mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-02-01 16:43:32 -05:00
100 lines
3.5 KiB
Python
100 lines
3.5 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
#
|
|
# Copyright 2014 Martin Račák <martin.racak@riseup.net>
|
|
# Copyright 2011 Miroslav Vasko <zemiak@gmail.com>
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2014 Martin Račák <martin.racak@riseup.net>, 2011 Miroslav Vasko <zemiak@gmail.com>'
|
|
|
|
'''
|
|
.týždeň - iný pohľad na spoločnosť
|
|
'''
|
|
|
|
import re
|
|
from calibre import strftime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from datetime import date
|
|
|
|
class Tyzden(BasicNewsRecipe):
|
|
title = u'týždeň'
|
|
__author__ = u'Martin Račák, zemiak'
|
|
description = 'A conservative weekly magazine.'
|
|
publisher = 'www.tyzden.sk'
|
|
publication_type = 'magazine'
|
|
language = 'sk'
|
|
needs_subscription = 'optional'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
if self.username is not None and self.password is not None:
|
|
br.open('http://www.tyzden.sk/prihlasenie.html')
|
|
br.select_form(nr=1)
|
|
br['user'] = self.username
|
|
br['pass'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
today = date.today()
|
|
iso = today.isocalendar()
|
|
year = iso[0]
|
|
weeknum = iso[1]
|
|
|
|
base_url_path = 'http://www.tyzden.sk/casopis/' + str(year) + '/' + str(weeknum)
|
|
base_url = base_url_path + '.html'
|
|
|
|
keep_only_tags = []
|
|
keep_only_tags.append(dict(name='div', attrs={'class': 'text_area top_nofoto'}))
|
|
keep_only_tags.append(dict(name='div', attrs={'class': 'text_block'}))
|
|
|
|
remove_tags_after = [dict(name='div', attrs={'class': 'text_block'})]
|
|
|
|
extra_css = '.top_nofoto h1 { text-align: left; font-size: 1.7em; }'
|
|
|
|
def find_sections(self):
|
|
soup = self.index_to_soup(self.base_url)
|
|
# find cover pic
|
|
imgdiv = soup.find('div', attrs={'class': 'foto'})
|
|
if imgdiv is not None:
|
|
img = imgdiv.find('img')
|
|
if img is not None:
|
|
self.cover_url = 'http://www.tyzden.sk/' + img['src']
|
|
# end find cover pic
|
|
|
|
for s in soup.findAll('a', attrs={'href': re.compile(r'rubrika/.*')}):
|
|
yield (self.tag_to_string(s), s)
|
|
|
|
def find_articles(self, soup):
|
|
for art in soup.findAllNext('a'):
|
|
if (not art['href'].startswith('casopis/' + str(self.year) + '/' + str(self.weeknum) + '/')):
|
|
break
|
|
|
|
url = art['href']
|
|
title = self.tag_to_string(art)
|
|
yield {
|
|
'title': title, 'url':self.base_url_path + '/' + url,
|
|
'date' : strftime(' %a, %d %b'),
|
|
}
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
for title, soup in self.find_sections():
|
|
feeds.append((title, list(self.find_articles(soup))))
|
|
|
|
return feeds
|