mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
60 lines
1.9 KiB
Python
60 lines
1.9 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, matek09, matek09@gmail.com'
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
class Histmag(BasicNewsRecipe):
|
|
|
|
title = u'Histmag'
|
|
__author__ = 'matek09'
|
|
description = u"Artykuly historyczne i publicystyczne"
|
|
encoding = 'utf-8'
|
|
no_stylesheets = True
|
|
language = 'pl'
|
|
remove_javascript = True
|
|
#max_articles_per_feed = 1
|
|
remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'article'}))
|
|
remove_tags_after = dict(dict(name = 'h2', attrs = {'class' : 'komentarze'}))
|
|
#keep_only_tags =[]
|
|
#keep_only_tags.append(dict(name = 'h2'))
|
|
#keep_only_tags.append(dict(name = 'p'))
|
|
|
|
remove_tags =[]
|
|
remove_tags.append(dict(name = 'p', attrs = {'class' : 'podpis'}))
|
|
remove_tags.append(dict(name = 'h2', attrs = {'class' : 'komentarze'}))
|
|
remove_tags.append(dict(name = 'img', attrs = {'src' : 'style/buttons/wesprzyjnas-1.jpg'}))
|
|
|
|
preprocess_regexps = [(re.compile(r'</span>'), lambda match: '</span><br><br>'),
|
|
(re.compile(r'<span>'), lambda match: '<br><br><span>')]
|
|
extra_css = '''
|
|
.left {font-size: x-small}
|
|
.right {font-size: x-small}
|
|
'''
|
|
|
|
def find_articles(self, soup):
|
|
articles = []
|
|
for div in soup.findAll('div', attrs={'class' : 'text'}):
|
|
articles.append({
|
|
'title' : self.tag_to_string(div.h3.a),
|
|
'url' : 'http://www.histmag.org/' + div.h3.a['href'],
|
|
'date' : self.tag_to_string(div.next('p')).split('|')[0],
|
|
'description' : self.tag_to_string(div.next('p', podpis=False)),
|
|
})
|
|
return articles
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('http://histmag.org/?arc=4&dx=0')
|
|
feeds = []
|
|
feeds.append((u"Artykuly historyczne", self.find_articles(soup)))
|
|
soup = self.index_to_soup('http://histmag.org/?arc=5&dx=0')
|
|
feeds.append((u"Artykuly publicystyczne", self.find_articles(soup)))
|
|
soup = self.index_to_soup('http://histmag.org/?arc=1&dx=0')
|
|
feeds.append((u"Wydarzenia", self.find_articles(soup)))
|
|
|
|
return feeds
|
|
|
|
|