mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
81 lines
2.3 KiB
Python
81 lines
2.3 KiB
Python
#!/usr/bin/env python
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2011, Miroslav Vasko zemiak@gmail.com'
|
|
|
|
'''
|
|
.tyzden, a weekly news magazine (a week old issue)
|
|
'''
|
|
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
|
|
|
|
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]
|
|
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'})]
|
|
|
|
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/')):
|
|
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'),
|
|
}
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
for title, soup in self.find_sections():
|
|
feeds.append((title, list(self.find_articles(soup))))
|
|
|
|
return feeds
|