the following function retrieves pages from the web and saves them in a specified dir. i want to extract the respective filenames from the urls e.g the page code.google.com shud be saved as code-google.htm or something similar. can u suggest me a way to do it def retrieve_url(self,url): """ The main method of the robot class and is called run method to retrieve the given urls from the web."""
if url is not None: try: if visited.has_key(url): return pieces=urlparse.urlparse(url) filepath=pieces[2] if filepath != '': filepath=filepath[1:] filename=filepath.split("/")[-1] else: filename='home.htm' path=os.path.join(PAGE_DIR,filename) url=urlparse.urlunparse(pieces) p=url.rfind('#') #temporary if p!=-1: url=url[:p] visited[url]=1 m=urllib2.urlopen(url) fopen=open(path,'wb') fopen.seek(0) fopen.write(url+'|') fopen.write(m.read()) fopen.close() print url ,'retrieved' except IOError: print url print "ERROR:OOPS! THE URL CAN'T BE RETRIEVED" return -- http://mail.python.org/mailman/listinfo/python-list