Skip single character & too long pages (closes felixonmars#1 & felixo…

…nmars#2)
anaer · May 23, 2020 · 8105228 · 8105228
1 parent 4aeb12f
commit 8105228
Showing 1 changed file with 5 additions and 1 deletion.
diff --git a/convert.py b/convert.py
@@ -15,7 +15,11 @@
         if not HANZI_RE.match(line):
             continue
 
-        # Skip list page.
+        # Skip single character & too long pages
+        if not 1 < len(line) < 9:
+            continue
+
+        # Skip list pages
         if line.endswith('\u5217\u8868'):
             continue