{"id":152311,"date":"2024-11-01T21:52:25","date_gmt":"2024-11-01T13:52:25","guid":{"rendered":"https:\/\/server.hk\/cnblog\/152311\/"},"modified":"2024-11-01T21:52:26","modified_gmt":"2024-11-01T13:52:26","slug":"%e6%8e%a1%e9%9b%86%e5%be%ae%e4%bf%a1%e5%85%ac%e7%9c%be%e8%99%9f%e6%96%87%e7%ab%a0%e6%95%b8%e6%93%9a%ef%bc%8c%e6%89%93%e9%80%a0%e6%95%b8%e6%93%9a%e5%ba%ab%e5%a4%a7-%e5%be%ae%e4%bf%a1%e5%85%ac%e7%9c%be","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/152311\/","title":{"rendered":"\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\uff0c\u6253\u9020\u6578\u64da\u5eab\u5927 (\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u63a1\u96c6\u5230\u6578\u64da\u5eab)"},"content":{"rendered":"<h1 id=\"%e6%8e%a1%e9%9b%86%e5%be%ae%e4%bf%a1%e5%85%ac%e7%9c%be%e8%99%9f%e6%96%87%e7%ab%a0%e6%95%b8%e6%93%9a%ef%bc%8c%e6%89%93%e9%80%a0%e6%95%b8%e6%93%9a%e5%ba%ab%e5%a4%a7-iyGWnklPVB\">\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\uff0c\u6253\u9020\u6578\u64da\u5eab\u5927<\/h1>\n<p>\u96a8\u8457\u793e\u4ea4\u5a92\u9ad4\u7684\u8fc5\u901f\u767c\u5c55\uff0c\u5fae\u4fe1\u516c\u773e\u865f\u5df2\u6210\u70ba\u4f01\u696d\u548c\u500b\u4eba\u50b3\u64ad\u4fe1\u606f\u7684\u91cd\u8981\u5e73\u53f0\u3002\u8a31\u591a\u7528\u6236\u548c\u4f01\u696d\u5e0c\u671b\u80fd\u5920\u5f9e\u9019\u4e9b\u516c\u773e\u865f\u4e2d\u63d0\u53d6\u6578\u64da\uff0c\u4ee5\u4fbf\u9032\u884c\u5206\u6790\u3001\u7814\u7a76\u6216\u5275\u5efa\u6578\u64da\u5eab\u3002\u672c\u6587\u5c07\u63a2\u8a0e\u5982\u4f55\u6709\u6548\u5730\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\uff0c\u4e26\u5c07\u5176\u6574\u7406\u6210\u4e00\u500b\u53ef\u7528\u7684\u6578\u64da\u5eab\u3002<\/p>\n<h2 id=\"%e7%82%ba%e4%bb%80%e9%ba%bc%e8%a6%81%e6%8e%a1%e9%9b%86%e5%be%ae%e4%bf%a1%e5%85%ac%e7%9c%be%e8%99%9f%e6%96%87%e7%ab%a0%e6%95%b8%e6%93%9a%ef%bc%9f-iyGWnklPVB\">\u70ba\u4ec0\u9ebc\u8981\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\uff1f<\/h2>\n<p>\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\u7684\u539f\u56e0\u6709\u5f88\u591a\uff0c\u4e3b\u8981\u5305\u62ec\uff1a<\/p>\n<ul>\n<li><strong>\u5e02\u5834\u5206\u6790\uff1a<\/strong>\u901a\u904e\u5206\u6790\u516c\u773e\u865f\u7684\u6587\u7ae0\u5167\u5bb9\uff0c\u53ef\u4ee5\u4e86\u89e3\u884c\u696d\u8da8\u52e2\u3001\u7af6\u722d\u5c0d\u624b\u7684\u52d5\u614b\u4ee5\u53ca\u7528\u6236\u7684\u9700\u6c42\u3002<\/li>\n<li><strong>\u5167\u5bb9\u5275\u4f5c\uff1a<\/strong>\u63a1\u96c6\u7684\u6578\u64da\u53ef\u4ee5\u5e6b\u52a9\u5167\u5bb9\u5275\u4f5c\u8005\u7372\u53d6\u9748\u611f\uff0c\u4e86\u89e3\u54ea\u4e9b\u4e3b\u984c\u53d7\u6b61\u8fce\uff0c\u5f9e\u800c\u63d0\u9ad8\u6587\u7ae0\u7684\u9ede\u64ca\u7387\u3002<\/li>\n<li><strong>\u5b78\u8853\u7814\u7a76\uff1a<\/strong>\u5b78\u8005\u548c\u7814\u7a76\u4eba\u54e1\u53ef\u4ee5\u5229\u7528\u9019\u4e9b\u6578\u64da\u9032\u884c\u793e\u6703\u5b78\u3001\u5a92\u9ad4\u5b78\u7b49\u65b9\u9762\u7684\u7814\u7a76\u3002<\/li>\n<\/ul>\n<h2 id=\"%e5%a6%82%e4%bd%95%e6%8e%a1%e9%9b%86%e5%be%ae%e4%bf%a1%e5%85%ac%e7%9c%be%e8%99%9f%e6%96%87%e7%ab%a0%e6%95%b8%e6%93%9a-iyGWnklPVB\">\u5982\u4f55\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da<\/h2>\n<p>\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\u7684\u904e\u7a0b\u53ef\u4ee5\u5206\u70ba\u5e7e\u500b\u6b65\u9a5f\uff1a<\/p>\n<h3 id=\"1-%e7%a2%ba%e5%ae%9a%e7%9b%ae%e6%a8%99%e5%85%ac%e7%9c%be%e8%99%9f-iyGWnklPVB\">1. \u78ba\u5b9a\u76ee\u6a19\u516c\u773e\u865f<\/h3>\n<p>\u9996\u5148\uff0c\u9700\u8981\u78ba\u5b9a\u8981\u63a1\u96c6\u6578\u64da\u7684\u516c\u773e\u865f\u3002\u53ef\u4ee5\u901a\u904e\u5fae\u4fe1\u641c\u7d22\u529f\u80fd\u627e\u5230\u76f8\u95dc\u7684\u516c\u773e\u865f\uff0c\u4e26\u8a18\u9304\u4e0b\u5176\u540d\u7a31\u548cID\u3002<\/p>\n<h3 id=\"2-%e4%bd%bf%e7%94%a8%e7%88%ac%e8%9f%b2%e6%8a%80%e8%a1%93-iyGWnklPVB\">2. \u4f7f\u7528\u722c\u87f2\u6280\u8853<\/h3>\n<p>\u722c\u87f2\u6280\u8853\u662f\u81ea\u52d5\u5316\u63d0\u53d6\u7db2\u9801\u6578\u64da\u7684\u5de5\u5177\u3002\u4ee5\u4e0b\u662f\u4e00\u500b\u7c21\u55ae\u7684Python\u722c\u87f2\u793a\u4f8b\uff0c\u4f7f\u7528\u4e86BeautifulSoup\u5eab\u4f86\u63d0\u53d6\u6587\u7ae0\u6a19\u984c\u548c\u5167\u5bb9\uff1a<\/p>\n<pre><code>import requests\nfrom bs4 import BeautifulSoup\n\ndef fetch_wechat_articles(url):\n    response = requests.get(url)\n    soup = BeautifulSoup(response.text, 'html.parser')\n    \n    articles = []\n    for item in soup.find_all('h2', class_='title'):\n        title = item.get_text()\n        link = item.find('a')['href']\n        articles.append({'title': title, 'link': link})\n    \n    return articles\n\nurl = 'https:\/\/mp.weixin.qq.com\/some_public_account'\narticles = fetch_wechat_articles(url)\nprint(articles)\n<\/code><\/pre>\n<h3 id=\"3-%e6%95%b8%e6%93%9a%e6%b8%85%e6%b4%97%e8%88%87%e6%95%b4%e7%90%86-iyGWnklPVB\">3. \u6578\u64da\u6e05\u6d17\u8207\u6574\u7406<\/h3>\n<p>\u7372\u53d6\u6578\u64da\u5f8c\uff0c\u9700\u9032\u884c\u6e05\u6d17\u548c\u6574\u7406\u3002\u9019\u5305\u62ec\u53bb\u9664\u91cd\u8907\u6578\u64da\u3001\u683c\u5f0f\u5316\u65e5\u671f\u3001\u6a19\u984c\u7b49\u3002\u53ef\u4ee5\u4f7f\u7528Pandas\u5eab\u4f86\u9032\u884c\u6578\u64da\u8655\u7406\uff1a<\/p>\n<pre><code>import pandas as pd\n\n# \u5047\u8a2d articles \u662f\u5f9e\u722c\u87f2\u7372\u53d6\u7684\u6578\u64da\ndf = pd.DataFrame(articles)\ndf.drop_duplicates(subset='title', inplace=True)\ndf.to_csv('wechat_articles.csv', index=False)\n<\/code><\/pre>\n<h3 id=\"4-%e6%95%b8%e6%93%9a%e5%ba%ab%e5%ad%98%e5%84%b2-iyGWnklPVB\">4. \u6578\u64da\u5eab\u5b58\u5132<\/h3>\n<p>\u6e05\u6d17\u5f8c\u7684\u6578\u64da\u53ef\u4ee5\u5b58\u5132\u5230\u6578\u64da\u5eab\u4e2d\u3002\u5e38\u7528\u7684\u6578\u64da\u5eab\u6709MySQL\u3001PostgreSQL\u7b49\u3002\u4ee5\u4e0b\u662f\u5c07\u6578\u64da\u5b58\u5132\u5230MySQL\u7684\u793a\u4f8b\uff1a<\/p>\n<pre><code>import mysql.connector\n\ndef store_to_db(data):\n    conn = mysql.connector.connect(user='username', password='password', host='localhost', database='wechat_db')\n    cursor = conn.cursor()\n    \n    for article in data:\n        cursor.execute(\"INSERT INTO articles (title, link) VALUES (%s, %s)\", (article['title'], article['link']))\n    \n    conn.commit()\n    cursor.close()\n    conn.close()\n\nstore_to_db(articles)\n<\/code><\/pre>\n<h2 id=\"%e6%b3%a8%e6%84%8f%e4%ba%8b%e9%a0%85-iyGWnklPVB\">\u6ce8\u610f\u4e8b\u9805<\/h2>\n<p>\u5728\u9032\u884c\u6578\u64da\u63a1\u96c6\u6642\uff0c\u9700\u9075\u5faa\u76f8\u95dc\u6cd5\u5f8b\u6cd5\u898f\uff0c\u5c0a\u91cd\u77e5\u8b58\u7522\u6b0a\u548c\u96b1\u79c1\u6b0a\u3002\u6b64\u5916\uff0c\u904e\u65bc\u983b\u7e41\u7684\u8acb\u6c42\u53ef\u80fd\u6703\u5c0e\u81f4IP\u88ab\u5c01\u7981\uff0c\u56e0\u6b64\u5efa\u8b70\u8a2d\u7f6e\u5408\u7406\u7684\u8acb\u6c42\u9593\u9694\u3002<\/p>\n<h2 id=\"%e7%b8%bd%e7%b5%90-iyGWnklPVB\">\u7e3d\u7d50<\/h2>\n<p>\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\u662f\u4e00\u500b\u6709\u6548\u7684\u65b9\u5f0f\uff0c\u53ef\u4ee5\u5e6b\u52a9\u7528\u6236\u9032\u884c\u5e02\u5834\u5206\u6790\u3001\u5167\u5bb9\u5275\u4f5c\u548c\u5b78\u8853\u7814\u7a76\u3002\u901a\u904e\u4f7f\u7528\u722c\u87f2\u6280\u8853\u3001\u6578\u64da\u6e05\u6d17\u548c\u6578\u64da\u5eab\u5b58\u5132\uff0c\u60a8\u53ef\u4ee5\u8f15\u9b06\u5730\u5efa\u7acb\u4e00\u500b\u5b8c\u6574\u7684\u6578\u64da\u5eab\u3002\u82e5\u60a8\u9700\u8981\u7a69\u5b9a\u7684\u6578\u64da\u5b58\u5132\u89e3\u6c7a\u65b9\u6848\uff0c\u8003\u616e\u4f7f\u7528<a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a>\u6216<a href=\"https:\/\/server.hk\">\u4e91\u670d\u52a1\u5668<\/a>\u4f86\u652f\u6301\u60a8\u7684\u6578\u64da\u5eab\u9700\u6c42\uff0c\u78ba\u4fdd\u6578\u64da\u7684\u5b89\u5168\u548c\u9ad8\u6548\u5b58\u53d6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a1\u96c6\u5fae\u4fe1\u516c\u773e\u865f\u6587\u7ae0\u6578\u64da\uff0c\u5efa\u7acb\u5168\u9762\u6578\u64da\u5eab\uff0c\u52a9\u529b\u5167\u5bb9\u5206\u6790\u8207\u5e02\u5834\u7814\u7a76\uff0c\u63d0\u5347\u884c\u696d\u6d1e\u5bdf\u529b\u3002<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-152311","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/152311","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=152311"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/152311\/revisions"}],"predecessor-version":[{"id":152312,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/152311\/revisions\/152312"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=152311"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=152311"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=152311"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}