{"id":175647,"date":"2024-05-08T18:55:07","date_gmt":"2024-05-08T10:55:07","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/175647.html"},"modified":"2024-05-08T18:55:12","modified_gmt":"2024-05-08T10:55:12","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%86%99%e4%b8%80%e4%b8%aa%e7%88%ac%e8%99%ab%e7%bb%9f%e8%ae%a1%e6%b7%98%e5%ae%9d%e6%9f%90%e4%bb%b6%e5%95%86%e5%93%81%e7%9a%84%e9%94%80%e9%87%8f","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/175647.html","title":{"rendered":"\u5982\u4f55\u7528python\u5199\u4e00\u4e2a\u722c\u866b\u7edf\u8ba1\u6dd8\u5b9d\u67d0\u4ef6\u5546\u54c1\u7684\u9500\u91cf"},"content":{"rendered":"<p style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/27053624\/b44818f9-0c24-41e6-bff1-e55a6b12bb78.webp\" alt=\"\u5982\u4f55\u7528python\u5199\u4e00\u4e2a\u722c\u866b\u7edf\u8ba1\u6dd8\u5b9d\u67d0\u4ef6\u5546\u54c1\u7684\u9500\u91cf\" \/><\/p>\n<p><p>\u7528Python\u5199\u4e00\u4e2a\u722c\u866b\u7edf\u8ba1\u6dd8\u5b9d\u67d0\u4ef6\u5546\u54c1\u7684\u9500\u91cf\uff0c\u4e3b\u8981\u901a\u8fc7\u4ee5\u4e0b\u51e0\u4e2a\u6b65\u9aa4\u5b9e\u73b0\uff1a<strong>\u5b89\u88c5\u548c\u914d\u7f6e\u722c\u866b\u73af\u5883\u3001\u7f16\u5199\u722c\u866b\u4ee3\u7801\u3001\u89e3\u6790\u5546\u54c1\u9875\u9762\u3001\u4fdd\u5b58\u548c\u7edf\u8ba1\u6570\u636e<\/strong>\u3002\u8fd9\u5176\u4e2d\uff0c<strong>\u7f16\u5199\u722c\u866b\u4ee3\u7801<\/strong>\u662f\u6838\u5fc3\u90e8\u5206\uff0c\u6d89\u53ca\u5230\u5bf9\u722c\u866b\u6846\u67b6\u7684\u9009\u62e9\uff08\u5982Scrapy\uff09\u3001\u7f51\u7edc\u8bf7\u6c42\u7684\u53d1\u9001\uff08\u4f7f\u7528requests\u6216Selenium\uff09\u4ee5\u53ca\u5bf9\u6dd8\u5b9d\u7f51\u9875\u7ed3\u6784\u7684\u7406\u89e3\u548c\u5206\u6790\u3002\u5c24\u5176\u662f\u4f7f\u7528Selenium\uff0c\u56e0\u4e3a\u6dd8\u5b9d\u5927\u91cf\u91c7\u7528\u4e86Ajax\u6280\u672f\u548c\u53cd\u722c\u6280\u672f\uff0c\u76f4\u63a5\u5bf9HTML\u6e90\u7801\u8fdb\u884c\u89e3\u6790\u7684\u96be\u5ea6\u8f83\u5927\uff0c\u800cSelenium\u80fd\u591f\u6a21\u62df\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u73af\u5883\uff0c\u52a8\u6001\u52a0\u8f7d\u7f51\u9875\uff0c\u66f4\u5bb9\u6613\u5b9e\u73b0\u5bf9\u5546\u54c1\u9500\u91cf\u7684\u6293\u53d6\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5b89\u88c5\u548c\u914d\u7f6e\u722c\u866b\u73af\u5883<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u7f16\u5199\u4ee3\u7801\u4e4b\u524d\uff0c\u9700\u8981\u786e\u4fddPython\u5df2\u7ecf\u5b89\u88c5\uff0c\u540c\u65f6\u9009\u5b9a\u4e00\u4e2a\u5408\u9002\u7684\u722c\u866b\u6846\u67b6\u5b89\u88c5\u597d\u3002Scrapy\u548cSelenium\u662f\u4e24\u4e2a\u5e38\u7528\u4e14\u529f\u80fd\u5f3a\u5927\u7684\u6846\u67b6\u3002Scrapy\u4e3b\u8981\u7528\u4e8e\u9759\u6001\u7f51\u9875\u7684\u722c\u53d6\uff0c\u901f\u5ea6\u8f83\u5feb\u3002\u800cSelenium\u80fd\u6a21\u62df\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u9002\u5408\u4e8e\u9700\u8981\u6267\u884cJavaScript\u811a\u672c\u7684\u52a8\u6001\u7f51\u9875\u3002<\/p>\n<\/p>\n<p><p>\u5bf9\u4e8e\u65b0\u624b\u6765\u8bf4\uff0c\u5b89\u88c5\u8fd9\u4e9b\u6846\u67b6\u548c\u914d\u7f6e\u73af\u5883\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u56f0\u96be\uff0c\u63a8\u8350\u4f7f\u7528pip\u4f5c\u4e3aPython\u7684\u5305\u7ba1\u7406\u5668\uff0c\u901a\u8fc7\u7b80\u5355\u7684\u547d\u4ee4\u5c31\u80fd\u5b8c\u6210\u5b89\u88c5\u3002<\/p>\n<\/p>\n<p><pre><code>pip install scrapy selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u786e\u4fdd\u5b89\u88c5\u4e86WebDriver\uff0c\u56e0\u4e3aSelenium\u9700\u8981\u5b83\u6765\u9a71\u52a8\u6d4f\u89c8\u5668\u3002\u9009\u62e9\u548c\u4f60\u7684\u6d4f\u89c8\u5668\u7248\u672c\u76f8\u5339\u914d\u7684WebDriver\uff0c\u5982Chrome\u6216Firefox\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u7f16\u5199\u722c\u866b\u4ee3\u7801<\/h3>\n<\/p>\n<p><h4>\u9009\u62e9\u5408\u9002\u7684\u722c\u866b\u6846\u67b6<\/h4>\n<\/p>\n<p><p>\u6839\u636e\u6dd8\u5b9d\u7f51\u7ad9\u7684\u7279\u70b9\uff0c\u9009\u62e9Selenium\u4f5c\u4e3a\u4e3b\u8981\u7684\u722c\u866b\u6846\u67b6\u3002\u56e0\u4e3a\u6dd8\u5b9d\u7f51\u9875\u5185\u5bb9\u4e30\u5bcc\uff0c\u5f88\u591a\u4fe1\u606f\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0cSelenium\u80fd\u6709\u6548\u89e3\u51b3\u8fd9\u4e00\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h4>\u7f16\u5199\u57fa\u672c\u7684\u722c\u866b\u903b\u8f91<\/h4>\n<\/p>\n<ol>\n<li>\u4f7f\u7528Selenium\u6253\u5f00\u4e00\u4e2a\u6dd8\u5b9d\u5546\u54c1\u9875\u9762\u3002<\/li>\n<li>\u6a21\u62df\u7528\u6237\u7684\u6eda\u52a8\u3001\u70b9\u51fb\u7b49\u884c\u4e3a\uff0c\u4ee5\u786e\u4fdd\u9875\u9762\u7684\u4fe1\u606f\u5b8c\u5168\u52a0\u8f7d\u3002<\/li>\n<li>\u83b7\u53d6\u9875\u9762\u6e90\u4ee3\u7801\u3002<\/li>\n<\/ol>\n<p><p>\u63a5\u4e0b\u6765\u662f\u9875\u9762\u89e3\u6790\u73af\u8282\uff0c\u63d0\u53d6\u51fa\u6211\u4eec\u5173\u6ce8\u7684\u5546\u54c1\u9500\u91cf\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790\u5546\u54c1\u9875\u9762<\/h3>\n<\/p>\n<p><p>\u9875\u9762\u89e3\u6790\u662f\u901a\u8fc7\u5206\u6790\u7f51\u9875\u7684DOM\u7ed3\u6784\uff0c\u627e\u5230\u5b58\u653e\u5546\u54c1\u9500\u91cf\u4fe1\u606f\u7684\u6807\u7b7e\u4f4d\u7f6e\u3002\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6216lxml\u8fd9\u6837\u7684\u5e93\u6765\u89e3\u6790HTML\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<ol>\n<li>\u4f7f\u7528BeautifulSoup\u89e3\u6790\u9875\u9762\uff1a<\/li>\n<\/ol>\n<p><pre><code>from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u5047\u5b9adriver\u662f\u4e00\u4e2aSelenium WebDriver\u5b9e\u4f8b\uff0c\u7528\u6765\u6253\u5f00\u7f51\u9875<\/strong><\/h2>\n<p>html = driver.page_source<\/p>\n<p>soup = BeautifulSoup(html, &#039;html.parser&#039;)<\/p>\n<h2><strong>\u57fa\u4e8e\u7f51\u9875\u7ed3\u6784\u5206\u6790\uff0c\u627e\u5230\u5546\u54c1\u9500\u91cf\u6240\u5728\u7684\u6807\u7b7e\uff0c\u5e76\u63d0\u53d6\u9500\u91cf<\/strong><\/h2>\n<p>sale_volume = soup.find(&#039;span&#039;, class_=&#039;sales-volume&#039;).text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u5206\u6790\u548c\u63d0\u53d6\u9500\u91cf\u4fe1\u606f\uff0c\u6ce8\u610f\u9500\u91cf\u4fe1\u606f\u53ef\u80fd\u4f1a\u968f\u65f6\u95f4\u6216\u8005\u6dd8\u5b9d\u524d\u7aef\u4ee3\u7801\u53d8\u5316\u800c\u53d8\u5316\uff0c\u9700\u8981\u7ecf\u5e38\u68c0\u67e5\u5e76\u66f4\u65b0\u9009\u62e9\u5668\u3002<\/li>\n<\/ol>\n<p><h3>\u56db\u3001\u4fdd\u5b58\u548c\u7edf\u8ba1\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u6536\u96c6\u5230\u5546\u54c1\u7684\u9500\u91cf\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u5c06\u5176\u4fdd\u5b58\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u8fdb\u884c\u540e\u7eed\u7684\u5206\u6790\u548c\u7edf\u8ba1\u3002<\/p>\n<\/p>\n<ol>\n<li>\u4fdd\u5b58\u5230CSV\u6587\u4ef6\uff1a<\/li>\n<\/ol>\n<p><pre><code>import csv<\/p>\n<p>with open(&#039;sales_volume.csv&#039;, mode=&#039;w&#039;, newline=&#039;&#039;, encoding=&#039;utf-8&#039;) as file:<\/p>\n<p>    writer = csv.writer(file)<\/p>\n<p>    writer.writerow([&#039;\u5546\u54c1ID&#039;, &#039;\u9500\u91cf&#039;])<\/p>\n<p>    writer.writerow([product_id, sale_volume])<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u6839\u636e\u9700\u8981\uff0c\u53ef\u4ee5\u4f7f\u7528Pandas\u3001Matplotlib\u7b49\u5e93\u5bf9\u6536\u96c6\u5230\u7684\u6570\u636e\u8fdb\u884c\u5206\u6790\u548c\u53ef\u89c6\u5316\u3002\u6bd4\u5982\uff0c\u7edf\u8ba1\u4e00\u6bb5\u65f6\u95f4\u5185\u5546\u54c1\u9500\u91cf\u7684\u53d8\u5316\u8d8b\u52bf\uff0c\u5206\u6790\u4fc3\u9500\u6d3b\u52a8\u5bf9\u9500\u91cf\u7684\u5f71\u54cd\u7b49\u3002<\/li>\n<\/ol>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u5373\u53ef\u5b9e\u73b0\u5bf9\u6dd8\u5b9d\u67d0\u4ef6\u5546\u54c1\u9500\u91cf\u7684\u722c\u53d6\u548c\u7edf\u8ba1\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u5e94\u5c0a\u91cd\u7f51\u7ad9\u89c4\u5b9a\uff0c\u9075\u5b88robots.txt\u534f\u8bae\uff0c\u5408\u7406\u5b89\u6392\u722c\u53d6\u9891\u7387\uff0c\u907f\u514d\u7ed9\u7f51\u7ad9\u670d\u52a1\u5668\u9020\u6210\u4e0d\u5fc5\u8981\u7684\u8d1f\u62c5\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>1. \u5982\u4f55\u4f7f\u7528Python\u7f16\u5199\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6dd8\u5b9d\u5546\u54c1\u9500\u91cf\u7edf\u8ba1\u722c\u866b\uff1f<\/strong><\/p>\n<p>\u4f7f\u7528Python\u7f16\u5199\u4e00\u4e2a\u5f3a\u5927\u7684\u6dd8\u5b9d\u5546\u54c1\u9500\u91cf\u7edf\u8ba1\u722c\u866b\u53ef\u4ee5\u8ba9\u6211\u4eec\u83b7\u53d6\u5230\u51c6\u786e\u7684\u9500\u91cf\u6570\u636e\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528Python\u7684\u7f51\u7edc\u8bf7\u6c42\u5e93\uff08\u5982requests\uff09\u6765\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u4ece\u6dd8\u5b9d\u7f51\u9875\u4e0a\u83b7\u53d6\u539f\u59cb\u6570\u636e\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684HTML\u89e3\u6790\u5e93\uff08\u5982BeautifulSoup\uff09\u6765\u89e3\u6790\u9875\u9762\uff0c\u63d0\u53d6\u9700\u8981\u7684\u9500\u91cf\u6570\u636e\u3002\u5bf9\u4e8e\u6bcf\u4e2a\u5546\u54c1\uff0c\u6211\u4eec\u53ef\u4ee5\u63d0\u53d6\u51fa\u5b83\u7684\u6807\u9898\u3001\u4ef7\u683c\u548c\u9500\u91cf\u7b49\u4fe1\u606f\uff0c\u5e76\u5c06\u5b83\u4eec\u4fdd\u5b58\u5230\u4e00\u4e2a\u6570\u636e\u7ed3\u6784\u4e2d\uff0c\u5982\u5b57\u5178\u6216\u8005CSV\u6587\u4ef6\uff0c\u4ee5\u4fbf\u6211\u4eec\u540e\u7eed\u8fdb\u884c\u7edf\u8ba1\u548c\u5206\u6790\u3002<\/p>\n<p><strong>2. \u6dd8\u5b9d\u5546\u54c1\u9500\u91cf\u7edf\u8ba1\u722c\u866b\u7684\u539f\u7406\u662f\u4ec0\u4e48\uff1f<\/strong><\/p>\n<p>\u6dd8\u5b9d\u5546\u54c1\u9500\u91cf\u7edf\u8ba1\u722c\u866b\u7684\u539f\u7406\u662f\u901a\u8fc7\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u6dd8\u5b9d\u7f51\u9875\u7684\u6e90\u4ee3\u7801\uff0c\u7136\u540e\u4f7f\u7528HTML\u89e3\u6790\u5e93\u89e3\u6790\u8be5\u6e90\u4ee3\u7801\uff0c\u63d0\u53d6\u51fa\u5546\u54c1\u7684\u76f8\u5173\u4fe1\u606f\uff0c\u5982\u6807\u9898\u3001\u4ef7\u683c\u548c\u9500\u91cf\u7b49\u3002\u5177\u4f53\u6765\u8bf4\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u5206\u6790\u6dd8\u5b9d\u7f51\u9875\u7684HTML\u7ed3\u6784\uff0c\u627e\u5230\u5305\u542b\u8fd9\u4e9b\u4fe1\u606f\u7684\u7279\u5b9a\u6807\u7b7e\u548c\u5c5e\u6027\uff0c\u5e76\u4f7f\u7528\u76f8\u5e94\u7684\u89e3\u6790\u65b9\u6cd5\u63d0\u53d6\u51fa\u8fd9\u4e9b\u4fe1\u606f\u3002\u7136\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u63d0\u53d6\u5230\u7684\u4fe1\u606f\u4fdd\u5b58\u5230\u4e00\u4e2a\u6570\u636e\u7ed3\u6784\u4e2d\uff0c\u8fdb\u884c\u7edf\u8ba1\u548c\u5206\u6790\u3002<\/p>\n<p><strong>3. \u5982\u4f55\u4f18\u5316\u722c\u53d6\u6dd8\u5b9d\u5546\u54c1\u9500\u91cf\u6570\u636e\u7684Python\u722c\u866b\uff1f<\/strong><\/p>\n<p>\u4f18\u5316\u722c\u53d6\u6dd8\u5b9d\u5546\u54c1\u9500\u91cf\u6570\u636e\u7684Python\u722c\u866b\u53ef\u4ee5\u63d0\u9ad8\u6570\u636e\u722c\u53d6\u7684\u6548\u7387\u548c\u51c6\u786e\u6027\u3002\u9996\u5148\uff0c\u6211\u4eec\u53ef\u4ee5\u8bbe\u7f6e\u5408\u7406\u7684\u722c\u53d6\u901f\u5ea6\uff0c\u907f\u514d\u5bf9\u6dd8\u5b9d\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u7684\u538b\u529b\uff0c\u5e76\u4e14\u4f7f\u7528\u9002\u5f53\u7684\u5ef6\u65f6\u673a\u5236\u6765\u6a21\u62df\u771f\u5b9e\u7528\u6237\u7684\u64cd\u4f5c\u3002\u5176\u6b21\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u5e76\u53d1\u722c\u53d6\u7684\u65b9\u6cd5\uff0c\u5982\u591a\u7ebf\u7a0b\u6216\u5f02\u6b65\u8bf7\u6c42\uff0c\u6765\u63d0\u9ad8\u722c\u53d6\u901f\u5ea6\u3002\u6b64\u5916\uff0c\u6211\u4eec\u53ef\u4ee5\u9488\u5bf9\u6dd8\u5b9d\u7f51\u9875\u7684\u7279\u5b9a\u7ed3\u6784\u548c\u6837\u5f0f\u8fdb\u884c\u5b9a\u5236\u5316\u7684\u89e3\u6790\u65b9\u6cd5\uff0c\u4ee5\u63d0\u9ad8\u89e3\u6790\u7684\u6548\u7387\u548c\u7cbe\u786e\u5ea6\u3002\u6700\u540e\uff0c\u4e3a\u4e86\u4fdd\u8bc1\u6570\u636e\u7684\u51c6\u786e\u6027\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u6570\u636e\u6821\u9a8c\u548c\u53bb\u91cd\u7684\u65b9\u6cd5\uff0c\u8fc7\u6ee4\u6389\u91cd\u590d\u6570\u636e\u548c\u5f02\u5e38\u6570\u636e\uff0c\u786e\u4fdd\u722c\u53d6\u5230\u7684\u6570\u636e\u662f\u51c6\u786e\u53ef\u9760\u7684\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u7528Python\u5199\u4e00\u4e2a\u722c\u866b\u7edf\u8ba1\u6dd8\u5b9d\u67d0\u4ef6\u5546\u54c1\u7684\u9500\u91cf\uff0c\u4e3b\u8981\u901a\u8fc7\u4ee5\u4e0b\u51e0\u4e2a\u6b65\u9aa4\u5b9e\u73b0\uff1a\u5b89\u88c5\u548c\u914d\u7f6e\u722c\u866b\u73af\u5883\u3001\u7f16\u5199\u722c\u866b\u4ee3\u7801\u3001\u89e3 [&hellip;]","protected":false},"author":3,"featured_media":175654,"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\/175647"}],"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=175647"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/175647\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/175654"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=175647"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=175647"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=175647"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}