Update: 初学记、佩文韵府 and 五车韵瑞

佩文韵府/parse_html_logic.py

@@ -0,0 +1,9 @@
+def simplify_char(c):
+    mapping = {'東': '东', '銅': '铜', '童': '童'} # add others if needed
+    return mapping.get(c, c)
+
+num_map = {'一':'1', '二':'2', '三':'3', '四':'4', '五':'5', '六':'6', '七':'7', '八':'8', '九':'9'}
+
+# "01之一"
+# If vol_m = re.search(r"卷(.)之(.)", text)
+# "0" + num_map[vol_m.group(1)] + "之" + vol_m.group(2)