mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
70 lines
2.6 KiB
Python
70 lines
2.6 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
|
|
'''
|
|
republika.co.yu
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Republika(BasicNewsRecipe):
|
|
title = 'Republika'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Glasilo gradjanskog samooslobadjanja. Protiv stihije straha, mrznje i nasilja'
|
|
publisher = ' Zadruga Res Publica'
|
|
category = 'news, politics, Serbia'
|
|
language = 'sr'
|
|
|
|
lang = 'sr-Latn-RS'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'cp1250'
|
|
use_embedded_content = False
|
|
INDEX = u'http://www.republika.co.yu/'
|
|
extra_css = ' @font-face {font-family: "serif1"; src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif} .naslov{font-size: x-large; font-weight: bold} .autor{font-size: small; font-weight: bold} ' # noqa
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True
|
|
}
|
|
|
|
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
|
|
|
|
keep_only_tags = [dict(attrs={'class': 'naslov'}), dict(attrs={'class': 'text1'})
|
|
]
|
|
|
|
remove_tags = [dict(name=['object', 'link', 'iframe', 'base', 'img'])]
|
|
|
|
feeds = [(u'Svi clanci', INDEX)]
|
|
|
|
def preprocess_html(self, soup):
|
|
attribs = ['style', 'font', 'valign', 'colspan', 'width', 'height', 'rowspan', 'summary', 'align', 'cellspacing', 'cellpadding', 'frames', 'rules', 'border' ] # noqa
|
|
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
|
|
item.name = 'div'
|
|
for attrib in attribs:
|
|
item[attrib] = ''
|
|
del item[attrib]
|
|
return soup
|
|
|
|
def parse_index(self):
|
|
totalfeeds = []
|
|
lfeeds = self.get_feeds()
|
|
for feedobj in lfeeds:
|
|
feedtitle, feedurl = feedobj
|
|
self.report_progress(0, _('Fetching feed') + ' %s...' %
|
|
(feedtitle if feedtitle else feedurl))
|
|
articles = []
|
|
soup = self.index_to_soup(feedurl)
|
|
for item in soup.findAll('a', attrs={'class': 'naslovLink'}):
|
|
url = item['href']
|
|
title = self.tag_to_string(item)
|
|
articles.append({
|
|
'title': title, 'date': '', 'url': url, 'description': ''
|
|
})
|
|
totalfeeds.append((feedtitle, articles))
|
|
return totalfeeds
|