def __init__(self):
     crwl=Crawler()
     crwl.get_pagelist()
     self.pagelist=crwl.return_pagelist()
     self.soup=crwl.return_soup()
     self.articledb=ArticleDb('localhost',27017)
     self.articledb.init_backend('testdb','testcol')
     self.final_docs=[]
     self.error_pagelist=[]