mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
77 lines
2.7 KiB
Python
77 lines
2.7 KiB
Python
#!/usr/bin/env python2
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
|
|
'''
|
|
dnevniavaz.ba
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
|
|
|
|
def new_tag(soup, name, attrs=()):
|
|
impl = getattr(soup, 'new_tag', None)
|
|
if impl is not None:
|
|
return impl(name, attrs=dict(attrs))
|
|
return Tag(soup, name, attrs=attrs or None)
|
|
|
|
|
|
class DnevniAvaz(BasicNewsRecipe):
|
|
title = 'Dnevni Avaz'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Latest news from Bosnia'
|
|
publisher = 'Dnevni Avaz'
|
|
category = 'news, politics, Bosnia and Herzegovina'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
remove_javascript = True
|
|
cover_url = 'http://www.dnevniavaz.ba/img/logo.gif'
|
|
lang = 'bs-BA'
|
|
language = 'bs'
|
|
|
|
direction = 'ltr'
|
|
|
|
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}' # 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(name='div', attrs={'id': [
|
|
'fullarticle-title', 'fullarticle-leading', 'fullarticle-date', 'fullarticle-text', 'articleauthor']})]
|
|
|
|
remove_tags = [dict(name=['object', 'link', 'base'])]
|
|
|
|
feeds = [
|
|
(u'Najnovije', u'http://www.dnevniavaz.ba/rss/novo'), (u'Najpopularnije',
|
|
u'http://www.dnevniavaz.ba/rss/popularno')
|
|
]
|
|
|
|
def replace_tagname(self, soup, tagname, tagid, newtagname):
|
|
headtag = soup.find(tagname, attrs={'id': tagid})
|
|
if headtag:
|
|
headtag.name = newtagname
|
|
return
|
|
|
|
def preprocess_html(self, soup):
|
|
soup.html['xml:lang'] = self.lang
|
|
soup.html['lang'] = self.lang
|
|
mlang = new_tag(soup, 'meta', [
|
|
("http-equiv", "Content-Language"), ("content", self.lang)])
|
|
mcharset = new_tag(soup, 'meta', [
|
|
("http-equiv", "Content-Type"), ("content", "text/html; charset=UTF-8")])
|
|
soup.head.insert(0, mlang)
|
|
soup.head.insert(1, mcharset)
|
|
self.replace_tagname(soup, 'div', 'fullarticle-title', 'h1')
|
|
self.replace_tagname(soup, 'div', 'fullarticle-leading', 'h3')
|
|
self.replace_tagname(soup, 'div', 'fullarticle-date', 'h5')
|
|
return self.adeify_images(soup)
|