www per bron

www/top2html.py

@@ -9,7 +9,9 @@ titles = {
     'personen':'personen',
     'organisaties':'organisaties',
     'overige-namen':'andere namen',
-    'nieuw-adjww':'nieuwe adjectieven, deelwoorden en werkwoorden'
+    'nieuw-adjww':'nieuwe adjectieven, deelwoorden en werkwoorden',
+    'cat.txt': 'categoriën',
+    'tag.txt': 'tags'
 }
 
 title = sys.argv[1]
@@ -29,6 +31,10 @@ with open(sys.argv[1], 'rt', encoding='utf-8') as fp:
     for line in fp:
         line = line.strip()
         aa = line.split('\t')
+        if len(aa) == 1:
+            bb = line.split()
+            aa[0] = bb[0]
+            aa.append(' '.join(bb[1:]))
         for i in range(1, len(aa)):
             aa[i] = html.escape(aa[i])
         v = int(aa[0])
@@ -39,5 +45,9 @@ with open(sys.argv[1], 'rt', encoding='utf-8') as fp:
         lineno += 1
         if lineno == 20:
             break
+while lineno < 20:
+    lineno += 1
+    sys.stdout.buffer.write(b'<tr><td><div style="width:0%"></div><td>&nbsp;</tr>\n')
 
-sys.stdout.buffer.write(b'</table>\n</div>\n')
+
+sys.stdout.buffer.write(b'</table>\n</div>\n\n')