mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
108 lines
4.5 KiB
Plaintext
108 lines
4.5 KiB
Plaintext
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2013, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.wired.com
|
|
'''
|
|
|
|
import re
|
|
from calibre import strftime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Wired(BasicNewsRecipe):
|
|
title = 'Wired Magazine'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Gaming news'
|
|
publisher = 'Conde Nast Digital'
|
|
category = 'news, games, IT, gadgets'
|
|
oldest_article = 32
|
|
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 = """
|
|
h1, .entry-header{font-family: brandon-grotesque,anchor-web,Helvetica,Arial,sans-serif}
|
|
.entry-header{display: block;}
|
|
.entry-header ul{ list-style-type:disc;}
|
|
.author, .entryDate, .entryTime, .entryEdit, .entryCategories{display: inline}
|
|
.entry-header li{text-transform: uppercase;}
|
|
div#container{font-family: 'Exchange SSm 4r', Georgia, serif}
|
|
"""
|
|
index = 'http://www.wired.com/magazine/'
|
|
|
|
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={'id':'container'})
|
|
remove_tags = [
|
|
dict(name=['object','embed','iframe','link','meta','base'])
|
|
,dict(name='div', attrs={'class':['social-top','podcast_storyboard','tweetmeme_button']})
|
|
,dict(attrs={'id':'ff_bottom_nav'})
|
|
,dict(name='a',attrs={'href':'http://www.wired.com/app'})
|
|
,dict(name='div', attrs={'id':'mag-bug'})
|
|
]
|
|
remove_attributes = ['height','width','lang','border','clear']
|
|
|
|
|
|
def parse_index(self):
|
|
totalfeeds = []
|
|
soup = self.index_to_soup(self.index)
|
|
majorf = soup.find('div',attrs={'class':'entry'})
|
|
if majorf:
|
|
articles = []
|
|
checker = []
|
|
for a in majorf.findAll('a', href=True):
|
|
if a['href'].startswith('http://www.wired.com/') and a['href'].endswith('/'):
|
|
title = self.tag_to_string(a)
|
|
url = a['href']
|
|
if title.lower() != 'read more' and url not in checker:
|
|
checker.append(url)
|
|
articles.append({
|
|
'title' :title
|
|
,'date' :strftime(self.timefmt)
|
|
,'url' :a['href']
|
|
,'description':''
|
|
})
|
|
totalfeeds.append(('Articles', articles))
|
|
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 = 'http://www.wired.com' + 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']
|
|
for item in soup.findAll('a'):
|
|
if item.string is not None:
|
|
tstr = item.string
|
|
item.replaceWith(tstr)
|
|
else:
|
|
item.name='span'
|
|
for atrs in ['href','target','alt','title','name','id']:
|
|
if item.has_key(atrs):
|
|
del item[atrs]
|
|
for item in soup.findAll('img'):
|
|
if not item.has_key('alt'):
|
|
item['alt'] = 'image'
|
|
if item.has_key('data-lazy-src'):
|
|
item['src'] = item['data-lazy-src']
|
|
del item['data-lazy-src']
|
|
return soup
|