Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update tyzden

Browse Source 
Merge branch 'master' of https://github.com/rakyi/calibre
This commit is contained in:
Kovid Goyal 2015-01-07 21:26:28 +05:30
commit 6a891948d3
1 changed files with 20 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
recipes/tyzden.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
#
# Copyright 2014 Martin Račák <martin.racak@riseup.net>
# Copyright 2014 - 2015 Martin Račák <rakyi@riseup.net>
# Copyright 2011 Miroslav Vasko <zemiak@gmail.com>
#
# This program is free software: you can redistribute it and/or modify
@ -18,7 +18,7 @@
# 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>'
__copyright__ = '2014 - 2015 Martin Račák <martin.racak@riseup.net>, 2011 Miroslav Vasko <zemiak@gmail.com>'
'''
.týždeň - iný pohľad na spoločnosť
@ -27,7 +27,6 @@ __copyright__ = '2014 Martin Račák <martin.racak@riseup.net>, 2011 Miroslav Va
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date
class Tyzden(BasicNewsRecipe):
title = u'týždeň'
@ -50,50 +49,40 @@ class Tyzden(BasicNewsRecipe):
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'
base_url = 'http://www.tyzden.sk/casopis.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')
# Use only the impotant part of page
content = soup.find('div', 'top')
content.extract()
# Find cover pic
img = content.find('div', 'foto').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)
for section in content.findAll('a', {'href': re.compile(r'rubrika/.*')}):
yield (self.tag_to_string(section), section)
def find_articles(self, soup):
for art in soup.findAllNext('a'):
if (not art['href'].startswith('casopis/' + str(self.year) + '/' + str(self.weeknum) + '/')):
for article in soup.findAllNext('a'):
if (not article['href'].startswith('casopis/')):
break
url = art['href']
title = self.tag_to_string(art)
yield {
'title': title, 'url':self.base_url_path + '/' + url,
'title': self.tag_to_string(article),
'url': self.base_url + '/' + article['href'],
'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))))
for title, section in self.find_sections():
feeds.append((title, list(self.find_articles(section))))
return feeds