import sys,os |
import sys,os |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
import scrape |
import genericScrapers |
foidocsdb = scrape.couch['disclosr-foidocuments'] |
#RSS feed not detailed |
|
|
#rss feed has only one entry |
#http://www.doughellmann.com/PyMOTW/abc/ |
http://www.daff.gov.au/about/foi/ips/disclosure-log |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
|
def getTable(self,soup): |
|
return soup.find(id = "page_content").table |
|
def getColumns(self,columns): |
|
(id, date, title, description, notes) = columns |
|
return (id, date, title, description, notes) |
|
|
|
if __name__ == '__main__': |
|
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
|
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
|
ScraperImplementation().doScrape() |
|
|
|
|