more scrapers
[disclosr.git] / documents / scrapers / b0a3281ba66efe173c5a33d5ef90ff76.py
blob:a/documents/scrapers/b0a3281ba66efe173c5a33d5ef90ff76.py -> blob:b/documents/scrapers/b0a3281ba66efe173c5a33d5ef90ff76.py
  import sys,os
  sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
  import genericScrapers
  import dateutil
  from dateutil.parser import *
  from datetime import *
   
   
  class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
   
  def __init__(self):
  super(ScraperImplementation, self).__init__()
   
  def getColumnCount(self):
  return 2
   
  def getColumns(self, columns):
  (date, title) = columns
  return (title, date, title, title, None)
   
   
  if __name__ == '__main__':
  print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
  print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
   
  nsi = ScraperImplementation()
  nsi.disclogURL = "http://www.immi.gov.au/about/foi/foi-disclosures-2012.htm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.immi.gov.au/about/foi/foi-disclosures-2011.htm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.immi.gov.au/about/foi/foi-disclosures-2010.htm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.immi.gov.au/about/foi/foi-disclosures-2009.htm"
  nsi.doScrape()