20250314

文件操作.ipynb

@@ -1,12 +1,5 @@
 {
  "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# 数字文件名转换为文本文件名"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -412,6 +405,132 @@
     "    fl1.writelines(list1)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 读取html文件"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-03-09T02:47:43.965042Z",
+     "iopub.status.busy": "2025-03-09T02:47:43.964342Z",
+     "iopub.status.idle": "2025-03-09T02:47:44.398962Z",
+     "shell.execute_reply": "2025-03-09T02:47:44.398531Z",
+     "shell.execute_reply.started": "2025-03-09T02:47:43.964980Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'list'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "from bs4 import BeautifulSoup\n",
+    "import re\n",
+    "from pathlib import Path\n",
+    "\n",
+    "def get_html_title(html_file_path):\n",
+    "    with open(html_file_path, 'r', encoding='utf-8') as f:\n",
+    "        html_content = f.read()\n",
+    "    \n",
+    "    soup = BeautifulSoup(html_content, 'html.parser')\n",
+    "    title_tag = soup.title\n",
+    "    \n",
+    "    if title_tag and hasattr(title_tag, 'string'):\n",
+    "        return title_tag.string.strip()\n",
+    "    else:\n",
+    "        return None  # 标签不存在或内容为空\n",
+    "\n",
+    "\n",
+    "path = Path('./file/guzi')\n",
+    "markdown_content = []\n",
+    "files = [file for file in path.iterdir() if file.is_file()]\n",
+    "sorted_files = sorted(files, key=lambda f: f.name)\n",
+    "print(type(sorted_files))\n",
+    "for file in sorted_files:\n",
+    "    if file.suffix=='.html':\n",
+    "        markdown_content.append('## '+get_html_title(file))\n",
+    "        with open(file, 'r', encoding='utf-8') as f:\n",
+    "            html_content = f.read()            \n",
+    "            soup = BeautifulSoup(html_content, 'html.parser')\n",
+    "            div = soup.find('div', class_=\"show-content\")\n",
+    "            p_elements = div.find_all('p')            \n",
+    "            for div in p_elements:\n",
+    "                markdown_content.append(div.get_text(strip=True))\n",
+    "                #markdown_content.append('\\n')\n",
+    "    if file.suffix=='.md':\n",
+    "        with open(file, 'r', encoding='utf-8') as f:\n",
+    "            txt_content = f.read()\n",
+    "            lines = txt_content.splitlines()\n",
+    "            for line in lines:\n",
+    "                line = line.strip()\n",
+    "                markdown_content.append(line)\n",
+    "                \n",
+    "markdown_content = '\\n'.join(markdown_content)\n",
+    "with open('guzi.md', 'w', encoding='utf-8') as file:\n",
+    "    file.write(markdown_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-03-09T02:36:40.207084Z",
+     "iopub.status.busy": "2025-03-09T02:36:40.206317Z",
+     "iopub.status.idle": "2025-03-09T02:36:40.223987Z",
+     "shell.execute_reply": "2025-03-09T02:36:40.223140Z",
+     "shell.execute_reply.started": "2025-03-09T02:36:40.207017Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from bs4 import BeautifulSoup\n",
+    "import re\n",
+    "from pathlib import Path\n",
+    "\n",
+    "\n",
+    "def get_html_title(html_file_path):\n",
+    "    with open(html_file_path, 'r', encoding='utf-8') as f:\n",
+    "        html_content = f.read()\n",
+    "    \n",
+    "    soup = BeautifulSoup(html_content, 'html.parser')\n",
+    "    title_tag = soup.title\n",
+    "    \n",
+    "    if title_tag and hasattr(title_tag, 'string'):\n",
+    "        return title_tag.string.strip()\n",
+    "    else:\n",
+    "        return None  # 标签不存在或内容为空\n",
+    "\n",
+    "\n",
+    "file='file/guzi/1-01.html'\n",
+    "markdown_content = []\n",
+    "markdown_content.append('## '+get_html_title(file))\n",
+    "with open(file, 'r', encoding='utf-8') as f:\n",
+    "    html_content = f.read()\n",
+    "    \n",
+    "    soup = BeautifulSoup(html_content, 'html.parser')\n",
+    "    div = soup.find('div', class_=\"show-content\")\n",
+    "    p_elements = div.find_all('p')\n",
+    "    \n",
+    "    for div in p_elements:\n",
+    "        markdown_content.append(div.get_text(strip=True))\n",
+    "        markdown_content.append('\\n')\n",
+    "markdown_content = '\\n'.join(markdown_content)\n",
+    "with open('1-01.md', 'w', encoding='utf-8') as file:\n",
+    "    file.write(markdown_content)\n",
+    "\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},