home *** CD-ROM | disk | FTP | other *** search
- #!/usr/bin/env python
- __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
- #url1 = split1[0]
- #url2 = split1[1]
- url3 = split1[2]
- #url4 = split1[3]
- url5 = split1[4]
- url6 = split1[5]
- url7 = split1[6]
- #url8 = split1[7]
-
- #need to convert to print_version
- #originalversion is : http://www.journalgazette.net/article/20100905/EDIT10/309059959/1021/EDIT
- #printversion should be: http://www.journalgazette.net/apps/pbcs.dll/article?AID=/20100905/EDIT10/309059959/-1/EDIT01&template=printart
- #results of the split
- #THE SPLIT IS: [u'http:', u'', u'www.journalgazette.net', u'article', u'20100905', u'EDIT10', u'309059959', u'1021', u'EDIT']
-
-
-
- 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
-