more scrapers
[disclosr.git] / documents / scrapers / 8796220032faf94501bd366763263685.py
blob:a/documents/scrapers/8796220032faf94501bd366763263685.py -> blob:b/documents/scrapers/8796220032faf94501bd366763263685.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 6
   
  def getColumns(self, columns):
  (id, date, title, description, datepub, notes) = columns
  return (id, date, title, description, notes)
   
   
  if __name__ == '__main__':
  print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
  print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
   
  nsi = ScraperImplementation()
  nsi.disclogURL = "http://www.dpmc.gov.au/foi/ips/disclosure_logs/pmo/2011-12.cfm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.dpmc.gov.au/foi/ips/disclosure_logs/dpmc/2011-12.cfm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.dpmc.gov.au/foi/ips/disclosure_logs/dpmc/2012-13.cfm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.dpmc.gov.au/foi/ips/disclosure_logs/omsi/2011-12.cfm"
  nsi.doScrape()
  nsi.disclogURL = "http://www.dpmc.gov.au/foi/ips/disclosure_logs/omps/2012-13.cfm"
  nsi.doScrape()