; margin-bottom: 1em; margin-top: 1em}
|
|
p{display: block; margin-bottom: 1em; margin-top: 1em}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : 'politika, Srbija'
|
|
, 'publisher': 'Pecat'
|
|
, 'language' : language
|
|
}
|
|
|
|
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
|
|
|
|
feeds = [(u'Clanci', u'http://www.pecat.co.rs/feed/')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll('a'):
|
|
limg = item.find('img')
|
|
if item.string is not None:
|
|
str = item.string
|
|
item.replaceWith(str)
|
|
else:
|
|
if limg:
|
|
limg.extract()
|
|
item.replaceWith(limg)
|
|
else:
|
|
str = self.tag_to_string(item)
|
|
item.replaceWith(str)
|
|
for item in soup.findAll('img'):
|
|
dad = item.findParent('p')
|
|
if dad:
|
|
mydad = dad.parent
|
|
myIndex = mydad.contents.index(dad)
|
|
item.extract()
|
|
mydad.insert(myIndex,item)
|
|
for item in soup.findAll('strong'):
|
|
dad = item.findParent('p')
|
|
if dad:
|
|
mydad = dad.parent
|
|
myIndex = mydad.contents.index(dad)
|
|
item.extract()
|
|
item.name='h4'
|
|
mydad.insert(myIndex,item)
|
|
return soup
|