calibre/recipes/wired.recipe
Kovid Goyal f554c663fe ...
2012-05-17 21:58:21 +05:30

114 lines
4.8 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2012, mkydgr'
'''
www.wired.com
based on the (broken) built-in recipe by Darko Miletic <darko.miletic at gmail.com>
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Wired(BasicNewsRecipe):
title = 'Wired Magazine'
__author__ = 'mkydgr'
description = 'Technology News'
publisher = 'Conde Nast Digital'
category = ''
oldest_article = 500
delay = 1
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
masthead_url = 'http://www.wired.com/images/home/wired_logo.gif'
language = 'en'
publication_type = 'magazine'
extra_css = ' body{font-family: Arial,Verdana,sans-serif} .entryDescription li {display: inline; list-style-type: none} '
index = 'http://www.wired.com/magazine'
departments = ['features','start','test','play','found', 'reviews']
preprocess_regexps = [(re.compile(r'<meta name="Title".*<title>', re.DOTALL|re.IGNORECASE),lambda match: '<title>')]
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
remove_tags_after = dict(name='div', attrs={'class':'tweetmeme_button'})
remove_tags = [
dict(name=['object','embed','iframe','link'])
,dict(name='div', attrs={'class':['podcast_storyboard','tweetmeme_button']})
,dict(attrs={'id':'ff_bottom_nav'})
,dict(name='a',attrs={'href':'http://www.wired.com/app'})
]
remove_attributes = ['height','width']
def parse_index(self):
totalfeeds = []
soup = self.index_to_soup(self.index)
#department feeds
depts = soup.find('div',attrs={'id':'department-posts'})
if depts:
for ditem in self.departments:
darticles = []
department = depts.find('h3',attrs={'id':'department-'+ditem})
if department:
#print '\n###### Found department %s ########'%(ditem)
el = department.next
while el and (el.__class__.__name__ == 'NavigableString' or el.name != 'h3'):
if el.__class__.__name__ != 'NavigableString':
#print '\t ... element',el.name
if el.name == 'ul':
for artitem in el.findAll('li'):
#print '\t\t ... article',repr(artitem)
feed_link = artitem.find('a')
#print '\t\t\t ... link',repr(feed_link)
if feed_link and feed_link.has_key('href'):
url = self.makeurl(feed_link['href'])
title = self.tag_to_string(feed_link)
date = strftime(self.timefmt)
#print '\t\t ... found "%s" %s'%(title,url)
darticles.append({
'title' :title
,'date' :date
,'url' :url
,'description':''
})
el = None
else:
el = el.next
totalfeeds.append((ditem.capitalize(), darticles))
return totalfeeds
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.index)
cover_item = soup.find('div',attrs={'class':'spread-image'})
if cover_item:
cover_url = self.makeurl(cover_item.a.img['src'])
return cover_url
def print_version(self, url):
return url.rstrip('/') + '/all/1'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def makeurl(self, addr):
if addr[:4] != 'http' : addr='http://www.wired.com' + addr
while addr[-2:] == '//' : addr=addr[:-1]
return addr