derive agencyID and disclog url from filename
[disclosr.git] / documents / scrapers / e2a845e55bc9986e6c75c5ad2c508b8d.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
import sys,os
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
import genericScrapers
#RSS feed not detailed
 
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
        def getColumns(self,columns):
                (id, date, title, description, notes) = columns
                return (id, date, description, title, notes)
 
if __name__ == '__main__':
    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper)
    ScraperImplementation().doScrape()
 
www.finance.gov.au/foi/disclosure-log/foi-rss.xml