added extract tree based on timestamp

Trie.py

@@ -4,6 +4,18 @@ class TrieNode:
         self.data = {}
         self.isEndOfUrl = False
 
+    def extract(self, startTimestamp , endTimeStamp):
+        pCrawl = self
+        pCrawlCopy = TrieNode()
+        pCrawlCopy.isEndOfUrl = pCrawl.isEndOfUrl
+        for data in pCrawl.data:
+            if data <= endTimeStamp and data >= startTimestamp:
+                pCrawlCopy.data[data] = pCrawl.data[data]
+        for child in pCrawl.children:
+            pCrawlJunior = pCrawl.children[child]
+            pCrawlCopy.children[child] = pCrawlJunior.extract(startTimestamp, endTimeStamp)
+        return pCrawlCopy
+
 class Trie:
 
     def __init__(self):
@@ -30,11 +42,8 @@ class Trie:
         pCrawl.isEndOfUrl = True
 
     def extract(self, startTimestamp , endTimeStamp):
-        print()
         # extract tree based on given timestamp
-        # pCrawl = self.root
-        # for child in pCrawl.children:
-        #     print(child)
+        return self.root.extract(startTimestamp, endTimeStamp)
 
     def comparison(self, tree1, tree2):
         print()

main.py

@@ -45,20 +45,12 @@ for dayData in data_train:
         payload = dayDataNP[i][9]
         sitemap.insert(parsedurl.path, timestamp, payload)
 
-        # if not(sitemapURLS.__contains__(parsedurl.path)):
-        #     sitemapURLS[parsedurl.path] = parsedurl[1]+parsedurl[2]
-        #     sitemap.insert(parsedurl.path, timestamp, payload)
-
-
-
-
-
-
-
-
-
-
-
+vtTree = sitemapURLS['www.vt.edu']
+vtTreeCopy = vtTree.extract('20140906125541','20141215204723')
+print('done')
 
 
 
+        # if not(sitemapURLS.__contains__(parsedurl.path)):
+        #     sitemapURLS[parsedurl.path] = parsedurl[1]+parsedurl[2]
+        #     sitemap.insert(parsedurl.path, timestamp, payload)