mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
80 lines
2.8 KiB
Python
80 lines
2.8 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
tomshardware.com/us
|
|
'''
|
|
|
|
import urllib
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
class Tomshardware(BasicNewsRecipe):
|
|
title = "Tom's Hardware US"
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Hardware reviews and News'
|
|
publisher = "Tom's Hardware"
|
|
category = 'news, IT, hardware, USA'
|
|
no_stylesheets = True
|
|
needs_subscription = True
|
|
language = 'en'
|
|
|
|
INDEX = 'http://www.tomshardware.com'
|
|
LOGIN = INDEX + '/membres/'
|
|
remove_javascript = True
|
|
use_embedded_content= False
|
|
|
|
html2lrf_options = [
|
|
'--comment', description
|
|
, '--category', category
|
|
, '--publisher', publisher
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
br.open(self.INDEX+'/us/')
|
|
if self.username is not None and self.password is not None:
|
|
data = urllib.urlencode({ 'action':'login_action'
|
|
,'r':self.INDEX+'/us/'
|
|
,'login':self.username
|
|
,'mdp':self.password
|
|
})
|
|
br.open(self.LOGIN,data)
|
|
return br
|
|
|
|
remove_tags = [
|
|
dict(name='div' , attrs={'id':'header' })
|
|
,dict(name='object')
|
|
]
|
|
|
|
feeds = [
|
|
(u'Latest Articles', u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-2.xml' )
|
|
,(u'Latest News' , u'http://www.tomshardware.com/feeds/atom/tom-s-hardware-us,18-1.xml')
|
|
]
|
|
|
|
def print_version(self, url):
|
|
main, sep, rest = url.rpartition('.html')
|
|
rmain, rsep, article_id = main.rpartition(',')
|
|
tmain, tsep, trest = rmain.rpartition('/reviews/')
|
|
rind = 'http://www.tomshardware.com/news_print.php?p1='
|
|
if tsep:
|
|
rind = 'http://www.tomshardware.com/review_print.php?p1='
|
|
return rind + article_id
|
|
|
|
def cleanup_image_tags(self,soup):
|
|
for item in soup.findAll('img'):
|
|
for attrib in ['height','width','border','align']:
|
|
if item.has_key(attrib):
|
|
del item[attrib]
|
|
return soup
|
|
|
|
def preprocess_html(self, soup):
|
|
del(soup.body['onload'])
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for it in soup.findAll('span'):
|
|
it.name="div"
|
|
return self.cleanup_image_tags(soup)
|