Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

New recipe for The Escapist by Lorenzo Vigentini

Browse Source
This commit is contained in:
Kovid Goyal 2010-01-09 10:07:34 -07:00
parent 3ced1df5e8
commit 7a2e4a43e6
3 changed files with 68 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
resources/recipes/freenature.recipe
View File

@ -1,5 +1,4 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
import re
class NatureNews(BasicNewsRecipe):
@ -30,15 +29,3 @@ class NatureNews(BasicNewsRecipe):
def get_article_url(self, article):
return article.get('id')
#def preprocess_html(self, soup):
#story = soup.find(name='div', attrs={'id':'contentColumn'})
#td = heading.findParent(name='td')
#td.extract()
#soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
#body = soup.find(name='body')
#body.insert(0, story)
#for x in soup.findAll(name='p', text=lambda x:x and '--&gt;' in x):
#p = x.findParent('p')
#if p is not None:
#p.extract()
#return soup

3
resources/recipes/nzherald.recipe
View File

@ -1,7 +1,4 @@
import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class NewZealandHerald(BasicNewsRecipe):

59
resources/recipes/the_escapist.recipe Normal file
View File

@ -0,0 +1,59 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini'
__copyright__ = '2009, Lorenzo Vigentini <l.vigentini at gmail.com>'
description = 'the Escapist Magazine - v1.02 (09, January 2010)'
'''
http://www.escapistmagazine.com/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class al(BasicNewsRecipe):
author = 'Lorenzo Vigentini'
description = 'the Escapist Magazine'
cover_url = 'http://cdn.themis-media.com/themes/escapistmagazine/default/images/logo.png'
title = u'the Escapist Magazine'
publisher = 'Themis media'
category = 'Video games news, lifestyle, gaming culture'
language = 'en'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 1
max_articles_per_feed = 100
use_embedded_content = False
recursion = 10
remove_javascript = True
no_stylesheets = True
feeds = [
(u'Daily News', u'http://www.escapistmagazine.com/rss/news/0.xml'),
(u'Articles', u'http://www.escapistmagazine.com/rss/articles/0.xml')
]
def print_version(self,url):
baseURL='http://www.escapistmagazine.com'
segments = url.split('/')
#basename = '/'.join(segments[:3]) + '/'
subPath= '/'+ segments[3] + '/'
articleURL=(segments[len(segments)-1])[0:5]
if articleURL[4] =='-':
articleURL=articleURL[:4]
printVerString='print/'+ articleURL
s= baseURL + subPath + printVerString
return s
keep_only_tags = [
dict(name='div', attrs={'id':'article'})
]
remove_tags = [
dict(name='div',attrs={'id':['ad_leaderboard','print_notice','bottom_panel_container']})
]