{"id":6938,"date":"2023-01-30T18:24:17","date_gmt":"2023-01-30T10:24:17","guid":{"rendered":"https:\/\/www.lalimao.com\/?p=6938"},"modified":"2024-02-04T14:54:43","modified_gmt":"2024-02-04T06:54:43","slug":"%e8%83%bd%e6%a8%a1%e6%8b%9f%e6%b5%b7%e5%a4%96%e7%9c%9f%e5%ae%9e%e7%8e%af%e5%a2%83%e7%9a%84%e6%b5%8f%e8%a7%88%e5%99%a8-%e6%8b%89%e5%8a%9b%e7%8c%ab%e6%8c%87%e7%ba%b9%e6%b5%8f%e8%a7%88%e5%99%a8-2","status":"publish","type":"post","link":"https:\/\/www.lalimao.com\/news\/6938.html","title":{"rendered":"Puppeteer\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u6700\u4f73\u5b9e\u8df5"},"content":{"rendered":"\n

\u5728\u73b0\u4ee3\u7684\u7f51\u7edc\u5e94\u7528\u548c\u6570\u636e\u91c7\u96c6\u4e2d\uff0c\u81ea\u52a8\u5316\u5de5\u5177\u7684\u9700\u6c42\u65e5\u76ca\u589e\u957f\u3002Puppeteer\u4f5c\u4e3a\u4e00\u6b3e\u5f3a\u5927\u7684\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u5728Web\u5f00\u53d1\u3001\u6d4b\u8bd5\u548c\u722c\u866b\u7b49\u9886\u57df\u90fd\u5f97\u5230\u4e86\u5e7f\u6cdb\u7684\u5e94\u7528\u3002\u672c\u6587\u5c06\u91cd\u70b9\u4ecb\u7ecdPuppeteer\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u7684\u6700\u4f73\u5b9e\u8df5\uff0c\u540c\u65f6\u7ed3\u5408\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u7279\u6027\uff0c\u63a2\u8ba8\u5982\u4f55\u66f4\u597d\u5730\u5229\u7528\u8fd9\u4e24\u4e2a\u5de5\u5177\u3002<\/p>\n\n\n\n

1. Puppeteer\u7b80\u4ecb<\/h2>\n\n\n\n

Puppeteer\u662f\u7531Google\u5f00\u53d1\u7684\u4e00\u4e2aNode\u5e93\uff0c\u7528\u4e8e\u63a7\u5236Chrome\u6216Chromium\u6d4f\u89c8\u5668\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u5957\u9ad8\u7ea7\u7684API\uff0c\u5141\u8bb8\u7528\u6237\u901a\u8fc7\u4ee3\u7801\u81ea\u52a8\u5b8c\u6210\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u5982\u9875\u9762\u5bfc\u822a\u3001\u6570\u636e\u6293\u53d6\u3001\u8868\u5355\u586b\u5199\u7b49\u3002\u4ee5\u4e0b\u662fPuppeteer\u7684\u4e00\u4e9b\u57fa\u672c\u7528\u6cd5\uff1a<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  const browser = await puppeteer.launch();\n  const page = await browser.newPage();\n  await page.goto('https:\/\/example.com');\n  \/\/ \u5728\u9875\u9762\u4e2d\u6267\u884c\u64cd\u4f5c\n  \/\/ ...\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

2. Puppeteer\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u6700\u4f73\u5b9e\u8df5<\/h2>\n\n\n\n

2.1 \u9875\u9762\u622a\u56fe\u548cPDF\u751f\u6210<\/h3>\n\n\n\n

Puppeteer\u5141\u8bb8\u6211\u4eec\u8f7b\u677e\u5730\u5bf9\u9875\u9762\u8fdb\u884c\u622a\u56fe\u6216\u751f\u6210PDF\u6587\u6863\uff0c\u8fd9\u5728\u7f51\u9875\u6d4b\u8bd5\u548c\u76d1\u63a7\u4e2d\u975e\u5e38\u6709\u7528\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff1a<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  const browser = await puppeteer.launch();\n  const page = await browser.newPage();\n  await page.goto('https:\/\/example.com');\n\n  \/\/ \u751f\u6210\u9875\u9762\u622a\u56fe\n  await page.screenshot({ path: 'example.png' });\n\n  \/\/ \u751f\u6210PDF\u6587\u6863\n  await page.pdf({ path: 'example.pdf', format: 'A4' });\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

2.2 \u8868\u5355\u586b\u5199\u548c\u63d0\u4ea4<\/h3>\n\n\n\n

Puppeteer\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u5728\u8868\u5355\u4e2d\u7684\u8f93\u5165\u548c\u70b9\u51fb\u64cd\u4f5c\uff0c\u65b9\u4fbf\u5730\u8fdb\u884c\u81ea\u52a8\u5316\u7684\u8868\u5355\u63d0\u4ea4\uff1a<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  const browser = await puppeteer.launch();\n  const page = await browser.newPage();\n  await page.goto('https:\/\/example.com');\n\n  \/\/ \u5728\u8868\u5355\u4e2d\u586b\u5199\u5185\u5bb9\n  await page.type('#username', 'your_username');\n  await page.type('#password', 'your_password');\n\n  \/\/ \u63d0\u4ea4\u8868\u5355\n  await page.click('input[type=submit]');\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

2.3 \u9875\u9762\u4ea4\u4e92\u548c\u4e8b\u4ef6\u6a21\u62df<\/h3>\n\n\n\n

Puppeteer\u652f\u6301\u6a21\u62df\u7528\u6237\u7684\u4ea4\u4e92\u884c\u4e3a\u548c\u4e8b\u4ef6\uff0c\u4f8b\u5982\u9f20\u6807\u70b9\u51fb\u3001\u952e\u76d8\u8f93\u5165\u7b49\uff0c\u53ef\u4ee5\u66f4\u5168\u9762\u5730\u6d4b\u8bd5\u548c\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff1a<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  const browser = await puppeteer.launch();\n  const page = await browser.newPage();\n  await page.goto('https:\/\/example.com');\n\n  \/\/ \u6a21\u62df\u70b9\u51fb\u6309\u94ae\n  await page.click('#myButton');\n\n  \/\/ \u6a21\u62df\u952e\u76d8\u8f93\u5165\n  await page.type('input[type=text]', 'Hello, Puppeteer!');\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

3. Puppeteer\u4e0e\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u7ed3\u5408\u5e94\u7528<\/h2>\n\n\n\n

\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u4f5c\u4e3a\u4e00\u6b3e\u591a\u529f\u80fd\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u4e3a\u7528\u6237\u63d0\u4f9b\u72ec\u7acb\u7684\u6d4f\u89c8\u5668\u6307\u7eb9\u548cIP\u767b\u5f55\u73af\u5883\uff0c\u9002\u7528\u4e8e\u8de8\u5883\u7535\u5546\u3001\u793e\u4ea4\u5a92\u4f53\u8425\u9500\u7b49\u591a\u8d26\u53f7\u8fd0\u8425\u9700\u6c42\u3002\u7ed3\u5408Puppeteer\uff0c\u6211\u4eec\u53ef\u4ee5\u66f4\u597d\u5730\u5b9e\u73b0\u81ea\u52a8\u5316\u4efb\u52a1\uff0c\u540c\u65f6\u5229\u7528\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u7279\u6027\u63d0\u5347\u5b89\u5168\u6027\u548c\u6548\u7387\u3002<\/p>\n\n\n\n

3.1 \u5229\u7528\u72ec\u7acbIP\u8fdb\u884c\u722c\u866b\u548c\u6570\u636e\u91c7\u96c6<\/h3>\n\n\n\n

\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u63d0\u4f9b\u4e86\u72ec\u7acb\u7684IP\u767b\u5f55\u73af\u5883\uff0c\u8fd9\u5bf9\u4e8e\u9700\u8981\u8fdb\u884c\u5927\u89c4\u6a21\u6570\u636e\u91c7\u96c6\u548c\u722c\u866b\u4efb\u52a1\u7684\u7528\u6237\u975e\u5e38\u6709\u7528\u3002\u901a\u8fc7\u7ed3\u5408Puppeteer\uff0c\u6211\u4eec\u53ef\u4ee5\u7f16\u5199\u81ea\u52a8\u5316\u811a\u672c\uff0c\u5229\u7528\u4e0d\u540c\u7684IP\u8fdb\u884c\u5e76\u884c\u7684\u6570\u636e\u91c7\u96c6\uff0c\u63d0\u9ad8\u6548\u7387\u7684\u540c\u65f6\u907f\u514d\u88ab\u76ee\u6807\u7f51\u7ad9\u5c01\u7981IP\u7684\u98ce\u9669\u3002<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  \/\/ \u4f7f\u7528\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u72ec\u7acbIP\u767b\u5f55\u73af\u5883\n  const browser = await puppeteer.launch({\n    args: ['--proxy-server=http:\/\/your_lum_proxy_ip:your_lum_proxy_port']\n  });\n  const page = await browser.newPage();\n\n  \/\/ \u5728\u6b64\u6267\u884c\u6570\u636e\u91c7\u96c6\u64cd\u4f5c\n  \/\/ ...\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

3.2 \u5b89\u5168\u5730\u8fdb\u884c\u591a\u8d26\u53f7\u64cd\u4f5c\u548c\u793e\u4ea4\u5a92\u4f53\u8425\u9500<\/h3>\n\n\n\n

\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u591a\u8d26\u53f7\u8fd0\u8425\u7279\u6027\u975e\u5e38\u9002\u7528\u4e8e\u8de8\u5883\u7535\u5546\u548c\u793e\u4ea4\u5a92\u4f53\u8425\u9500\u9886\u57df\u3002\u7ed3\u5408Puppeteer\uff0c\u6211\u4eec\u53ef\u4ee5\u7f16\u5199\u81ea\u52a8\u5316\u811a\u672c\uff0c\u5b9e\u73b0\u5728\u4e00\u53f0\u7535\u8111\u4e0a\u540c\u65f6\u591a\u5f00\u6d4f\u89c8\u5668\uff0c\u6bcf\u4e2a\u6d4f\u89c8\u5668\u62e5\u6709\u72ec\u7acb\u7684\u6d4f\u89c8\u5668\u6307\u7eb9\u548cIP\uff0c\u786e\u4fdd\u8d26\u53f7\u7684\u5b89\u5168\u6027\u548c\u7a33\u5b9a\u6027\u3002<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  \/\/ \u4f7f\u7528\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u591a\u8d26\u53f7\u73af\u5883\n  const browser = await puppeteer.launch();\n\n  \/\/ \u6253\u5f00\u591a\u4e2a\u9875\u9762\uff0c\u6bcf\u4e2a\u9875\u9762\u5bf9\u5e94\u4e00\u4e2a\u8d26\u53f7\n  const page1 = await browser.newPage();\n  const page2 = await browser.newPage();\n  \/\/ ...\n\n  \/\/ \u5728\u6bcf\u4e2a\u9875\u9762\u6267\u884c\u8d26\u53f7\u64cd\u4f5c\u548c\u793e\u4ea4\u5a92\u4f53\u8425\u9500\u4efb\u52a1\n  \/\/ ...\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

3.3 \u9632\u5173\u8054\u6279\u91cf\u7ba1\u7406\u548c\u6ce8\u518c\u8d26\u53f7<\/h3>\n\n\n\n

\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u63d0\u4f9b\u4e86\u9632\u5173\u8054\u6279\u91cf\u7ba1\u7406\u529f\u80fd\uff0c\u53ef\u4ee5\u6709\u6548\u9632\u6b62\u8d26\u53f7\u4e4b\u95f4<\/p>\n\n\n\n

\u7684\u5173\u8054\u6027\uff0c\u63d0\u5347\u8d26\u53f7\u7684\u5b89\u5168\u6027\u3002\u7ed3\u5408Puppeteer\uff0c\u6211\u4eec\u53ef\u4ee5\u7f16\u5199\u81ea\u52a8\u5316\u811a\u672c\uff0c\u5b9e\u73b0\u6279\u91cf\u6ce8\u518c\u8d26\u53f7\u5e76\u8fdb\u884c\u9632\u5173\u8054\u7ba1\u7406\u3002<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  \/\/ \u4f7f\u7528\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u9632\u5173\u8054\u6279\u91cf\u7ba1\u7406\u73af\u5883\n  const browser = await puppeteer.launch();\n  const page = await browser.newPage();\n\n  \/\/ \u6279\u91cf\u6ce8\u518c\u8d26\u53f7\n  for (let i = 0; i < 10; i++) {\n    await page.goto('https:\/\/example.com\/register');\n    \/\/ \u5728\u6ce8\u518c\u9875\u9762\u586b\u5199\u4fe1\u606f\n    \/\/ ...\n    await page.click('input[type=submit]');\n    \/\/ \u8fdb\u884c\u9632\u5173\u8054\u7ba1\u7406\n    \/\/ ...\n  }\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

4. \u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u5728Puppeteer\u4e2d\u7684\u5b9e\u9645\u5e94\u7528\u6848\u4f8b<\/h2>\n\n\n\n

\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u4e0ePuppeteer\u7684\u7ed3\u5408\uff0c\u53ef\u4ee5\u5e94\u5bf9\u5404\u79cd\u590d\u6742\u7684\u81ea\u52a8\u5316\u4efb\u52a1\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b9e\u9645\u5e94\u7528\u6848\u4f8b\uff1a<\/p>\n\n\n\n

\u5047\u8bbe\u6211\u4eec\u9700\u8981\u5728\u4e9a\u9a6c\u900a\u4e0a\u8fdb\u884c\u5546\u54c1\u4fe1\u606f\u7684\u6279\u91cf\u91c7\u96c6\uff0c\u540c\u65f6\u786e\u4fdd\u6bcf\u4e2a\u91c7\u96c6\u4efb\u52a1\u90fd\u5177\u6709\u72ec\u7acb\u7684IP\u548c\u6d4f\u89c8\u5668\u6307\u7eb9\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Puppeteer\u7f16\u5199\u4e00\u4e2a\u81ea\u52a8\u5316\u811a\u672c\uff0c\u7ed3\u5408\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u72ec\u7acbIP\u7279\u6027\uff0c\u5b9e\u73b0\u9ad8\u6548\u800c\u5b89\u5168\u7684\u5546\u54c1\u4fe1\u606f\u91c7\u96c6\u3002<\/p>\n\n\n\n

const puppeteer = require('puppeteer');\n\n(async () => {\n  \/\/ \u4f7f\u7528\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u72ec\u7acbIP\u767b\u5f55\u73af\u5883\n  const browser = await puppeteer.launch({\n    args: ['--proxy-server=http:\/\/your_lum_proxy_ip:your_lum_proxy_port']\n  });\n\n  \/\/ \u6279\u91cf\u6253\u5f00\u9875\u9762\uff0c\u6bcf\u4e2a\u9875\u9762\u5bf9\u5e94\u4e00\u4e2a\u5546\u54c1\u94fe\u63a5\n  const productLinks = ['https:\/\/amazon.com\/product1', 'https:\/\/amazon.com\/product2', \/* ... *\/];\n  const pages = await Promise.all(productLinks.map(link => browser.newPage()));\n\n  \/\/ \u5728\u6bcf\u4e2a\u9875\u9762\u6267\u884c\u5546\u54c1\u4fe1\u606f\u91c7\u96c6\u64cd\u4f5c\n  for (let i = 0; i < productLinks.length; i++) {\n    const page = pages[i];\n    await page.goto(productLinks[i]);\n\n    \/\/ \u91c7\u96c6\u5546\u54c1\u4fe1\u606f\n    \/\/ ...\n\n    \/\/ \u6bcf\u4e2a\u91c7\u96c6\u4efb\u52a1\u90fd\u6709\u72ec\u7acb\u7684IP\u548c\u6d4f\u89c8\u5668\u6307\u7eb9\n    \/\/ ...\n  }\n\n  await browser.close();\n})();<\/code><\/pre>\n\n\n\n

\u7ed3\u8bed<\/h2>\n\n\n\n

\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u6df1\u5165\u4e86\u89e3\u4e86Puppeteer\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u7684\u6700\u4f73\u5b9e\u8df5\uff0c\u5e76\u63a2\u8ba8\u4e86\u4e0e\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\u7684\u7ed3\u5408\u5e94\u7528\u3002\u8fd9\u79cd\u7ed3\u5408\u53ef\u4ee5\u4e3a\u7528\u6237\u63d0\u4f9b\u66f4\u5b89\u5168\u3001\u9ad8\u6548\u7684\u81ea\u52a8\u5316\u89e3\u51b3\u65b9\u6848\uff0c\u7279\u522b\u662f\u5728\u8de8\u5883\u7535\u5546\u3001\u793e\u4ea4\u5a92\u4f53\u8425\u9500\u7b49\u9886\u57df\u3002\u5229\u7528Puppeteer\u548c\u62c9\u529b\u732b\u6307\u7eb9\u6d4f\u89c8\u5668\uff0c\u7528\u6237\u53ef\u4ee5\u66f4\u7075\u6d3b\u5730\u5e94\u5bf9\u590d\u6742\u7684\u81ea\u52a8\u5316\u4efb\u52a1\uff0c\u63d0\u5347\u5de5\u4f5c\u6548\u7387\uff0c\u786e\u4fdd\u8d26\u53f7\u7684\u5b89\u5168\u6027\u3002\u5982\u679c\u60a8\u5c1a\u672a\u5c1d\u8bd5\u8fc7\u8fd9\u4e24\u4e2a\u5de5\u5177\u7684\u7ed3\u5408\u5e94\u7528\uff0c\u4e0d\u59a8\u5728\u5b9e\u9645\u573a\u666f\u4e2d\u8fdb\u884c\u5c1d\u8bd5\uff0c\u5e76\u4f53\u9a8c\u5176\u5353\u8d8a\u6027\u80fd\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"

\u5728\u73b0\u4ee3\u7684\u7f51\u7edc\u5e94\u7528\u548c\u6570\u636e\u91c7\u96c6\u4e2d\uff0c\u81ea\u52a8\u5316\u5de5\u5177\u7684\u9700\u6c42\u65e5\u76ca\u589e\u957f\u3002Puppeteer\u4f5c\u4e3a\u4e00\u6b3e\u5f3a\u5927\u7684\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u5728W […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[49,39,38],"tags":[],"class_list":["post-6938","post","type-post","status-publish","format-standard","hentry","category-49","category-anonymous-browser","category-private-browser"],"_links":{"self":[{"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/posts\/6938","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/comments?post=6938"}],"version-history":[{"count":2,"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/posts\/6938\/revisions"}],"predecessor-version":[{"id":11434,"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/posts\/6938\/revisions\/11434"}],"wp:attachment":[{"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/media?parent=6938"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/categories?post=6938"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lalimao.com\/news\/wp-json\/wp\/v2\/tags?post=6938"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}