{"id":1175295,"date":"2025-01-15T17:30:04","date_gmt":"2025-01-15T09:30:04","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1175295.html"},"modified":"2025-01-15T17:30:08","modified_gmt":"2025-01-15T09:30:08","slug":"%e5%a6%82%e4%bd%95%e5%88%a9%e7%94%a8python%e9%87%87%e9%9b%86%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1175295.html","title":{"rendered":"\u5982\u4f55\u5229\u7528python\u91c7\u96c6\u6570\u636e"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25110759\/b9248560-eff7-498d-9de0-3a6e30c1be8d.webp\" alt=\"\u5982\u4f55\u5229\u7528python\u91c7\u96c6\u6570\u636e\" \/><\/p>\n<p><p> \u5229\u7528Python\u91c7\u96c6\u6570\u636e\u7684\u65b9\u6cd5\u5305\u62ec<strong>\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u9875\u9762\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316\u3001\u8c03\u7528API\u63a5\u53e3\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6<\/strong>\u3002\u5176\u4e2d\uff0c<strong>requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/strong>\u662f\u6700\u5e38\u89c1\u4e14\u57fa\u7840\u7684\u65b9\u6cd5\u3002\u5b83\u901a\u8fc7\u5411\u76ee\u6807\u7f51\u7ad9\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff0c\u518d\u7ed3\u5408BeautifulSoup\u89e3\u6790\u9875\u9762\uff0c\u5b9e\u73b0\u6570\u636e\u7684\u63d0\u53d6\u3002\u4f8b\u5982\uff0c\u4f7f\u7528requests\u5e93\u53ef\u4ee5\u83b7\u53d6\u7f51\u9875\u7684HTML\u6587\u672c\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u8fdb\u884c\u89e3\u6790\uff0c\u63d0\u53d6\u51fa\u9700\u8981\u7684\u6570\u636e\u3002\u8fd9\u79cd\u65b9\u6cd5\u7b80\u5355\u9ad8\u6548\uff0c\u9002\u7528\u4e8e\u5927\u90e8\u5206\u9759\u6001\u7f51\u9875\u7684\u6293\u53d6\u3002<\/p>\n<\/p>\n<hr>\n<p><h3>\u4e00\u3001\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>requests\u5e93\u662fPython\u4e2d\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u7b2c\u4e09\u65b9\u5e93\uff0c\u53ef\u4ee5\u7528\u4e8e\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002\u5b83\u7684\u4f7f\u7528\u65b9\u6cd5\u975e\u5e38\u7b80\u5355\uff0c\u4ec5\u9700\u51e0\u884c\u4ee3\u7801\u5373\u53ef\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5requests\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5requests\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u54cd\u5e94\u5bf9\u8c61<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/example.com&#39;)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff08HTML\u6587\u672c\uff09<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u901a\u8fc7<code>requests.get()<\/code>\u65b9\u6cd5\u53d1\u9001HTTP GET\u8bf7\u6c42\uff0c\u83b7\u53d6\u76ee\u6807\u7f51\u9875\u7684\u54cd\u5e94\u5185\u5bb9\u3002<code>response.text<\/code>\u5c5e\u6027\u5305\u542b\u4e86\u7f51\u9875\u7684HTML\u6587\u672c\u3002<\/p>\n<\/p>\n<p><h4>3\u3001\u5904\u7406\u8bf7\u6c42\u5934\u548c\u53c2\u6570<\/h4>\n<\/p>\n<p><p>\u6709\u65f6\uff0c\u4e3a\u4e86\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u9700\u8981\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\u6dfb\u52a0\u8bf7\u6c42\u5934\u4fe1\u606f\uff0c\u4f8b\u5982User-Agent\u3002\u8fd8\u53ef\u4ee5\u5728\u8bf7\u6c42\u4e2d\u6dfb\u52a0URL\u53c2\u6570\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u5b9a\u4e49\u8bf7\u6c42\u5934<\/strong><\/h2>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<h2><strong>\u5b9a\u4e49URL\u53c2\u6570<\/strong><\/h2>\n<p>params = {<\/p>\n<p>    &#39;query&#39;: &#39;python&#39;<\/p>\n<p>}<\/p>\n<h2><strong>\u53d1\u9001\u5e26\u6709\u8bf7\u6c42\u5934\u548c\u53c2\u6570\u7684HTTP\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/example.com\/search&#39;, headers=headers, params=params)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff08HTML\u6587\u672c\uff09<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u548c\u53c2\u6570\uff0c\u53ef\u4ee5\u66f4\u597d\u5730\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u63d0\u5347\u8bf7\u6c42\u7684\u6210\u529f\u7387\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u9875\u9762<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u662fPython\u4e2d\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5BeautifulSoup\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\u548cHTML\u89e3\u6790\u5668\u5e93lxml\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">pip install beautifulsoup4 lxml<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u89e3\u6790HTML\u5185\u5bb9<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u5047\u8bbehtml_content\u662f\u83b7\u53d6\u5230\u7684\u7f51\u9875HTML\u6587\u672c<\/strong><\/h2>\n<p>html_content = &quot;&quot;&quot;<\/p>\n<p>&lt;html&gt;<\/p>\n<p>    &lt;head&gt;&lt;title&gt;Example&lt;\/title&gt;&lt;\/head&gt;<\/p>\n<p>    &lt;body&gt;<\/p>\n<p>        &lt;h1&gt;Hello, World!&lt;\/h1&gt;<\/p>\n<p>        &lt;p&gt;This is a paragraph.&lt;\/p&gt;<\/p>\n<p>    &lt;\/body&gt;<\/p>\n<p>&lt;\/html&gt;<\/p>\n<p>&quot;&quot;&quot;<\/p>\n<h2><strong>\u89e3\u6790HTML\u5185\u5bb9<\/strong><\/h2>\n<p>soup = BeautifulSoup(html_content, &#39;lxml&#39;)<\/p>\n<h2><strong>\u63d0\u53d6\u6807\u9898<\/strong><\/h2>\n<p>title = soup.title.string<\/p>\n<h2><strong>\u63d0\u53d6\u6240\u6709\u6bb5\u843d<\/strong><\/h2>\n<p>paragraphs = soup.find_all(&#39;p&#39;)<\/p>\n<h2><strong>\u6253\u5370\u7ed3\u679c<\/strong><\/h2>\n<p>print(&#39;Title:&#39;, title)<\/p>\n<p>for p in paragraphs:<\/p>\n<p>    print(&#39;Paragraph:&#39;, p.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u901a\u8fc7<code>BeautifulSoup()<\/code>\u65b9\u6cd5\u89e3\u6790HTML\u6587\u672c\uff0c\u751f\u6210\u4e00\u4e2aBeautifulSoup\u5bf9\u8c61\u3002\u901a\u8fc7\u5bf9\u8c61\u7684\u5c5e\u6027\u548c\u65b9\u6cd5\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u63d0\u53d6\u51fa\u9700\u8981\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316<\/h3>\n<\/p>\n<p><p>Selenium\u662f\u4e00\u4e2a\u7528\u4e8e\u7f51\u9875\u81ea\u52a8\u5316\u6d4b\u8bd5\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u5728\u6d4f\u89c8\u5668\u4e2d\u7684\u64cd\u4f5c\uff0c\u9002\u7528\u4e8e\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5Selenium\u5e93\u548c\u6d4f\u89c8\u5668\u9a71\u52a8<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Selenium\u5e93\u548c\u76f8\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff08\u4f8b\u5982ChromeDriver\uff09\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0b\u8f7dChromeDriver\uff0c\u5e76\u5c06\u5176\u8def\u5f84\u6dfb\u52a0\u5230\u7cfb\u7edf\u73af\u5883\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u7f51\u9875\u64cd\u4f5c<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528Selenium\u8fdb\u884c\u7f51\u9875\u64cd\u4f5c\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<h2><strong>\u521b\u5efa\u6d4f\u89c8\u5668\u9a71\u52a8\u5bf9\u8c61\uff08\u4ee5Chrome\u4e3a\u4f8b\uff09<\/strong><\/h2>\n<p>driver = webdriver.Chrome()<\/p>\n<h2><strong>\u6253\u5f00\u76ee\u6807\u7f51\u9875<\/strong><\/h2>\n<p>driver.get(&#39;https:\/\/example.com&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u5143\u7d20\u5e76\u8fdb\u884c\u64cd\u4f5c<\/strong><\/h2>\n<p>element = driver.find_element_by_tag_name(&#39;h1&#39;)<\/p>\n<p>print(&#39;Element text:&#39;, element.text)<\/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>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u901a\u8fc7<code>webdriver.Chrome()<\/code>\u65b9\u6cd5\u521b\u5efaChrome\u6d4f\u89c8\u5668\u9a71\u52a8\u5bf9\u8c61\uff0c\u5e76\u4f7f\u7528<code>get()<\/code>\u65b9\u6cd5\u6253\u5f00\u76ee\u6807\u7f51\u9875\u3002\u53ef\u4ee5\u4f7f\u7528<code>find_element_by_tag_name()<\/code>\u65b9\u6cd5\u67e5\u627e\u9875\u9762\u5143\u7d20\uff0c\u5e76\u8fdb\u884c\u76f8\u5173\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u8c03\u7528API\u63a5\u53e3<\/h3>\n<\/p>\n<p><p>\u8bb8\u591a\u7f51\u7ad9\u63d0\u4f9b\u4e86API\u63a5\u53e3\uff0c\u4f9b\u7528\u6237\u8fdb\u884c\u6570\u636e\u8bbf\u95ee\u3002\u8c03\u7528API\u63a5\u53e3\u901a\u5e38\u6bd4\u7f51\u9875\u6293\u53d6\u66f4\u52a0\u89c4\u8303\u548c\u9ad8\u6548\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u4e86\u89e3API\u63a5\u53e3\u6587\u6863<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u4e86\u89e3\u76ee\u6807\u7f51\u7ad9\u7684API\u63a5\u53e3\u6587\u6863\uff0c\u4e86\u89e3\u63a5\u53e3\u7684\u4f7f\u7528\u65b9\u6cd5\u3001\u8bf7\u6c42\u65b9\u5f0f\u3001\u53c2\u6570\u7b49\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u53d1\u9001API\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u53d1\u9001API\u8bf7\u6c42\u7684\u57fa\u672c\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u5b9a\u4e49API\u63a5\u53e3URL<\/strong><\/h2>\n<p>api_url = &#39;https:\/\/api.example.com\/data&#39;<\/p>\n<h2><strong>\u5b9a\u4e49\u8bf7\u6c42\u5934<\/strong><\/h2>\n<p>headers = {<\/p>\n<p>    &#39;Authorization&#39;: &#39;Bearer YOUR_ACCESS_TOKEN&#39;<\/p>\n<p>}<\/p>\n<h2><strong>\u53d1\u9001API\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(api_url, headers=headers)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff08JSON\u683c\u5f0f\uff09<\/strong><\/h2>\n<p>data = response.json()<\/p>\n<h2><strong>\u6253\u5370\u7ed3\u679c<\/strong><\/h2>\n<p>print(data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u901a\u8fc7<code>requests.get()<\/code>\u65b9\u6cd5\u53d1\u9001API\u8bf7\u6c42\uff0c\u5e76\u901a\u8fc7<code>response.json()<\/code>\u65b9\u6cd5\u5c06\u54cd\u5e94\u5185\u5bb9\u89e3\u6790\u4e3aJSON\u683c\u5f0f\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6<\/h3>\n<\/p>\n<p><p>Scrapy\u662fPython\u4e2d\u4e00\u4e2a\u5f3a\u5927\u7684\u7f51\u9875\u6293\u53d6\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6\u4efb\u52a1\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5Scrapy<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Scrapy\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">pip install scrapy<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u521b\u5efaScrapy\u9879\u76ee<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528Scrapy\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u9879\u76ee\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">scrapy startproject myproject<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fdb\u5165\u9879\u76ee\u76ee\u5f55\uff0c\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u722c\u866b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">cd myproject<\/p>\n<p>scrapy genspider myspider example.com<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3\u3001\u7f16\u5199\u722c\u866b<\/h4>\n<\/p>\n<p><p>\u5728\u751f\u6210\u7684\u722c\u866b\u6587\u4ef6\u4e2d\u7f16\u5199\u722c\u866b\u903b\u8f91\uff1a<\/p>\n<\/p>\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>    allowed_dom<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>ns = [&#39;example.com&#39;]<\/p>\n<p>    start_urls = [&#39;https:\/\/example.com&#39;]<\/p>\n<p>    def parse(self, response):<\/p>\n<p>        # \u63d0\u53d6\u6570\u636e<\/p>\n<p>        title = response.xpath(&#39;\/\/title\/text()&#39;).get()<\/p>\n<p>        paragraphs = response.xpath(&#39;\/\/p\/text()&#39;).getall()<\/p>\n<p>        # \u6253\u5370\u7ed3\u679c<\/p>\n<p>        print(&#39;Title:&#39;, title)<\/p>\n<p>        for p in paragraphs:<\/p>\n<p>            print(&#39;Paragraph:&#39;, p)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4\u3001\u8fd0\u884c\u722c\u866b<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fd0\u884c\u722c\u866b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-shell\">scrapy crawl myspider<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>Scrapy\u5c06\u4f1a\u81ea\u52a8\u5904\u7406\u8bf7\u6c42\u3001\u54cd\u5e94\u548c\u6570\u636e\u63d0\u53d6\uff0c\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u3001\u9ad8\u6548\u7684\u6570\u636e\u6293\u53d6\u4efb\u52a1\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u6570\u636e\u5b58\u50a8\u4e0e\u5904\u7406<\/h3>\n<\/p>\n<p><p>\u5728\u6570\u636e\u91c7\u96c6\u5b8c\u6210\u540e\uff0c\u901a\u5e38\u9700\u8981\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6570\u636e\u5e93\u6216\u6587\u4ef6\u4e2d\u8fdb\u884c\u8fdb\u4e00\u6b65\u5904\u7406\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b58\u50a8\u5230CSV\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528Python\u7684csv\u6a21\u5757\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import csv<\/p>\n<h2><strong>\u5b9a\u4e49\u6570\u636e<\/strong><\/h2>\n<p>data = [<\/p>\n<p>    [&#39;Title&#39;, &#39;Paragraph&#39;],<\/p>\n<p>    [&#39;Example Title&#39;, &#39;This is a paragraph.&#39;]<\/p>\n<p>]<\/p>\n<h2><strong>\u6253\u5f00CSV\u6587\u4ef6\uff0c\u5199\u5165\u6570\u636e<\/strong><\/h2>\n<p>with open(&#39;data.csv&#39;, &#39;w&#39;, newline=&#39;&#39;, encoding=&#39;utf-8&#39;) as file:<\/p>\n<p>    writer = csv.writer(file)<\/p>\n<p>    writer.writerows(data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u5b58\u50a8\u5230\u6570\u636e\u5e93<\/h4>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528SQLAlchemy\u5e93\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6570\u636e\u5e93\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from sqlalchemy import create_engine, Column, Integer, String, Base<\/p>\n<h2><strong>\u521b\u5efa\u6570\u636e\u5e93\u5f15\u64ce<\/strong><\/h2>\n<p>engine = create_engine(&#39;sqlite:\/\/\/data.db&#39;)<\/p>\n<h2><strong>\u5b9a\u4e49\u6570\u636e\u6a21\u578b<\/strong><\/h2>\n<p>class Data(Base):<\/p>\n<p>    __tablename__ = &#39;data&#39;<\/p>\n<p>    id = Column(Integer, primary_key=True)<\/p>\n<p>    title = Column(String)<\/p>\n<p>    paragraph = Column(String)<\/p>\n<h2><strong>\u521b\u5efa\u8868<\/strong><\/h2>\n<p>Base.metadata.create_all(engine)<\/p>\n<h2><strong>\u521b\u5efa\u6570\u636e\u5e93\u4f1a\u8bdd<\/strong><\/h2>\n<p>from sqlalchemy.orm import sessionmaker<\/p>\n<p>Session = sessionmaker(bind=engine)<\/p>\n<p>session = Session()<\/p>\n<h2><strong>\u63d2\u5165\u6570\u636e<\/strong><\/h2>\n<p>new_data = Data(title=&#39;Example Title&#39;, paragraph=&#39;This is a paragraph.&#39;)<\/p>\n<p>session.add(new_data)<\/p>\n<p>session.commit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u53ef\u4ee5\u5c06\u91c7\u96c6\u5230\u7684\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4fbf\u4e8e\u540e\u7eed\u7684\u5206\u6790\u548c\u5904\u7406\u3002<\/p>\n<\/p>\n<p><h3>\u4e03\u3001\u5e38\u89c1\u95ee\u9898\u4e0e\u89e3\u51b3\u65b9\u6848<\/h3>\n<\/p>\n<p><p>\u5728\u6570\u636e\u91c7\u96c6\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u5e38\u89c1\u95ee\u9898\uff0c\u5982\u53cd\u722c\u866b\u673a\u5236\u3001\u6570\u636e\u89e3\u6790\u9519\u8bef\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u95ee\u9898\u53ca\u5176\u89e3\u51b3\u65b9\u6848\uff1a<\/p>\n<\/p>\n<p><h4>1\u3001\u53cd\u722c\u866b\u673a\u5236<\/h4>\n<\/p>\n<p><p>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u91c7\u7528\u53cd\u722c\u866b\u673a\u5236\uff0c\u5982IP\u5c01\u9501\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u65b9\u6cd5\u5e94\u5bf9\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u4f7f\u7528\u4ee3\u7406IP<\/strong>\uff1a\u901a\u8fc7\u66f4\u6362\u4ee3\u7406IP\uff0c\u907f\u514d\u88ab\u5c01\u9501\u3002<\/li>\n<li><strong>\u6a21\u62df\u4eba\u7c7b\u884c\u4e3a<\/strong>\uff1a\u6dfb\u52a0\u968f\u673a\u5ef6\u65f6\u3001\u6a21\u62df\u9f20\u6807\u70b9\u51fb\u7b49\uff0c\u51cf\u5c11\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u7684\u98ce\u9669\u3002<\/li>\n<li><strong>\u4f7f\u7528\u9ad8\u7ea7\u722c\u866b\u6846\u67b6<\/strong>\uff1a\u5982Scrapy\uff0c\u63d0\u4f9b\u4e86\u66f4\u5f3a\u5927\u7684\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236\u7684\u529f\u80fd\u3002<\/li>\n<\/ul>\n<p><h4>2\u3001\u6570\u636e\u89e3\u6790\u9519\u8bef<\/h4>\n<\/p>\n<p><p>\u5728\u89e3\u6790HTML\u5185\u5bb9\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u6570\u636e\u89e3\u6790\u9519\u8bef\u3002\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u65b9\u6cd5\u89e3\u51b3\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u68c0\u67e5HTML\u7ed3\u6784<\/strong>\uff1a\u786e\u4fddHTML\u7ed3\u6784\u672a\u53d1\u751f\u53d8\u5316\uff0c\u8c03\u6574\u89e3\u6790\u903b\u8f91\u3002<\/li>\n<li><strong>\u4f7f\u7528\u66f4\u5f3a\u5927\u7684\u89e3\u6790\u5e93<\/strong>\uff1a\u5982lxml\uff0c\u63d0\u4f9b\u66f4\u9ad8\u6548\u3001\u51c6\u786e\u7684\u89e3\u6790\u529f\u80fd\u3002<\/li>\n<\/ul>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u6709\u6548\u89e3\u51b3\u6570\u636e\u91c7\u96c6\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u5e38\u89c1\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h3>\u516b\u3001\u6570\u636e\u91c7\u96c6\u7684\u6cd5\u5f8b\u4e0e\u9053\u5fb7\u95ee\u9898<\/h3>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u6570\u636e\u91c7\u96c6\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u6cd5\u5f8b\u4e0e\u9053\u5fb7\u95ee\u9898\u3002\u672a\u7ecf\u6388\u6743\u7684\u6570\u636e\u91c7\u96c6\u53ef\u80fd\u4fb5\u72af\u7f51\u7ad9\u7684\u77e5\u8bc6\u4ea7\u6743\u6216\u7528\u6237\u9690\u79c1\u3002\u5e94\u9075\u5faa\u4ee5\u4e0b\u539f\u5219\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u9075\u5b88\u6cd5\u5f8b\u6cd5\u89c4<\/strong>\uff1a\u786e\u4fdd\u6570\u636e\u91c7\u96c6\u884c\u4e3a\u5408\u6cd5\uff0c\u4e0d\u4fb5\u72af\u4ed6\u4eba\u6743\u76ca\u3002<\/li>\n<li><strong>\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6<\/strong>\uff1a\u9075\u5faa\u7f51\u7ad9robots.txt\u6587\u4ef6\u4e2d\u7684\u89c4\u5219\uff0c\u907f\u514d\u91c7\u96c6\u88ab\u7981\u6b62\u7684\u6570\u636e\u3002<\/li>\n<li><strong>\u83b7\u5f97\u6388\u6743<\/strong>\uff1a\u5728\u91c7\u96c6\u654f\u611f\u6570\u636e\u65f6\uff0c\u83b7\u5f97\u7f51\u7ad9\u6216\u6570\u636e\u6240\u6709\u8005\u7684\u6388\u6743\u3002<\/li>\n<\/ul>\n<p><p>\u901a\u8fc7\u9075\u5faa\u6cd5\u5f8b\u4e0e\u9053\u5fb7\u539f\u5219\uff0c\u53ef\u4ee5\u786e\u4fdd\u6570\u636e\u91c7\u96c6\u884c\u4e3a\u5408\u6cd5\u3001\u5408\u89c4\u3002<\/p>\n<\/p>\n<p><h3>\u4e5d\u3001\u5b9e\u9645\u5e94\u7528\u6848\u4f8b<\/h3>\n<\/p>\n<p><p>\u6570\u636e\u91c7\u96c6\u5728\u5b9e\u9645\u4e2d\u6709\u5e7f\u6cdb\u7684\u5e94\u7528\uff0c\u5982\u7535\u5546\u6570\u636e\u5206\u6790\u3001\u793e\u4ea4\u5a92\u4f53\u6570\u636e\u6316\u6398\u3001\u65b0\u95fb\u8d44\u8baf\u76d1\u63a7\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b9e\u9645\u5e94\u7528\u6848\u4f8b\uff1a<\/p>\n<\/p>\n<p><h4>1\u3001\u7535\u5546\u6570\u636e\u5206\u6790<\/h4>\n<\/p>\n<p><p>\u53ef\u4ee5\u901a\u8fc7\u6570\u636e\u91c7\u96c6\u83b7\u53d6\u7535\u5546\u5e73\u53f0\u7684\u5546\u54c1\u4fe1\u606f\u3001\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\uff0c\u8fdb\u884c\u5e02\u573a\u5206\u6790\u548c\u7ade\u4e89\u5bf9\u624b\u7814\u7a76\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>def get_product_info(url):<\/p>\n<p>    headers = {<\/p>\n<p>        &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>    }<\/p>\n<p>    response = requests.get(url, headers=headers)<\/p>\n<p>    soup = BeautifulSoup(response.text, &#39;lxml&#39;)<\/p>\n<p>    title = soup.find(&#39;span&#39;, {&#39;id&#39;: &#39;productTitle&#39;}).text.strip()<\/p>\n<p>    price = soup.find(&#39;span&#39;, {&#39;id&#39;: &#39;priceblock_ourprice&#39;}).text.strip()<\/p>\n<p>    rating = soup.find(&#39;span&#39;, {&#39;class&#39;: &#39;a-icon-alt&#39;}).text.strip()<\/p>\n<p>    return {<\/p>\n<p>        &#39;title&#39;: title,<\/p>\n<p>        &#39;price&#39;: price,<\/p>\n<p>        &#39;rating&#39;: rating<\/p>\n<p>    }<\/p>\n<p>product_url = &#39;https:\/\/www.amazon.com\/dp\/B08N5WRWNW&#39;<\/p>\n<p>product_info = get_product_info(product_url)<\/p>\n<p>print(product_info)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u4ee3\u7801\uff0c\u53ef\u4ee5\u83b7\u53d6\u6307\u5b9a\u5546\u54c1\u7684\u6807\u9898\u3001\u4ef7\u683c\u548c\u8bc4\u5206\u4fe1\u606f\uff0c\u8fdb\u884c\u8fdb\u4e00\u6b65\u7684\u5206\u6790\u548c\u5904\u7406\u3002<\/p>\n<\/p>\n<p><h3>\u5341\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u5229\u7528Python\u8fdb\u884c\u6570\u636e\u91c7\u96c6\u7684\u65b9\u6cd5\u591a\u79cd\u591a\u6837\uff0c\u5305\u62ec\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u9875\u9762\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316\u3001\u8c03\u7528API\u63a5\u53e3\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6\u3002\u901a\u8fc7\u7ed3\u5408\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u53ef\u4ee5\u9ad8\u6548\u5730\u91c7\u96c6\u6240\u9700\u7684\u6570\u636e\uff0c\u5e76\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u8fdb\u884c\u8fdb\u4e00\u6b65\u5904\u7406\u3002\u5728\u8fdb\u884c\u6570\u636e\u91c7\u96c6\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u53cd\u722c\u866b\u673a\u5236\u3001\u6570\u636e\u89e3\u6790\u9519\u8bef\u7b49\u5e38\u89c1\u95ee\u9898\uff0c\u5e76\u9075\u5faa\u6cd5\u5f8b\u4e0e\u9053\u5fb7\u539f\u5219\uff0c\u786e\u4fdd\u6570\u636e\u91c7\u96c6\u884c\u4e3a\u5408\u6cd5\u3001\u5408\u89c4\u3002\u6570\u636e\u91c7\u96c6\u5728\u7535\u5546\u6570\u636e\u5206\u6790\u3001\u793e\u4ea4\u5a92\u4f53\u6570\u636e\u6316\u6398\u7b49\u5b9e\u9645\u5e94\u7528\u4e2d\u5177\u6709\u5e7f\u6cdb\u7684\u5e94\u7528\u524d\u666f\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u8fdb\u884c\u6570\u636e\u91c7\u96c6\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u8fdb\u884c\u6570\u636e\u91c7\u96c6\u65f6\uff0c\u901a\u5e38\u9700\u8981\u51e0\u4e2a\u6b65\u9aa4\uff1a\u9996\u5148\uff0c\u9009\u62e9\u9002\u5408\u7684\u5e93\uff0c\u5982Requests\u7528\u4e8e\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0cBeautifulSoup\u6216lxml\u7528\u4e8e\u89e3\u6790HTML\u3002\u63a5\u7740\uff0c\u786e\u5b9a\u6570\u636e\u6e90\uff0c\u53ef\u80fd\u662f\u7f51\u7ad9\u3001API\u6216\u6570\u636e\u5e93\u3002\u7136\u540e\uff0c\u7f16\u5199\u4ee3\u7801\u4ee5\u8bf7\u6c42\u6570\u636e\u5e76\u89e3\u6790\u6240\u9700\u7684\u4fe1\u606f\uff0c\u6700\u540e\u5c06\u91c7\u96c6\u5230\u7684\u6570\u636e\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u4ee5\u4fbf\u540e\u7eed\u5206\u6790\u3002<\/p>\n<p><strong>Python\u4e2d\u6709\u54ea\u4e9b\u5e38\u7528\u7684\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u8fdb\u884c\u6570\u636e\u91c7\u96c6\uff1f<\/strong><br \/>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5f3a\u5927\u7684\u5e93\u6765\u652f\u6301\u6570\u636e\u91c7\u96c6\u3002\u5e38\u7528\u7684\u5e93\u5305\u62ecRequests\uff08\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff09\uff0cBeautifulSoup\u548clxml\uff08\u7528\u4e8e\u89e3\u6790\u548c\u63d0\u53d6HTML\/XML\u6570\u636e\uff09\uff0cScrapy\uff08\u4e00\u4e2a\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff09\uff0cPandas\uff08\u7528\u4e8e\u6570\u636e\u5904\u7406\u548c\u5206\u6790\uff09\uff0c\u4ee5\u53caSelenium\uff08\u7528\u4e8e\u5904\u7406\u9700\u8981JavaScript\u4ea4\u4e92\u7684\u7f51\u7ad9\uff09\u3002\u8fd9\u4e9b\u5e93\u5404\u5177\u7279\u8272\uff0c\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u4f7f\u7528\u3002<\/p>\n<p><strong>\u5728\u91c7\u96c6\u6570\u636e\u65f6\uff0c\u6709\u54ea\u4e9b\u6ce8\u610f\u4e8b\u9879\u9700\u8981\u9075\u5faa\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u6570\u636e\u91c7\u96c6\u65f6\uff0c\u9075\u5faa\u4e00\u4e9b\u6700\u4f73\u5b9e\u8df5\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u9996\u5148\uff0c\u786e\u4fdd\u9075\u5b88\u76ee\u6807\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\uff0c\u4ee5\u907f\u514d\u4fb5\u72af\u5176\u4f7f\u7528\u653f\u7b56\u3002\u5176\u6b21\uff0c\u5408\u7406\u8bbe\u7f6e\u8bf7\u6c42\u9891\u7387\uff0c\u4ee5\u9632\u6b62\u5bf9\u76ee\u6807\u670d\u52a1\u5668\u9020\u6210\u8d1f\u62c5\u6216\u88ab\u5c01\u7981\u3002\u540c\u65f6\uff0c\u5904\u7406\u6570\u636e\u65f6\u8981\u6ce8\u610f\u6570\u636e\u7684\u51c6\u786e\u6027\u548c\u5b8c\u6574\u6027\u3002\u6b64\u5916\uff0c\u5c0a\u91cd\u4e2a\u4eba\u9690\u79c1\uff0c\u907f\u514d\u91c7\u96c6\u654f\u611f\u4fe1\u606f\uff0c\u786e\u4fdd\u5408\u6cd5\u5408\u89c4\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5229\u7528Python\u91c7\u96c6\u6570\u636e\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790H [&hellip;]","protected":false},"author":3,"featured_media":1175302,"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\/1175295"}],"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=1175295"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1175295\/revisions"}],"predecessor-version":[{"id":1175307,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1175295\/revisions\/1175307"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1175302"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1175295"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1175295"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1175295"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}