20240522

围棋点校文献/文件处理.ipynb

@@ -76,15 +76,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "3ecfe0a8-3af1-4f48-a2b0-6c3eb25df07d",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-05-18T14:34:21.905084Z",
-     "iopub.status.busy": "2024-05-18T14:34:21.904353Z",
-     "iopub.status.idle": "2024-05-18T14:34:21.916057Z",
-     "shell.execute_reply": "2024-05-18T14:34:21.914979Z",
-     "shell.execute_reply.started": "2024-05-18T14:34:21.905017Z"
+     "iopub.execute_input": "2024-05-21T23:57:39.161812Z",
+     "iopub.status.busy": "2024-05-21T23:57:39.161088Z",
+     "iopub.status.idle": "2024-05-21T23:57:39.171261Z",
+     "shell.execute_reply": "2024-05-21T23:57:39.169939Z",
+     "shell.execute_reply.started": "2024-05-21T23:57:39.161751Z"
     },
     "tags": []
    },
@@ -112,6 +112,15 @@
     "    modified_text = re.sub(pattern, replacement, text)\n",
     "    return modified_text\n",
     "\n",
+    "def replace_numbers_with_braces(text):\n",
+    "    # 使用正则表达式查找连续的数字\n",
+    "    pattern = re.compile(r'\\d+')\n",
+    "    \n",
+    "    # 使用re.sub()进行替换\n",
+    "    result = pattern.sub(lambda x: f\"{{{{ img_{x.group(0)} }}}}\", text)\n",
+    "    \n",
+    "    return result\n",
+    "\n",
     "list1 = []\n",
     "filepath = '文本文件/'\n",
     "files = glob.glob(f'{filepath}*.txt')\n",
@@ -119,7 +128,7 @@
     "    with open(fn, \"r\") as f:\n",
     "        data = f.readlines()\n",
     "        for s in data:\n",
-    "            ss = replace_numbers(s)\n",
+    "            ss = replace_numbers_with_braces(s)\n",
     "            list1 = find_all_numbers(ss)\n",
     "            list1 = list(set(list1))\n",
     "            list1.sort()\n",