[sixxs] improve parsing

import_sixxs_prefixes.py

@@ -15,34 +15,69 @@ class MyHTMLParser(HTMLParser):
 
         self.results = []
 
+        self.th = False
+        self.prefix = False
+        self.name = False
+        self.org = False
+        self.website = False
+
     def handle_starttag(self, tag, attrs):
 #        print(f"Encountered a start tag: '{tag}'")
 
-        if tag == "tbody":
-            self.tbody_count += 1
-            print(f"tbody: {self.tbody_count} {attrs}")
+        if tag == "th":
+            self.th = True
 
-            if self.tbody_count == 2:
-                self.in_table = True
-                print("in real table")
-
-        elif self.in_table and tag == "tr":
+        if self.in_table and tag == "tr":
             self.in_row = True
-            print("in real table")
+            self.col_index = 0
 
         elif self.in_row and tag == "td":
-            print("td data")
+            self.col_index += 1
 
+            if self.col_index == 2:
+                self.name = True
+            elif self.col_index == 3:
+                self.org = True
+
+        elif self.col_index == 1 and tag == "a":
+            self.prefix = True
+        elif self.col_index == 4 and tag == "a":
+            self.website = True
 
 
     def handle_endtag(self, tag):
-        pass
-        #print("Encountered an end tag :", tag)
+        if tag == "th":
+            self.th = False
+        elif tag == "tr":
+            self.in_row = False
+
 
     def handle_data(self, data):
-        #print("Encountered some data  :", data)
-        pass
+        if self.th and data == "Prefix":
+            print("Found table start")
+            self.in_table = True
 
+        if self.prefix:
+            self.record = {}
+            self.record['prefix'] = data
+
+            self.results.append(self.record)
+
+            self.prefix = False
+
+        elif self.name:
+            self.record['name'] = data
+            self.name = False
+        elif self.org:
+            self.record['organization'] = data
+            self.org = False
+        elif self.website:
+            self.record['website'] = data
+            self.website = False
+
+    def report(self):
+        for record in self.results:
+            print(record)
 
 if __name__ == '__main__':
     url = "https://www.sixxs.net/tools/grh/ula/list/"
@@ -51,3 +86,5 @@ if __name__ == '__main__':
     html = "\n".join([ line.decode('utf-8') for line in response.readlines() ])
 
     parser.feed(html)
+
+    parser.report()