Updated .týždeň recipe to work with current version of the site.

This commit is contained in:
Martin Račák 2014-10-26 22:52:30 +01:00
parent 6dcbd4e4d8
commit 525bb17d88

View File

@ -1,52 +1,70 @@
#!/usr/bin/env python
#!/usr/bin/env python
#
# 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__ = '2011, Miroslav Vasko zemiak@gmail.com'
__copyright__ = '2014 Martin Račák <martin.racak@riseup.net>, 2011 Miroslav Vasko <zemiak@gmail.com>'
'''
.tyzden, a weekly news magazine (a week old issue)
.týždeň - iný pohľad na spoločnosť
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date
import re
class TyzdenRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'zemiak'
language = 'sk'
version = 1
class Tyzden(BasicNewsRecipe):
title = '.týždeň'
__author__ = '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
publisher = u'www.tyzden.sk'
category = u'Magazine'
description = u'A conservative weekly magazine. The latest free issue'
today = date.today()
iso = today.isocalendar()
year = iso[0]
today = date.today()
iso = today.isocalendar()
year = iso[0]
weeknum = iso[1]
if (weeknum > 1):
weeknum -= 1
title = u'tyzden'
base_url_path = 'http://www.tyzden.sk/casopis/' + str(year) + '/' + str(weeknum)
base_url = base_url_path + '.html'
oldest_article = 20
max_articles_per_feed = 100
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
keep_only_tags = []
keep_only_tags.append(dict(name = 'h1'))
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
@ -62,14 +80,14 @@ class TyzdenRecipe(BasicNewsRecipe):
def find_articles(self, soup):
for art in soup.findAllNext('a'):
if (not art['href'].startswith('casopis/')):
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, 'description':title,
'date' : strftime('%a, %d %b'),
'title': title, 'url':self.base_url_path + '/' + url,
'date' : strftime(' %a, %d %b'),
}
def parse_index(self):