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

Updated Kopalnia Wiedzy

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-09 02:56:25 -06:00
parent 7a97190b79
commit 06960ff7a6
1 changed files with 14 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
recipes/kopalniawiedzy.recipe
View File

@ -1,4 +1,3 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Attis <attis@attis.one.pl>' __copyright__ = '2011, Attis <attis@attis.one.pl>'
__version__ = 'v. 0.1' __version__ = 'v. 0.1'
@ -16,21 +15,21 @@ class KopalniaWiedzy(BasicNewsRecipe):
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
INDEX = u'http://kopalniawiedzy.pl/' INDEX = u'http://kopalniawiedzy.pl/'
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
remove_tags = [{'name':'p', 'attrs': {'class': 'keywords'} }] remove_tags = [{'name':'p', 'attrs': {'class': 'keywords'} }, {'name':'div', 'attrs': {'class':'sexy-bookmarks sexy-bookmarks-bg-caring'}}]
remove_tags_after = dict(attrs={'class':'ad-square'}) remove_tags_after = dict(attrs={'class':'ad-square'})
keep_only_tags = [dict(name="div", attrs={'id':'articleContent'})] keep_only_tags = [dict(name="div", attrs={'id':'articleContent'})]
extra_css = '.topimage {margin-top: 30px}' extra_css = '.topimage {margin-top: 30px}'
preprocess_regexps = [ preprocess_regexps = [
(re.compile(u'<a .* rel="lightboxText" .*><img (.*)></a>'), (re.compile(u'<a .* rel="lightboxText" .*><img (.*)></a>'),
lambda match: '<img class="topimage" ' + match.group(1) + '>' ), lambda match: '<img class="topimage" ' + match.group(1) + '>' ),
(re.compile(u'<br /><br />'), (re.compile(u'<br /><br />'),
lambda match: '<br\/>') lambda match: '<br\/>')
] ]
feeds = [ feeds = [
(u'Biologia', u'http://kopalniawiedzy.pl/wiadomosci_biologia.rss'), (u'Biologia', u'http://kopalniawiedzy.pl/wiadomosci_biologia.rss'),
(u'Medycyna', u'http://kopalniawiedzy.pl/wiadomosci_medycyna.rss'), (u'Medycyna', u'http://kopalniawiedzy.pl/wiadomosci_medycyna.rss'),
@ -39,10 +38,10 @@ class KopalniaWiedzy(BasicNewsRecipe):
(u'Ciekawostki', u'http://kopalniawiedzy.pl/wiadomosci_ciekawostki.rss'), (u'Ciekawostki', u'http://kopalniawiedzy.pl/wiadomosci_ciekawostki.rss'),
(u'Artykuły', u'http://kopalniawiedzy.pl/artykuly.rss') (u'Artykuły', u'http://kopalniawiedzy.pl/artykuly.rss')
] ]
def is_link_wanted(self, url, tag): def is_link_wanted(self, url, tag):
return tag['class'] == 'next' return tag['class'] == 'next'
def remove_beyond(self, tag, next): def remove_beyond(self, tag, next):
while tag is not None and getattr(tag, 'name', None) != 'body': while tag is not None and getattr(tag, 'name', None) != 'body':
after = getattr(tag, next) after = getattr(tag, next)
@ -51,30 +50,30 @@ class KopalniaWiedzy(BasicNewsRecipe):
after.extract() after.extract()
after = ns after = ns
tag = tag.parent tag = tag.parent
def append_page(self, soup, appendtag, position): def append_page(self, soup, appendtag, position):
pager = soup.find('a',attrs={'class':'next'}) pager = soup.find('a',attrs={'class':'next'})
if pager: if pager:
nexturl = self.INDEX + pager['href'] nexturl = self.INDEX + pager['href']
soup2 = self.index_to_soup(nexturl) soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'id':'articleContent'}) texttag = soup2.find('div', attrs={'id':'articleContent'})
tag = texttag.find(attrs={'class':'pages'}) tag = texttag.find(attrs={'class':'pages'})
self.remove_beyond(tag, 'nextSibling') self.remove_beyond(tag, 'nextSibling')
newpos = len(texttag.contents) newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos) self.append_page(soup2,texttag,newpos)
appendtag.insert(position,texttag) appendtag.insert(position,texttag)
def preprocess_html(self, soup): def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
for item in soup.findAll('div',attrs={'class':'pages'}): for item in soup.findAll('div',attrs={'class':'pages'}):
item.extract() item.extract()
for item in soup.findAll('p', attrs={'class':'wykop'}): for item in soup.findAll('p', attrs={'class':'wykop'}):
item.extract() item.extract()
return soup return soup