last commit was not the latest.

cleanup-roster.py

@@ -1,8 +1,7 @@
-# import system module
 import sys, re, argparse
 import csv
 
-class   Students:
+class   Student:
 
     def     __init__(self):
         self.id = ""
@@ -57,39 +56,49 @@ def     write_csv(file, student_list, fields):
 # print(args)
 
 student_list = []
-field_num = -1 
 student = None
 previous = ''
 
-with open(args.infile, 'r') as file:
-    num_lines = 0
-    for line in file:
-        num_lines += 1
+try:
+    with open(args.infile, 'r') as file:
+        num_lines = 0
+        for line in file:
+            num_lines += 1
 
-        if line.startswith('<tr>') or line.startswith('</table>'):
-            if student is not None:
-                student_list.append(student)
-                field_num = -1
-                student = None
+            if line.startswith('<tr>') or line.startswith('</table>'):
+                if student is not None:
+                    student_list.append(student)
+                    student = None
+                previous = ''
+                continue
 
-        # remove spaces at the end of the line, including newline
-        line = line.rstrip()
+            # remove spaces at the end of the line, including newline
+            line = line.rstrip()
 
-        if line.startswith('<td'):
-            previous = ''
-        else:
-            line = previous + line
-
-        if not line.endswith('</td>'):
-            previous = line  
-            continue
-
-        # now we have a line that starts with "<td" and ends with "</td>"
-        m = re.search(r'^<td[^>]*>(.*)</td>', line)
-        if m:
-            if student is None:
-                student = Students()
-            student.add_field(m.group(1))
+            # append to previous line, if there is any
+            if previous: 
+                line = previous + line
+
+            if not line.startswith("<td"):
+                # ignore lines that do not indicate a new field
+                assert(previous == '')
+                continue
+
+            # print(line)
+
+            # now we check if a line that starts with "<td" and has a "</td>"
+            m = re.match(r'<td[^>]*>(.*)</td>', line)
+            if m:
+                if student is None:
+                    student = Student()
+                student.add_field(m.group(1))
+                previous = ''
+            else:
+                # if there is need more lines
+                previous = line
+except FileNotFoundError as e:
+    print(e)
+    exit(1)
 
 if args.o != '':
     with open(args.o, 'w', newline='') as csvfile: