20221002

数据处理.ipynb

@@ -57,6 +57,13 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-30T14:14:46.100665Z",
+     "iopub.status.busy": "2022-09-30T14:14:46.100139Z",
+     "iopub.status.idle": "2022-09-30T14:14:46.109863Z",
+     "shell.execute_reply": "2022-09-30T14:14:46.108679Z",
+     "shell.execute_reply.started": "2022-09-30T14:14:46.100616Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -74,6 +81,99 @@
     "print(list1)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-10-02T01:11:16.449789Z",
+     "iopub.status.busy": "2022-10-02T01:11:16.449246Z",
+     "iopub.status.idle": "2022-10-02T01:11:16.458463Z",
+     "shell.execute_reply": "2022-10-02T01:11:16.457216Z",
+     "shell.execute_reply.started": "2022-10-02T01:11:16.449740Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "('5', '10', '48')"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import re\n",
+    "t = '5小时10分48秒'\n",
+    "m = re.match(r'(.*)小时(.*)分(.*)秒', t)\n",
+    "m.groups()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-10-02T01:20:50.471217Z",
+     "iopub.status.busy": "2022-10-02T01:20:50.470675Z",
+     "iopub.status.idle": "2022-10-02T01:20:50.482522Z",
+     "shell.execute_reply": "2022-10-02T01:20:50.481212Z",
+     "shell.execute_reply.started": "2022-10-02T01:20:50.471168Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0, '10', '48']\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "t = '10分48秒'\n",
+    "list1 = []\n",
+    "if '小时' in t and '分' in t:\n",
+    "    m = re.match(r'(.*)小时(.*)分(.*)秒', t)\n",
+    "    list1 = [m[1],m[2],m[3]]\n",
+    "elif '小时' in t:\n",
+    "    m = re.match(r'(.*)小时(.*)秒', t)\n",
+    "    list1 = [m[1],0,m[2]]\n",
+    "elif '分' in t:\n",
+    "    m = re.match(r'(.*)分(.*)秒', t)\n",
+    "    list1 = [0,m[1],m[2]]\n",
+    "print(list1)\n",
+    "#m.group()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-30T14:22:32.892529Z",
+     "iopub.status.busy": "2022-09-30T14:22:32.892006Z",
+     "iopub.status.idle": "2022-09-30T14:22:32.900751Z",
+     "shell.execute_reply": "2022-09-30T14:22:32.898954Z",
+     "shell.execute_reply.started": "2022-09-30T14:22:32.892480Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "s = '2022-09-28-《气郁组》-视频学习详情_155229'\n",
+    "m = re.findall(r'《(.+)》',s)\n",
+    "print(m)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -397,7 +497,6 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "jp-MarkdownHeadingCollapsed": true,
     "tags": []
    },
    "source": [
@@ -1230,7 +1329,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2022-06-30T01:50:36.294943Z",