{"id":1148552,"date":"2025-01-13T16:38:47","date_gmt":"2025-01-13T08:38:47","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1148552.html"},"modified":"2025-01-13T16:38:49","modified_gmt":"2025-01-13T08:38:49","slug":"python%e5%a6%82%e4%bd%95%e8%8e%b7%e5%8f%96%e7%bd%91%e9%a1%b5%e5%86%85%e5%ae%b9","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1148552.html","title":{"rendered":"python\u5982\u4f55\u83b7\u53d6\u7f51\u9875\u5185\u5bb9"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25172311\/ea06f444-9ffc-4966-940c-3fc62ace0453.webp\" alt=\"python\u5982\u4f55\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\" \/><\/p>\n<p><p> \u8981\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u4e3b\u8981\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u79cd\u65b9\u5f0f\uff1a<strong>\u4f7f\u7528requests\u5e93\u3001\u4f7f\u7528BeautifulSoup\u5e93\u8fdb\u884c\u89e3\u6790\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u5185\u5bb9\u83b7\u53d6\u3001\u4f7f\u7528Scrapy\u8fdb\u884c\u722c\u866b\u5f00\u53d1<\/strong>\u3002\u5176\u4e2d\uff0c<strong>requests\u5e93<\/strong>\u662f\u6700\u5e38\u7528\u7684\u4e00\u79cd\u65b9\u5f0f\uff0c\u56e0\u4e3a\u5b83\u7b80\u5355\u6613\u7528\uff0c\u5e76\u4e14\u53ef\u4ee5\u4e0e\u5176\u4ed6\u5e93\u7ed3\u5408\u4f7f\u7528\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528requests\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528requests\u5e93<\/h3>\n<\/p>\n<p><p><strong>requests\u5e93<\/strong>\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u8bf7\u6c42\u5e93\uff0c\u7528\u4e8e\u5411\u76ee\u6807\u7f51\u9875\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5requests\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528\u4e0b\u9762\u7684\u547d\u4ee4\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u4f7f\u7528requests\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<h2><strong>\u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/strong><\/h2>\n<p>if response.status_code == 200:<\/p>\n<p>    page_content = response.text<\/p>\n<p>    print(page_content)<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve webpage. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u5e93\u8fdb\u884c\u89e3\u6790<\/h3>\n<\/p>\n<p><p><strong>BeautifulSoup<\/strong>\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\uff0c\u53ef\u4ee5\u5c06\u7f51\u9875\u5185\u5bb9\u89e3\u6790\u6210\u7ed3\u6784\u5316\u7684\u6570\u636e\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\u548clxml\u89e3\u6790\u5668\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4 lxml<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    soup = BeautifulSoup(response.text, &#39;lxml&#39;)<\/p>\n<p>    print(soup.prettify())<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;Failed to retrieve webpage. Status code: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u5185\u5bb9\u83b7\u53d6<\/h3>\n<\/p>\n<p><p><strong>Selenium<\/strong>\u662f\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316\u6d4f\u89c8\u5668\u64cd\u4f5c\u7684\u5de5\u5177\uff0c\u9002\u5408\u7528\u6765\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Selenium\u5e93\u548c\u76f8\u5e94\u7684WebDriver\uff0c\u4f8b\u5982Chrome WebDriver\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u4e0b\u8f7dChrome WebDriver\u5e76\u5c06\u5176\u6dfb\u52a0\u5230\u7cfb\u7edf\u8def\u5f84\u3002\u4f7f\u7528Selenium\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(url)<\/p>\n<p>page_content = driver.page_source<\/p>\n<p>print(page_content)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u4f7f\u7528Scrapy\u8fdb\u884c\u722c\u866b\u5f00\u53d1<\/h3>\n<\/p>\n<p><p><strong>Scrapy<\/strong>\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u7528\u6765\u5f00\u53d1\u590d\u6742\u7684\u722c\u866b\u9879\u76ee\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Scrapy\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install scrapy<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4f7f\u7528Scrapy\u5f00\u53d1\u722c\u866b\u9879\u76ee\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u521b\u5efaScrapy\u9879\u76ee\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-bash\">scrapy startproject myproject<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u521b\u5efa\u722c\u866b\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-bash\">cd myproject<\/p>\n<p>scrapy genspider myspider example.com<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"3\">\n<li>\u7f16\u8f91<code>myspider.py<\/code>\u6587\u4ef6\uff0c\u6dfb\u52a0\u722c\u866b\u903b\u8f91\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import scrapy<\/p>\n<p>class MySpider(scrapy.Spider):<\/p>\n<p>    name = &#39;myspider&#39;<\/p>\n<p>    start_urls = [&#39;http:\/\/example.com&#39;]<\/p>\n<p>    def parse(self, response):<\/p>\n<p>        page_content = response.text<\/p>\n<p>        self.log(page_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"4\">\n<li>\u8fd0\u884c\u722c\u866b\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-bash\">scrapy crawl myspider<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u8be6\u7ec6\u63a2\u8ba8\u4e86\u5982\u4f55\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u51e0\u79cd\u5e38\u7528\u65b9\u6cd5\u3002<strong>requests\u5e93<\/strong>\u9002\u5408\u7528\u4e8e\u7b80\u5355\u7684\u7f51\u9875\u8bf7\u6c42\uff0c<strong>BeautifulSoup\u5e93<\/strong>\u53ef\u4ee5\u5bf9\u7f51\u9875\u5185\u5bb9\u8fdb\u884c\u89e3\u6790\u548c\u5904\u7406\uff0c<strong>Selenium\u5de5\u5177<\/strong>\u80fd\u591f\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9\uff0c\u800c<strong>Scrapy\u6846\u67b6<\/strong>\u5219\u9002\u5408\u7528\u4e8e\u5f00\u53d1\u590d\u6742\u7684\u722c\u866b\u9879\u76ee\u3002\u6839\u636e\u5b9e\u9645\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u9ad8\u6548\u5730\u83b7\u53d6\u548c\u5904\u7406\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u8fd9\u4e9b\u65b9\u6cd5\u5f80\u5f80\u53ef\u4ee5\u7ed3\u5408\u4f7f\u7528\uff0c\u4f8b\u5982\uff0c\u5148\u7528Selenium\u83b7\u53d6\u52a8\u6001\u7f51\u9875\u5185\u5bb9\uff0c\u518d\u7528BeautifulSoup\u8fdb\u884c\u89e3\u6790\u5904\u7406\uff0c\u6216\u8005\u7528Scrapy\u5f00\u53d1\u4e00\u4e2a\u5b8c\u6574\u7684\u722c\u866b\u9879\u76ee\u4ee5\u81ea\u52a8\u5316\u5730\u91c7\u96c6\u6570\u636e\u3002\u901a\u8fc7\u719f\u7ec3\u638c\u63e1\u8fd9\u4e9b\u5de5\u5177\u548c\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u66f4\u597d\u5730\u5e94\u5bf9\u5404\u79cd\u7f51\u9875\u5185\u5bb9\u83b7\u53d6\u7684\u9700\u6c42\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1f<\/strong><br \/>\u8981\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u53ef\u4ee5\u501f\u52a9\u4e00\u4e9b\u6d41\u884c\u7684\u5e93\uff0c\u5982<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u3002<code>requests<\/code>\u5e93\u53ef\u4ee5\u7528\u6765\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff0c\u800c<code>BeautifulSoup<\/code>\u5219\u53ef\u4ee5\u5e2e\u52a9\u89e3\u6790HTML\u6587\u6863\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\u4ee3\u7801\uff1a  <\/p>\n<pre><code class=\"language-python\">import requests\nfrom bs4 import BeautifulSoup\n\nurl = &#39;https:\/\/example.com&#39;\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.text, &#39;html.parser&#39;)\n\nprint(soup.prettify())\n<\/code><\/pre>\n<p>\u901a\u8fc7\u8fd0\u884c\u4ee5\u4e0a\u4ee3\u7801\uff0c\u60a8\u53ef\u4ee5\u83b7\u53d6\u5230\u6307\u5b9a\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u5e76\u4ee5\u66f4\u53ef\u8bfb\u7684\u65b9\u5f0f\u8f93\u51fa\u3002<\/p>\n<p><strong>\u5728\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u4e8b\u9879\uff1f<\/strong><br \/>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u6709\u51e0\u4e2a\u91cd\u8981\u4e8b\u9879\u9700\u8981\u5173\u6ce8\u3002\u9996\u5148\uff0c\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u6587\u4ef6\u4e2d\u7684\u722c\u866b\u89c4\u5219\uff0c\u907f\u514d\u8fdd\u53cd\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u3002\u5176\u6b21\uff0c\u8bbe\u7f6e\u5408\u9002\u7684\u8bf7\u6c42\u5934\uff0c\u6a21\u4eff\u6d4f\u89c8\u5668\u8bbf\u95ee\uff0c\u4ee5\u51cf\u5c11\u88ab\u7f51\u7ad9\u5c01\u7981\u7684\u98ce\u9669\u3002\u6b64\u5916\uff0c\u5904\u7406\u8bf7\u6c42\u65f6\u8981\u8003\u8651\u5f02\u5e38\u60c5\u51b5\uff0c\u6bd4\u5982\u7f51\u7edc\u95ee\u9898\u6216\u7f51\u9875\u4e0d\u5b58\u5728\u7684\u60c5\u51b5\uff0c\u5efa\u8bae\u4f7f\u7528\u5f02\u5e38\u5904\u7406\u6765\u786e\u4fdd\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u3002<\/p>\n<p><strong>\u5982\u4f55\u89e3\u6790\u83b7\u53d6\u5230\u7684\u7f51\u9875\u5185\u5bb9\uff1f<\/strong><br \/>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u89e3\u6790\u662f\u4e0b\u4e00\u6b65\u3002\u4f7f\u7528<code>BeautifulSoup<\/code>\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u4f8b\u5982\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528<code>soup.find()<\/code>\u6216<code>soup.find_all()<\/code>\u65b9\u6cd5\u6765\u67e5\u627e\u7279\u5b9a\u7684HTML\u6807\u7b7e\u548c\u5185\u5bb9\u3002\u4ee3\u7801\u793a\u4f8b\u5982\u4e0b\uff1a  <\/p>\n<pre><code class=\"language-python\">titles = soup.find_all(&#39;h1&#39;)  # \u83b7\u53d6\u6240\u6709h1\u6807\u7b7e\u7684\u5185\u5bb9\nfor title in titles:\n    print(title.get_text())\n<\/code><\/pre>\n<p>\u901a\u8fc7\u8fd9\u79cd\u65b9\u6cd5\uff0c\u53ef\u4ee5\u8f7b\u677e\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6807\u9898\u3001\u6bb5\u843d\u6216\u5176\u4ed6\u5143\u7d20\uff0c\u8fdb\u800c\u8fdb\u884c\u6570\u636e\u5206\u6790\u6216\u4fe1\u606f\u6574\u7406\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u4e3b\u8981\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u79cd\u65b9\u5f0f\uff1a\u4f7f\u7528requests\u5e93\u3001\u4f7f\u7528BeautifulSou [&hellip;]","protected":false},"author":3,"featured_media":1148559,"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\/1148552"}],"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=1148552"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1148552\/revisions"}],"predecessor-version":[{"id":1148563,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1148552\/revisions\/1148563"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1148559"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1148552"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1148552"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1148552"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}