{"id":164847,"date":"2024-05-08T15:03:42","date_gmt":"2024-05-08T07:03:42","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/164847.html"},"modified":"2024-05-08T15:03:49","modified_gmt":"2024-05-08T07:03:49","slug":"python-%e7%88%ac%e8%99%ab-%e5%a6%82%e4%bd%95%e8%8e%b7%e5%8f%96javascript%e8%bf%94%e5%9b%9e%e7%9a%84%e5%93%8d%e5%ba%94%e5%86%85%e5%ae%b9","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/164847.html","title":{"rendered":"Python \u722c\u866b \u5982\u4f55\u83b7\u53d6javascript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9"},"content":{"rendered":"<p style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/26231759\/228e45d6-2b8a-40f7-8ced-c273aef83656.webp\" alt=\"Python \u722c\u866b \u5982\u4f55\u83b7\u53d6javascript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9\" \/><\/p>\n<p><p>\u83b7\u53d6JavaScript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9\u662fPython\u722c\u866b\u5f00\u53d1\u4e2d\u7684\u4e00\u9879\u9ad8\u7ea7\u548c\u5fc5\u5907\u6280\u80fd\uff0c\u56e0\u4e3a\u8bb8\u591a\u73b0\u4ee3\u7f51\u7ad9\u548c\u5e94\u7528\u90fd\u4f7f\u7528JavaScript\u6765\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u3002<strong>\u8981\u6709\u6548\u5730\u6267\u884c\u8fd9\u4e00\u64cd\u4f5c\uff0c\u4e3b\u8981\u7b56\u7565\u5305\u62ec\u4f7f\u7528Selenium\u3001Pyppeteer\u3001Scrapy\u7ed3\u5408Splash<\/strong>\u3002\u8fd9\u5176\u4e2d\uff0c<strong>Selenium\u7684\u4f7f\u7528\u5c24\u4e3a\u7a81\u51fa<\/strong>\uff0c\u56e0\u4e3a\u5b83\u4e0d\u4ec5\u6a21\u62df\u4e86\u771f\u5b9e\u7528\u6237\u7684\u884c\u4e3a\uff0c\u8fd8\u80fd\u5904\u7406\u7f51\u9875\u4e0a\u7684JavaScript\u4ee3\u7801\u3002<\/p>\n<\/p>\n<hr>\n<p><h3>\u4e00\u3001\u4f7f\u7528SELENIUM<\/h3>\n<\/p>\n<p><p>Selenium\u662f\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316\u7f51\u9875\u6d4b\u8bd5\u7684\u5de5\u5177\uff0c\u8be5\u5de5\u5177\u63d0\u4f9b\u4e86\u4e00\u5957\u5b8c\u6574\u7684API\u6765\u6a21\u62df\u7528\u6237\u5728\u7f51\u9875\u4e0a\u7684\u5404\u79cd\u64cd\u4f5c\u3002\u901a\u8fc7WebDriver\uff0cSelenium\u542f\u52a8\u5b9e\u9645\u7684\u6d4f\u89c8\u5668\u5b9e\u4f8b\uff0c\u8fd9\u610f\u5473\u7740\u5b83\u80fd\u591f\u4ee5\u771f\u5b9e\u7528\u6237\u7684\u89c6\u89d2\u6267\u884cJavaScript\u4ee3\u7801\u5e76\u83b7\u53d6\u52a8\u6001\u751f\u6210\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u5b89\u88c5Selenium\u4e0e\u6d4f\u89c8\u5668\u9a71\u52a8\u662f\u524d\u63d0\u3002\u4f60\u9700\u8981\u6839\u636e\u6240\u4f7f\u7528\u7684\u6d4f\u89c8\u5668\u7c7b\u578b\uff08\u5982Chrome\u3001Firefox\u7b49\uff09\u4e0b\u8f7d\u5bf9\u5e94\u7684\u9a71\u52a8\uff0c\u7136\u540e\u5b89\u88c5Selenium\u5e93\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4f7f\u7528Selenium\u83b7\u53d6JavaScript\u751f\u6210\u7684\u5185\u5bb9\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u5bfc\u5165Selenium\u7684WebDriver\u3002<\/li>\n<li>\u5b9e\u4f8b\u5316\u4e00\u4e2a\u6d4f\u89c8\u5668\u5bf9\u8c61\u3002<\/li>\n<li>\u901a\u8fc7\u6d4f\u89c8\u5668\u5bf9\u8c61\u8bbf\u95ee\u7f51\u9875\u3002<\/li>\n<li>\u7b49\u5f85JavaScript\u52a0\u8f7d\u5b8c\u6210\u3002<\/li>\n<li>\u901a\u8fc7Selenium\u63d0\u4f9b\u7684API\u83b7\u53d6\u9875\u9762\u6e90\u7801\u6216\u7279\u5b9a\u5143\u7d20\u3002<\/li>\n<\/ol>\n<p><p>\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>import time<\/p>\n<h2><strong>\u5b9e\u4f8b\u5316Chrome\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver = webdriver.Chrome(&#039;\/path\/to\/chromedriver&#039;)<\/p>\n<h2><strong>\u6253\u5f00\u7f51\u9875<\/strong><\/h2>\n<p>driver.get(&#039;http:\/\/example.com&#039;)<\/p>\n<h2><strong>\u7b49\u5f85JavaScript\u52a0\u8f7d<\/strong><\/h2>\n<p>time.sleep(5) # \u901a\u5e38\u4f7f\u7528\u663e\u5f0f\u6216\u9690\u5f0f\u7b49\u5f85\u66f4\u4e3a\u5408\u7406<\/p>\n<h2><strong>\u83b7\u53d6\u9875\u9762\u6e90\u7801<\/strong><\/h2>\n<p>page_source = driver.page_source<\/p>\n<p>print(page_source)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4f7f\u7528Selenium\u7684\u4e00\u4e2a\u4e3b\u8981\u6311\u6218\u662f\u5904\u7406\u52a0\u8f7d\u65f6\u95f4\u3002Web\u5e94\u7528\u53ef\u80fd\u9700\u8981\u4e0d\u786e\u5b9a\u7684\u65f6\u95f4\u6765\u5b8c\u6210\u6570\u636e\u7684\u52a8\u6001\u52a0\u8f7d\uff0c\u56e0\u6b64\uff0c\u5408\u7406\u4f7f\u7528WebDriver\u63d0\u4f9b\u7684\u7b49\u5f85\u673a\u5236\uff0c\u5982\u663e\u5f0f\u7b49\u5f85\uff08<code>WebDriverW<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>t<\/code>\uff09\u4e0e\u9690\u5f0f\u7b49\u5f85\uff0c\u662f\u4fdd\u8bc1\u80fd\u591f\u6210\u529f\u6293\u53d6\u5230\u6570\u636e\u7684\u5173\u952e\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528PYPPETEER<\/h3>\n<\/p>\n<p><p>Pyppeteer\u662fPython\u754c\u7684Puppeteer\uff0c\u4e00\u4e2a\u7528\u4e8e\u63a7\u5236\u65e0\u5934\u6d4f\u89c8\u5668\u7684\u5e93\uff0c\u5176\u901a\u8fc7DevTools\u534f\u8bae\u63a7\u5236Chromium\u6216Chrome\u3002Pyppeteer\u5929\u7136\u652f\u6301\u73b0\u4ee3web\u6280\u672f\uff0c\u6545\u800c\u9002\u5408\u83b7\u53d6JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u5b89\u88c5Pyppeteer\u975e\u5e38\u7b80\u5355\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install pyppeteer<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0eSelenium\u7c7b\u4f3c\uff0cPyppeteer\u7684\u4f7f\u7528\u6d41\u7a0b\u6db5\u76d6\u4e86\u542f\u52a8\u6d4f\u89c8\u5668\u3001\u6253\u5f00\u7f51\u9875\u3001\u7b49\u5f85\u5185\u5bb9\u52a0\u8f7d\u53ca\u83b7\u53d6\u6570\u636e\u3002\u4e0d\u540c\u4e4b\u5904\u5728\u4e8e\u5b83\u9ed8\u8ba4\u64cd\u4f5c\u65e0\u5934\u6d4f\u89c8\u5668\uff0c\u5bf9\u4e8e\u6279\u91cf\u6216\u540e\u53f0\u722c\u53d6\u4efb\u52a1\u66f4\u4e3a\u4fbf\u6377\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import asyncio<\/p>\n<p>from pyppeteer import launch<\/p>\n<p>async def main():<\/p>\n<p>    browser = await launch()<\/p>\n<p>    page = await browser.newPage()<\/p>\n<p>    await page.goto(&#039;http:\/\/example.com&#039;)<\/p>\n<p>    # \u7b49\u5f85\u7f51\u7edc\u7a7a\u95f2\uff0c\u786e\u4fddJS\u52a0\u8f7d\u5b8c\u6210<\/p>\n<p>    await page.waitForNavigation({&#039;waitUntil&#039;: &#039;networkidle0&#039;})<\/p>\n<p>    content = await page.content()<\/p>\n<p>    print(content)<\/p>\n<p>    await browser.close()<\/p>\n<p>asyncio.run(main())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u7ed3\u5408SCRAPY\u4e0eSPLASH<\/h3>\n<\/p>\n<p><p>Scrapy\u662f\u4e00\u4e2a\u5feb\u901f\u9ad8\u6548\u7684\u7f51\u9875\u722c\u53d6\u6846\u67b6\uff0c\u800cSplash\u5219\u662f\u4e00\u4e2a\u5e26\u6709HTTP API\u7684\u8f7b\u91cf\u7ea7\u6d4f\u89c8\u5668\u6e32\u67d3\u670d\u52a1\uff0c\u4e13\u95e8\u7528\u4e8e\u5904\u7406JavaScript\u9875\u9762\u3002\u5c06\u4e24\u8005\u7ed3\u5408\u4f7f\u7528\uff0c\u53ef\u4ee5\u5728Scrapy\u5f3a\u5927\u7684\u6293\u53d6\u53ca\u5904\u7406\u80fd\u529b\u7684\u57fa\u7840\u4e0a\uff0c\u901a\u8fc7Splash\u6e32\u67d3\u9875\u9762\u6765\u83b7\u53d6JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u4f7f\u7528Scrapy\u4e0eSplash\u4e4b\u524d\uff0c\u9700\u8981\u786e\u4fddSplash\u5df2\u7ecf\u88ab\u6b63\u786e\u5b89\u88c5\u548c\u914d\u7f6e\u3002\u5177\u4f53\u53ef\u4ee5\u53c2\u8003Splash\u7684\u5b98\u65b9\u6587\u6863\u3002<\/p>\n<\/p>\n<p><p>\u5728Scrapy\u9879\u76ee\u4e2d\u4f7f\u7528Splash\uff0c\u4e3b\u8981\u662f\u901a\u8fc7Splash\u4e2d\u95f4\u4ef6\u548cScrapy-Splash\u7684Docker\u5bb9\u5668\u6765\u5b9e\u73b0\u7684\u3002\u914d\u7f6e\u597dScrapy\u9879\u76ee\u540e\uff0c\u9700\u8981\u5728<code>settings.py<\/code>\u4e2d\u542f\u7528Splash\u4e2d\u95f4\u4ef6\uff0c\u5e76\u8bbe\u7f6e\u76f8\u5e94\u7684Splash\u670d\u52a1\u5668\u5730\u5740\u3002<\/p>\n<\/p>\n<p><p>\u83b7\u53d6JavaScript\u5185\u5bb9\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u914d\u7f6eScrapy\u9879\u76ee\uff0c\u542f\u7528Splash\u4e2d\u95f4\u4ef6\u3002<\/li>\n<li>\u7f16\u5199Spider\uff0c\u4f7f\u7528Splash\u8bf7\u6c42\u9875\u9762\u3002<\/li>\n<li>\u4ece\u8fd4\u56de\u7684\u54cd\u5e94\u4e2d\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002<\/li>\n<\/ol>\n<p><p>\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import scrapy<\/p>\n<p>from scrapy_splash import SplashRequest<\/p>\n<p>class JavascriptContentSpider(scrapy.Spider):<\/p>\n<p>    name = &quot;javascript_content&quot;<\/p>\n<p>    start_urls = [<\/p>\n<p>        &quot;http:\/\/example.com&quot;,<\/p>\n<p>    ]<\/p>\n<p>    def start_requests(self):<\/p>\n<p>        for url in self.start_urls:<\/p>\n<p>            yield SplashRequest(url, self.parse_result, args={&#039;wait&#039;: 0.5})<\/p>\n<p>    def parse_result(self, response):<\/p>\n<p>        # \u63d0\u53d6JavaScript\u751f\u6210\u7684\u5185\u5bb9<\/p>\n<p>        self.log(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7efc\u4e0a\u6240\u8ff0\uff0c\u83b7\u53d6JavaScript\u751f\u6210\u7684\u5185\u5bb9\u5bf9\u4e8e\u722c\u866b\u5f00\u53d1\u8005\u800c\u8a00\u662f\u4e00\u9879\u91cd\u8981\u7684\u6280\u80fd\u3002\u9009\u62e9\u4f55\u79cd\u65b9\u6cd5\u53d6\u51b3\u4e8e\u9879\u76ee\u9700\u6c42\u3001\u9884\u671f\u7684\u590d\u6742\u6027\u4ee5\u53ca\u5f00\u53d1\u8005\u5bf9\u6280\u672f\u6808\u7684\u719f\u6089\u7a0b\u5ea6\u3002Selenium\u3001Pyppeteer\u548cScrapy\u7ed3\u5408Splash\u662f\u76ee\u524d\u8f83\u4e3a\u6d41\u884c\u4e14\u6709\u6548\u7684\u4e09\u79cd\u65b9\u6848\u3002\u6bcf\u79cd\u65b9\u6848\u90fd\u6709\u5176\u4f18\u52bf\u548c\u573a\u666f\uff0c<strong>\u5bf9\u4e8e\u9700\u8981\u6a21\u62df\u7528\u6237\u884c\u4e3a\u7684\u573a\u666f\uff0cSelenium\u548cPyppeteer\u66f4\u4e3a\u5408\u9002\uff1b\u800c\u5bf9\u4e8e\u5927\u89c4\u6a21\u3001\u9700\u8981\u5feb\u901f\u54cd\u5e94\u7684\u722c\u866b\u9879\u76ee\uff0cScrapy\u548cSplash\u7684\u7ec4\u5408\u5c06\u662f\u66f4\u4f73\u7684\u9009\u62e9<\/strong>\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>1. \u5982\u4f55\u5728Python\u722c\u866b\u4e2d\u5904\u7406JavaScript\u54cd\u5e94\u5185\u5bb9\uff1f<\/strong><\/p>\n<p>\u5728Python\u722c\u866b\u4e2d\u83b7\u53d6JavaScript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9\uff0c\u53ef\u4ee5\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u5982Selenium\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002\u901a\u8fc7Selenium\u53ef\u4ee5\u6267\u884cJavaScript\u4ee3\u7801\uff0c\u5e76\u83b7\u53d6JavaScript\u751f\u6210\u7684\u54cd\u5e94\u5185\u5bb9\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Selenium\u5e93\uff0c\u7136\u540e\u4f7f\u7528WebDriver\u6765\u52a0\u8f7d\u7f51\u9875\uff0c\u6267\u884cJavaScript\u4ee3\u7801\uff0c\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<p><strong>2. \u6709\u54ea\u4e9b\u5de5\u5177\u53ef\u4ee5\u5e2e\u52a9\u6211\u83b7\u53d6JavaScript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9\uff1f<\/strong><\/p>\n<p>\u9664\u4e86Selenium\uff0c\u8fd8\u6709\u4e00\u4e9b\u5176\u4ed6\u5de5\u5177\u53ef\u4ee5\u5e2e\u52a9\u4f60\u83b7\u53d6JavaScript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528PhantomJS\u6216Puppeteer\u7b49\u65e0\u5934\u6d4f\u89c8\u5668\u6765\u52a0\u8f7d\u7f51\u9875\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002\u8fd9\u4e9b\u5de5\u5177\u90fd\u652f\u6301\u6267\u884cJavaScript\u4ee3\u7801\uff0c\u5e76\u83b7\u53d6JavaScript\u751f\u6210\u7684\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n<p><strong>3. \u5982\u4f55\u5904\u7406\u90a3\u4e9b\u4f9d\u8d56\u4e8eJavaScript\u751f\u6210\u7684\u5185\u5bb9\u7684\u7f51\u9875\uff1f<\/strong><\/p>\n<p>\u5982\u679c\u4e00\u4e2a\u7f51\u9875\u4f9d\u8d56\u4e8eJavaScript\u751f\u6210\u5185\u5bb9\uff0c\u800c\u4e14\u65e0\u6cd5\u76f4\u63a5\u901a\u8fc7Python\u722c\u866b\u83b7\u53d6\u5230\u5b8c\u6574\u7684\u5185\u5bb9\uff0c\u4f60\u53ef\u4ee5\u4f7f\u7528\u4e0a\u8ff0\u63d0\u53ca\u7684\u5de5\u5177\u6765\u52a0\u8f7d\u7f51\u9875\u5e76\u6267\u884cJavaScript\u4ee3\u7801\uff0c\u5c06\u751f\u6210\u7684\u5185\u5bb9\u83b7\u53d6\u5230\u3002\u53e6\u5916\uff0c\u4f60\u8fd8\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u8be5\u7f51\u9875\u7684XHR\u8bf7\u6c42\uff0c\u627e\u5230\u5bf9\u5e94\u7684\u63a5\u53e3\uff0c\u76f4\u63a5\u8bf7\u6c42\u63a5\u53e3\u83b7\u53d6\u5230\u6240\u9700\u5185\u5bb9\u3002\u8fd9\u79cd\u65b9\u5f0f\u4e0d\u9700\u8981\u4f7f\u7528\u5230\u6d4f\u89c8\u5668\u6a21\u62df\uff0c\u80fd\u591f\u66f4\u9ad8\u6548\u5730\u83b7\u53d6\u5230JavaScript\u751f\u6210\u7684\u5185\u5bb9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u83b7\u53d6JavaScript\u8fd4\u56de\u7684\u54cd\u5e94\u5185\u5bb9\u662fPython\u722c\u866b\u5f00\u53d1\u4e2d\u7684\u4e00\u9879\u9ad8\u7ea7\u548c\u5fc5\u5907\u6280\u80fd\uff0c\u56e0\u4e3a\u8bb8\u591a\u73b0\u4ee3\u7f51\u7ad9\u548c\u5e94\u7528\u90fd\u4f7f [&hellip;]","protected":false},"author":3,"featured_media":164862,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/164847"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=164847"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/164847\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/164862"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=164847"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=164847"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=164847"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}