mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
54 lines
2.5 KiB
Python
54 lines
2.5 KiB
Python
#!/usr/bin/env python2
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'somedayson & TonytheBookworm, revised by Cynthia Clavey'
|
|
__copyright__ = '2010, Cynthia Clavey cynvision@yahoo.com'
|
|
__version__ = '1.02'
|
|
__date__ = '05, september 2010'
|
|
__docformat__ = 'restructuredtext en'
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
class AdvancedUserRecipe1283666183(BasicNewsRecipe):
|
|
title = u'Journal Gazette Ft. Wayne IN'
|
|
__author__ = 'cynvision'
|
|
oldest_article = 1
|
|
language = 'en'
|
|
max_articles_per_feed = 8
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
keep_only_tags = [dict(name='div', attrs={'id': 'mainContent'})]
|
|
extra_css = '#copyinfo { font-size: 6 ;} \n #photocredit { font-size: 6 ;} \n .pubinfo { font-size: 6 ;}'
|
|
masthead_url = 'http://www.journalgazette.net/img/icons/jgmini.gif'
|
|
# cover_url = 'http://www.journalgazette.net/img/icons/jgmini.gif'
|
|
encoding = 'cp1252'
|
|
|
|
feeds = [(u'Opinion', u'http://journalgazette.net/apps/pbcs.dll/section?Category=EDIT&template=blogrss&mime=xml'),
|
|
(u'Local News', u'http://journalgazette.net/apps/pbcs.dll/section?Category=LOCAL&template=blogrss&mime=xml'),
|
|
(u'Sports', u'http://journalgazette.net/apps/pbcs.dll/section?Category=SPORTS&template=blogrss&mime=xml'),
|
|
(u'Features', u'http://journalgazette.net/apps/pbcs.dll/section?Category=FEAT&template=blogrss&mime=xml'),
|
|
(u'Business', u'http://journalgazette.net/apps/pbcs.dll/section?Category=BIZ&template=blogrss&mime=xml'),
|
|
(u'Ice Chips', u'http://journalgazette.net/apps/pbcs.dll/section?Category=BLOGS11&template=blogrss&mime=xml '),
|
|
(u'Entertainment', u'http://journalgazette.net/apps/pbcs.dll/section?Category=ENT&template=blogrss&mime=xml'),
|
|
(u'Food', u'http://journalgazette.net/apps/pbcs.dll/section?Category=FOOD&template=blogrss&mime=xml')
|
|
]
|
|
|
|
def print_version(self, url):
|
|
split1 = url.split("/")
|
|
# print 'THE SPLIT IS: ', split1
|
|
url3 = split1[2]
|
|
url5 = split1[4]
|
|
url6 = split1[5]
|
|
url7 = split1[6]
|
|
|
|
print_url = 'http://' + url3 + '/apps/pbcs.dll/article?AID=/' + \
|
|
url5 + '/' + url6 + '/' + url7 + '/-1/EDIT01&template=printart'
|
|
# print 'THIS URL WILL PRINT: ', print_url # this is a test string to
|
|
# see what the url is it will return
|
|
return print_url
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|