calibre/recipes/novilist_novine_hr.recipe
2024-03-30 13:03:29 +05:30

96 lines
3.8 KiB
Python

__license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
novine.novilist.hr
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class NoviList_hr(BasicNewsRecipe):
title = 'Novi List'
__author__ = 'Darko Miletic'
description = 'Vijesti iz Hrvatske'
publisher = 'NOVI LIST d.d.'
category = 'Novi list, politika, hrvatski dnevnik, Novine, Hrvatska, Croatia, News, newspaper, Hrvatski,Primorje, dnevni list, Rijeka'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'cp1250'
use_embedded_content = False
language = 'hr'
remove_empty_feeds = True
publication_type = 'newspaper'
needs_subscription = True
masthead_url = 'http://novine.novilist.hr/images/system/novilist-logo.jpg'
index = 'http://novine.novilist.hr/'
extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Geneva,Arial,Helvetica,Swiss,sans1,sans-serif }
img{display:block; margin-bottom: 0.4em; margin-top: 0.4em}
.nadnaslov,.podnaslov{font-size: small; display: block; margin-bottom: 1em}
.naslov{font-size: x-large; color: maroon; font-weight: bold; display: block; margin-bottom: 1em;}
p{display: block}
"""
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
}
keep_only_tags = [
dict(name='td', attrs={'class': ['nadnaslov', 'naslov', 'podnaslov']}),
dict(name='font', attrs={'face': 'Geneva,Arial,Helvetica,Swiss'})
]
remove_tags = [dict(name=['meta', 'link', 'iframe', 'embed', 'object'])]
remove_attributes = ['border', 'lang', 'size', 'face', 'bgcolor']
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open(self.index + 'loginnow.asp')
br.select_form(nr=0)
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
articles = []
count = 0
soup = self.index_to_soup(self.index)
# cover url
for alink in soup.findAll('a'):
if alink['href'].startswith('images/clanci/DOC_'):
self.cover_url = self.index + alink['href']
# feeds
for item in soup.findAll('td', attrs={'class': 'tocrubrika'}):
count = count + 1
if self.test and count > 2:
return articles
aitem = item.a
section = self.tag_to_string(aitem)
feedlink = self.index + aitem['href']
feedpage = self.index_to_soup(feedlink)
self.report_progress(0, _('Fetching feed') + ' %s...' % (section))
inarts = []
for alink in feedpage.findAll('a', attrs={'class': 'naslovlinkdesno'}):
url = self.index + alink['href']
inarts.append({
'title': self.tag_to_string(alink), 'date': strftime(self.timefmt), 'url': url, 'description': ''
})
if self.remove_empty_feeds:
if inarts:
articles.append((section, inarts))
else:
articles.append((section, inarts))
return articles
def print_version(self, url):
return url.replace('?WCI=Rubrike&', '?WCI=Pretrazivac&')