mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
44 lines
1.9 KiB
Plaintext
44 lines
1.9 KiB
Plaintext
from calibre.ptempfile import PersistentTemporaryFile
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1276930924(BasicNewsRecipe):
|
|
title = u'Maximum PC'
|
|
__author__ = 'rty'
|
|
description = 'Maximum PC'
|
|
publisher = 'http://www.maximumpc.com'
|
|
category = 'news, computer, technology'
|
|
language = 'en'
|
|
oldest_article = 30
|
|
max_articles_per_feed = 100
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
language = 'en'
|
|
temp_files = []
|
|
articles_are_obfuscated = True
|
|
feeds = [(u'News', u'http://www.maximumpc.com/articles/4/feed'),
|
|
(u'Reviews', u'http://www.maximumpc.com/articles/40/feed'),
|
|
(u'Editors Blog', u'http://www.maximumpc.com/articles/6/feed'),
|
|
(u'How-to', u'http://www.maximumpc.com/articles/32/feed'),
|
|
(u'Features', u'http://www.maximumpc.com/articles/31/feed'),
|
|
(u'From the Magazine', u'http://www.maximumpc.com/articles/72/feed')
|
|
]
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class':['print-title','article_body']}),
|
|
]
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class':'comments-tags-actions'}),
|
|
]
|
|
remove_tags_before = dict(name='div', attrs={'class':'print-title'})
|
|
remove_tags_after = dict(name='div', attrs={'class':'meta-content'})
|
|
|
|
def get_obfuscated_article(self, url):
|
|
br = self.get_browser()
|
|
br.open(url)
|
|
response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
|
|
html = response.read()
|
|
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
|
self.temp_files[-1].write(html)
|
|
self.temp_files[-1].close()
|
|
return self.temp_files[-1].name
|