| 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 genericScrapers | import genericScrapers |
| #RSS feed not detailed | #RSS feed not detailed |
| #http://www.doughellmann.com/PyMOTW/abc/ | #http://www.doughellmann.com/PyMOTW/abc/ |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
| def getAgencyID(self): | def getTable(self,soup): |
| return "8c9421f852c441910bf1d93a57b31d64" | return soup.find(id = "page_content").table |
| def getURL(self): | |
| return "http://www.daff.gov.au/about/foi/ips/disclosure-log" | |
| def getColumns(self,columns): | def getColumns(self,columns): |
| (id, date, title, description, notes) = columns | (id, date, title, description, notes) = columns |
| return (id, date, description, title, notes) | return (id, date, title, description, notes) |
| if __name__ == '__main__': | if __name__ == '__main__': |
| print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
| ScraperImplementation().doScrape() | ScraperImplementation().doScrape() |