calibre/recipes/vreme.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

86 lines
3.4 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
vreme.com
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Vreme(BasicNewsRecipe):
title = 'Vreme'
__author__ = 'Darko Miletic'
description = 'Politicki Nedeljnik Srbije'
publisher = 'NP Vreme d.o.o.'
category = 'news, politics, Serbia'
delay = 1
no_stylesheets = True
needs_subscription = True
INDEX = 'http://www.vreme.com'
LOGIN = 'http://www.vreme.com/account/login.php?url=%2F'
use_embedded_content = False
encoding = 'utf-8'
language = 'sr'
publication_type = 'magazine'
masthead_url = 'http://www.vreme.com/g/vreme-logo.gif'
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: serif1, serif}
.article_description{font-family: serif1, serif}
.column-heading2{font-family: sans1, sans-serif; font-size: large}
.column-heading1{font-family: sans1, sans-serif; font-size: x-large}
.column-normal{font-family: sans1, sans-serif; font-size: medium}
.large{font-family: sans1, sans-serif; font-size: large}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags_before = dict(attrs={'class': 'toc-heading'})
remove_tags_after = dict(attrs={'class': 'footer'})
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open(self.LOGIN)
br.select_form(name='f')
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div', attrs={'id': 'najava'})
if cover_item:
self.cover_url = self.INDEX + cover_item.img['src']
for item in soup.findAll(['h3', 'h4']):
description = u''
title_prefix = u''
feed_link = item.find('a', href=True)
if feed_link and (feed_link['href'].startswith('cms/view.php') or feed_link['href'].startswith('/cms/view.php')):
if feed_link['href'].startswith('cms/view.php'):
url = self.INDEX + '/' + feed_link['href']
else:
url = self.INDEX + feed_link['href']
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title': title, 'date': date, 'url': url, 'description': description
})
return [('Nedeljnik Vreme', articles)]
remove_tags = [
dict(name=['object', 'link']), dict(
name='table', attrs={'xclass': 'image'})
]
def print_version(self, url):
return url + '&print=yes'