calibre/recipes/kopalniawiedzy.recipe

83 lines
3.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2011 Attis <attis@attis.one.pl>, 2012 Tomasz Długosz <tomek3d@gmail.com>'
__version__ = 'v. 0.1'
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class KopalniaWiedzy(BasicNewsRecipe):
title = u'Kopalnia Wiedzy'
publisher = u'Kopalnia Wiedzy'
description = u'Ciekawostki ze świata nauki i techniki'
encoding = 'utf-8'
__author__ = 'Attis & Tomasz Długosz'
language = 'pl'
oldest_article = 7
max_articles_per_feed = 100
INDEX = u'http://kopalniawiedzy.pl/'
remove_javascript = True
remove_empty_feeds = True
no_stylesheets = True
remove_tags = [{'name': 'p', 'attrs': {'class': 'keywords'}}, {'name': 'div', 'attrs': {'class': 'sexy-bookmarks sexy-bookmarks-bg-caring'}},
{'name': 'div', 'attrs': {'class': 'article-time-and-cat'}}, {'name': 'p', 'attrs': {'class': 'tags'}}]
remove_tags_after = dict(attrs={'class': 'ad-square'})
keep_only_tags = [
dict(name="div", attrs={'class': 'article-text text-small'})]
extra_css = '.topimage {margin-top: 30px}'
preprocess_regexps = [
(re.compile(u'<a .* rel="lightboxText" .*><img (.*)></a>'),
lambda match: '<img class="topimage" ' + match.group(1) + '>'),
(re.compile(u'<br /><br />'),
lambda match: '<br/>')
]
feeds = [
(u'Biologia', u'http://kopalniawiedzy.pl/wiadomosci_biologia.rss'),
(u'Medycyna', u'http://kopalniawiedzy.pl/wiadomosci_medycyna.rss'),
(u'Psychologia', u'http://kopalniawiedzy.pl/wiadomosci_psychologia.rss'),
(u'Technologie', u'http://kopalniawiedzy.pl/wiadomosci_technologie.rss'),
(u'Ciekawostki', u'http://kopalniawiedzy.pl/wiadomosci_ciekawostki.rss'),
(u'Artykuły', u'http://kopalniawiedzy.pl/artykuly.rss')
]
def is_link_wanted(self, url, tag):
return ''.join(tag['class']) == 'next'
def remove_beyond(self, tag, next):
while tag is not None and getattr(tag, 'name', None) != 'body':
after = getattr(tag, next)
while after is not None:
ns = getattr(tag, next)
after.extract()
after = ns
tag = tag.parent
def append_page(self, soup, appendtag, position):
pager = soup.find('a', attrs={'class': 'next'})
if pager:
nexturl = self.INDEX + pager['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'id': 'articleContent'})
tag = texttag.find(attrs={'class': 'pages'})
self.remove_beyond(tag, 'nextSibling')
newpos = len(texttag.contents)
self.append_page(soup2, texttag, newpos)
appendtag.insert(position, texttag)
def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3)
for item in soup.findAll('div', attrs={'class': 'pages'}):
item.extract()
for item in soup.findAll('p', attrs={'class': 'wykop'}):
item.extract()
return soup