From 77ebbb602254885dfca406f3d79e248460d28594 Mon Sep 17 00:00:00 2001 From: richardxdh Date: Tue, 20 Jun 2017 14:47:27 +0800 Subject: [PATCH] Update searchengine.py fill in isindexed --- chapter4/searchengine.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/chapter4/searchengine.py b/chapter4/searchengine.py index 1b99b62..4c729d5 100644 --- a/chapter4/searchengine.py +++ b/chapter4/searchengine.py @@ -76,6 +76,11 @@ def separatewords(self,text): # Return true if this url is already indexed def isindexed(self,url): + u=self.con.execute("select rowid from urllist where url='%s'" % url).fetchone() + if u!=None: + # Check if it has actually been crawled + v=self.con.execute( 'select * from wordlocation where urlid=%d' % u[0]).fetchone() + if v!=None: return True return False # Add a link between two pages