{"id":561,"date":"2024-12-26T23:04:17","date_gmt":"2024-12-26T15:04:17","guid":{"rendered":"https:\/\/www.laixuexila.com\/?p=561"},"modified":"2024-12-26T23:04:17","modified_gmt":"2024-12-26T15:04:17","slug":"%e4%bd%bf%e7%94%a8-python-%e6%8a%93%e5%8f%96%e5%8a%a8%e6%80%81%e7%bd%91%e9%a1%b5%ef%bc%9aselenium%e3%80%81playwright%e3%80%81requests-html-%e5%92%8c-pyppeteer-%e7%9a%84%e5%af%b9%e6%af%94%e4%b8%8e","status":"publish","type":"post","link":"https:\/\/www.laixuexila.com\/index.php\/2024\/12\/26\/%e4%bd%bf%e7%94%a8-python-%e6%8a%93%e5%8f%96%e5%8a%a8%e6%80%81%e7%bd%91%e9%a1%b5%ef%bc%9aselenium%e3%80%81playwright%e3%80%81requests-html-%e5%92%8c-pyppeteer-%e7%9a%84%e5%af%b9%e6%af%94%e4%b8%8e\/","title":{"rendered":"\u4f7f\u7528 Python \u6293\u53d6\u52a8\u6001\u7f51\u9875\uff1aSelenium\u3001Playwright\u3001requests-html \u548c Pyppeteer \u7684\u5bf9\u6bd4\u4e0e\u5e94\u7528"},"content":{"rendered":"\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\">\u6293\u53d6\u52a8\u6001\u7f51\u9875\uff08\u5373\u901a\u8fc7 JavaScript \u6e32\u67d3\u5185\u5bb9\u7684\u7f51\u9875\uff09\u5728 Python \u4e2d\u7684\u4f20\u7edf\u6293\u53d6\u65b9\u6cd5\uff08\u5982 <code>requests<\/code> \u6216 <code>BeautifulSoup<\/code>\uff09\u901a\u5e38\u65e0\u6cd5\u6293\u53d6\u901a\u8fc7 JavaScript \u52a8\u6001\u751f\u6210\u7684\u5185\u5bb9\u3002\u4e3a\u4e86\u5904\u7406\u8fd9\u7c7b\u7f51\u9875\uff0c\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e9b\u5de5\u5177\u548c\u5e93\uff0c\u5b83\u4eec\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u7684\u884c\u4e3a\u5e76\u6293\u53d6\u6700\u7ec8\u6e32\u67d3\u7684\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee5\u4e0b\u662f\u5e38\u89c1\u7684\u51e0\u79cd\u65b9\u6cd5\u6765\u4f7f\u7528 Python \u6293\u53d6\u52a8\u6001\u7f51\u9875\uff1a<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">1. <strong>\u4f7f\u7528 Selenium + WebDriver<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Selenium \u662f\u4e00\u4e2a\u53ef\u4ee5\u81ea\u52a8\u5316\u7f51\u9875\u6d4f\u89c8\u5668\u64cd\u4f5c\u7684\u5de5\u5177\uff0c\u652f\u6301\u4e0e\u7f51\u9875\u4e2d\u7684 JavaScript \u4ea4\u4e92\u3002\u4f60\u53ef\u4ee5\u901a\u8fc7 Selenium \u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u52a0\u8f7d JavaScript \u6e32\u67d3\u7684\u5185\u5bb9\uff0c\u5e76\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6570\u636e\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u5b89\u88c5 Selenium \u548c WebDriver\uff1a<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u9996\u5148\u9700\u8981\u5b89\u88c5 Selenium \u548c\u4e00\u4e2a\u6d4f\u89c8\u5668\u9a71\u52a8\uff08\u5982 ChromeDriver\uff09\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>pip install selenium<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u7136\u540e\u4e0b\u8f7d\u4e0e\u6d4f\u89c8\u5668\u7248\u672c\u5339\u914d\u7684 WebDriver\uff08\u5982 <a href=\"https:\/\/sites.google.com\/chromium.org\/driver\/\">ChromeDriver<\/a>\uff09\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u793a\u4f8b\uff1a\u4f7f\u7528 Selenium \u6293\u53d6\u52a8\u6001\u7f51\u9875<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>from selenium import webdriver\nfrom selenium.webdriver.common.by import By\nimport time\n\n# \u8bbe\u7f6e Chrome \u6d4f\u89c8\u5668\u9a71\u52a8\ndriver = webdriver.Chrome(executable_path='\/path\/to\/chromedriver')  # \u66ff\u6362\u4e3a\u5b9e\u9645\u8def\u5f84\n\n# \u6253\u5f00\u7f51\u9875\ndriver.get('https:\/\/example.com')  # \u66ff\u6362\u4e3a\u5b9e\u9645\u76ee\u6807\u7f51\u9875\n\n# \u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6bd5\uff0c\u65f6\u95f4\u53ef\u4ee5\u6839\u636e\u9700\u8981\u8c03\u6574\ntime.sleep(3)\n\n# \u83b7\u53d6\u7f51\u9875\u4e2d\u52a8\u6001\u6e32\u67d3\u7684\u5143\u7d20\nelement = driver.find_element(By.XPATH, '\/\/div&#91;@class=\"example-class\"]')\nprint(element.text)\n\n# \u5173\u95ed\u6d4f\u89c8\u5668\ndriver.quit()<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c<code>driver.get()<\/code> \u4f1a\u52a0\u8f7d\u7f51\u9875\uff0c<code>time.sleep(3)<\/code> \u4f1a\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\uff0c\u4e4b\u540e\u4f60\u53ef\u4ee5\u50cf\u64cd\u4f5c\u666e\u901a\u7f51\u9875\u4e00\u6837\u6293\u53d6\u5143\u7d20\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u4f7f\u7528 JavaScript \u6e32\u67d3\u540e\u7684\u9875\u9762<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u6709\u65f6\u5019\uff0c\u9875\u9762\u5185\u5bb9\u662f\u901a\u8fc7 JavaScript \u52a8\u6001\u6e32\u67d3\u7684\u3002\u4f7f\u7528 Selenium\uff0c\u4f60\u53ef\u4ee5\u83b7\u53d6\u52a0\u8f7d\u5b8c\u6210\u540e\u7684\u5b8c\u6574 HTML \u5185\u5bb9\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u83b7\u53d6\u9875\u9762\u6e32\u67d3\u540e\u7684 HTML \u5185\u5bb9\nhtml_content = driver.page_source<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">2. <strong>\u4f7f\u7528 Playwright<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Playwright \u662f\u53e6\u4e00\u4e2a\u5f3a\u5927\u7684\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u5b83\u652f\u6301 Chromium\u3001Firefox \u548c WebKit \u7684\u6d4f\u89c8\u5668\uff0c\u53ef\u4ee5\u4e0e JavaScript \u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u8fdb\u884c\u4ea4\u4e92\uff0c\u5e76\u83b7\u53d6\u6e32\u67d3\u540e\u7684\u5185\u5bb9\u3002Playwright \u6bd4 Selenium \u66f4\u52a0\u9ad8\u6548\u548c\u7a33\u5b9a\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u5b89\u88c5 Playwright<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>pip install playwright<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">Playwright \u4f1a\u81ea\u52a8\u5b89\u88c5\u6240\u9700\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\u7a0b\u5e8f\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u793a\u4f8b\uff1a\u4f7f\u7528 Playwright \u6293\u53d6\u52a8\u6001\u7f51\u9875<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>from playwright.sync_api import sync_playwright\n\nwith sync_playwright() as p:\n    # \u542f\u52a8\u6d4f\u89c8\u5668\n    browser = p.chromium.launch(headless=True)  # \u8bbe\u7f6e\u4e3a False \u53ef\u4ee5\u663e\u793a\u6d4f\u89c8\u5668\n    page = browser.new_page()\n\n    # \u6253\u5f00\u76ee\u6807\u7f51\u9875\n    page.goto('https:\/\/example.com')\n\n    # \u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\n    page.wait_for_selector('div.example-class')\n\n    # \u83b7\u53d6\u52a8\u6001\u6e32\u67d3\u7684\u5185\u5bb9\n    content = page.text_content('div.example-class')\n    print(content)\n\n    # \u5173\u95ed\u6d4f\u89c8\u5668\n    browser.close()<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0cPlaywright \u7528 <code>page.goto()<\/code> \u6253\u5f00\u7f51\u9875\uff0c<code>page.wait_for_selector()<\/code> \u7b49\u5f85\u7279\u5b9a\u5143\u7d20\u52a0\u8f7d\u5b8c\u6210\u3002\u4f60\u53ef\u4ee5\u7528 <code>page.text_content()<\/code> \u6216\u5176\u4ed6\u65b9\u6cd5\u63d0\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">3. <strong>\u4f7f\u7528 Requests-HTML<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><code>requests-html<\/code> \u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u5e93\uff0c\u5b83\u57fa\u4e8e PyQuery \u548c Chromium\uff08\u901a\u8fc7 Pyppeteer\uff09\u5b9e\u73b0\u4e86\u7c7b\u4f3c\u6d4f\u89c8\u5668\u7684\u529f\u80fd\uff0c\u53ef\u4ee5\u76f4\u63a5\u6e32\u67d3 JavaScript \u5185\u5bb9\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u5b89\u88c5 requests-html<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>pip install requests-html<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">\u793a\u4f8b\uff1a\u4f7f\u7528 requests-html \u6293\u53d6\u52a8\u6001\u7f51\u9875<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>from requests_html import HTMLSession\n\n# \u521b\u5efa\u4e00\u4e2a\u4f1a\u8bdd\nsession = HTMLSession()\n\n# \u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\nresponse = session.get('https:\/\/example.com')\n\n# \u6e32\u67d3 JavaScript \u5185\u5bb9\nresponse.html.render()\n\n# \u83b7\u53d6\u6e32\u67d3\u540e\u7684 HTML \u5185\u5bb9\nhtml_content = response.html.html\nprint(html_content)\n\n# \u83b7\u53d6\u67d0\u4e2a\u7279\u5b9a\u5143\u7d20\u7684\u6587\u672c\u5185\u5bb9\nelement = response.html.find('.example-class', first=True)\nprint(element.text)<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c<code>response.html.render()<\/code> \u4f1a\u4f7f\u7528 Chromium \u6e32\u67d3 JavaScript \u52a8\u6001\u5185\u5bb9\u3002\u7136\u540e\uff0c\u4f60\u53ef\u4ee5\u50cf\u5904\u7406\u666e\u901a HTML \u4e00\u6837\u63d0\u53d6\u6e32\u67d3\u540e\u7684\u5185\u5bb9\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">4. <strong>\u4f7f\u7528 Pyppeteer<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Pyppeteer \u662f Python \u4e2d\u5bf9 Puppeteer \u7684\u5c01\u88c5\uff0cPuppeteer \u662f\u4e00\u4e2a\u57fa\u4e8e Chromium \u7684\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u53ef\u4ee5\u5b8c\u5168\u6a21\u62df\u6d4f\u89c8\u5668\u7684\u884c\u4e3a\uff0c\u9002\u5408\u6293\u53d6\u52a8\u6001\u7f51\u9875\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u5b89\u88c5 Pyppeteer<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>pip install pyppeteer<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">\u793a\u4f8b\uff1a\u4f7f\u7528 Pyppeteer \u6293\u53d6\u52a8\u6001\u7f51\u9875<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>import asyncio\nfrom pyppeteer import launch\n\nasync def main():\n    # \u542f\u52a8 Chromium \u6d4f\u89c8\u5668\n    browser = await launch(headless=True)\n    page = await browser.newPage()\n\n    # \u6253\u5f00\u76ee\u6807\u7f51\u9875\n    await page.goto('https:\/\/example.com')\n\n    # \u7b49\u5f85\u9875\u9762\u52a0\u8f7d\n    await page.waitForSelector('div.example-class')\n\n    # \u83b7\u53d6\u7f51\u9875\u5185\u5bb9\n    content = await page.evaluate('document.querySelector(\"div.example-class\").innerText')\n    print(content)\n\n    # \u5173\u95ed\u6d4f\u89c8\u5668\n    await browser.close()\n\n# \u8fd0\u884c\u5f02\u6b65\u4e8b\u4ef6\nasyncio.get_event_loop().run_until_complete(main())<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0cPyppeteer \u901a\u8fc7 <code>launch()<\/code> \u542f\u52a8 Chromium \u6d4f\u89c8\u5668\uff0c<code>page.evaluate()<\/code> \u53ef\u4ee5\u6267\u884c JavaScript \u4ee3\u7801\u83b7\u53d6\u7f51\u9875\u4e2d\u7684\u5143\u7d20\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u603b\u7ed3<\/h3>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Selenium<\/strong>\uff1a\u9002\u5408\u81ea\u52a8\u5316\u6d4f\u89c8\u5668\uff0c\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u6293\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002\u53ef\u4ee5\u4e0e JavaScript \u8fdb\u884c\u4ea4\u4e92\uff0c\u652f\u6301\u591a\u79cd\u6d4f\u89c8\u5668\u3002<\/li>\n\n\n\n<li><strong>Playwright<\/strong>\uff1a\u66f4\u73b0\u4ee3\u3001\u9ad8\u6548\u7684\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u652f\u6301 Chromium\u3001Firefox \u548c WebKit\uff0c\u6027\u80fd\u66f4\u597d\uff0c\u9002\u7528\u4e8e\u52a8\u6001\u7f51\u9875\u6293\u53d6\u3002<\/li>\n\n\n\n<li><strong>requests-html<\/strong>\uff1a\u7b80\u5355\u4e14\u9ad8\u6548\uff0c\u4f7f\u7528\u5185\u7f6e\u7684\u6d4f\u89c8\u5668\u5f15\u64ce\u6765\u6e32\u67d3\u52a8\u6001\u7f51\u9875\uff0c\u9002\u5408\u6293\u53d6\u57fa\u4e8e JavaScript \u6e32\u67d3\u7684\u5185\u5bb9\u3002<\/li>\n\n\n\n<li><strong>Pyppeteer<\/strong>\uff1a\u57fa\u4e8e Puppeteer \u7684 Python \u5c01\u88c5\uff0c\u9002\u7528\u4e8e\u9700\u8981\u9ad8\u7cbe\u5ea6\u6d4f\u89c8\u5668\u63a7\u5236\u7684\u4efb\u52a1\u3002<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">\u9009\u62e9\u5de5\u5177\u65f6\uff0c\u53ef\u4ee5\u6839\u636e\u4efb\u52a1\u7684\u590d\u6742\u6027\u548c\u5bf9\u6027\u80fd\u7684\u8981\u6c42\u6765\u51b3\u5b9a\u4f7f\u7528\u54ea\u79cd\u65b9\u6848\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6293\u53d6\u52a8\u6001\u7f51\u9875\uff08\u5373\u901a\u8fc7 JavaScript \u6e32\u67d3\u5185\u5bb9\u7684\u7f51\u9875\uff09\u5728 Python \u4e2d\u7684\u4f20\u7edf\u6293\u53d6\u65b9\u6cd5\uff08\u5982 reque [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[54],"tags":[],"class_list":["post-561","post","type-post","status-publish","format-standard","hentry","category-python"],"_links":{"self":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/561","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/comments?post=561"}],"version-history":[{"count":1,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/561\/revisions"}],"predecessor-version":[{"id":562,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/561\/revisions\/562"}],"wp:attachment":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/media?parent=561"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/categories?post=561"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/tags?post=561"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}