more scrapers
[disclosr.git] / documents / scrapers / 54cbb3439276062b7a9f007f9f69d1f6.py
blob:a/documents/scrapers/54cbb3439276062b7a9f007f9f69d1f6.py -> blob:b/documents/scrapers/54cbb3439276062b7a9f007f9f69d1f6.py
  import sys,os
  sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
  import genericScrapers
  import scrape
  from bs4 import BeautifulSoup
   
  #http://www.doughellmann.com/PyMOTW/abc/
  class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
  #def getTable(self,soup):
  # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
  def getColumnCount(self):
  return 4
  def getColumns(self,columns):
  (id, date, title, description) = columns
  return (id, date, title, description, None)
   
  if __name__ == '__main__':
  print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
  print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
  ScraperImplementation().doScrape()