calibre/recipes/linux_journal.recipe
Tomasz Długosz ed815e8396 various fixes
2013-03-21 00:56:45 +01:00

41 lines
2.7 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class LinuxJournal(BasicNewsRecipe):
title = u'Linux Journal'
__author__ = 'fenuks'
description = u'The monthly magazine of the Linux community, promoting the use of Linux worldwide.'
cover_url = 'http://www.linuxjournal.com/files/linuxjournal.com/ufiles/logo-lj.jpg'
category = 'IT, Linux'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
keep_only_tags=[dict(id='content-inner')]
remove_tags_after= dict(attrs={'class':'user-signature clear-block'})
remove_tags=[dict(attrs={'class':['user-signature clear-block', 'breadcrumb', 'terms terms-inline']})]
feeds = [(u'Front Page', u'http://feeds.feedburner.com/linuxjournalcom'), (u'News', u'http://feeds.feedburner.com/LinuxJournal-BreakingNews'), (u'Blogs', u'http://www.linuxjournal.com/blog/feed'), (u'Audio/Video', u'http://www.linuxjournal.com/taxonomy/term/28/0/feed'), (u'Community', u'http://www.linuxjournal.com/taxonomy/term/18/0/feed'), (u'Education', u'http://www.linuxjournal.com/taxonomy/term/25/0/feed'), (u'Embedded', u'http://www.linuxjournal.com/taxonomy/term/27/0/feed'), (u'Hardware', u'http://www.linuxjournal.com/taxonomy/term/23/0/feed'), (u'HOWTOs', u'http://www.linuxjournal.com/taxonomy/term/19/0/feed'), (u'International', u'http://www.linuxjournal.com/taxonomy/term/30/0/feed'), (u'Security', u'http://www.linuxjournal.com/taxonomy/term/31/0/feed'), (u'Software', u'http://www.linuxjournal.com/taxonomy/term/17/0/feed'), (u'Sysadmin', u'http://www.linuxjournal.com/taxonomy/term/21/0/feed'), (u'Webmaster', u'http://www.linuxjournal.com/taxonomy/term/24/0/feed')]
def append_page(self, soup, appendtag):
next = appendtag.find('li', attrs={'class':'pager-next'})
while next:
nexturl = next.a['href']
appendtag.find('div', attrs={'class':'links'}).extract()
soup2 = self.index_to_soup('http://www.linuxjournal.com'+ nexturl)
pagetext = soup2.find(attrs={'class':'node-inner'}).find(attrs={'class':'content'})
next = appendtag.find('li', attrs={'class':'pager-next'})
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
tag = appendtag.find('div', attrs={'class':'links'})
if tag:
tag.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup