{"id":1055641,"date":"2024-12-31T14:52:29","date_gmt":"2024-12-31T06:52:29","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1055641.html"},"modified":"2024-12-31T14:52:43","modified_gmt":"2024-12-31T06:52:43","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e7%bd%91%e9%a1%b5%e4%b8%8d%e5%90%8c%e7%9a%84%e5%ad%97%e6%ae%b5","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1055641.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u7f51\u9875\u4e0d\u540c\u7684\u5b57\u6bb5"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/a9069258-7eb7-48e1-9671-4fea89549f1d.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u7f51\u9875\u4e0d\u540c\u7684\u5b57\u6bb5\" \/><\/p>\n<p><p> <strong>Python\u722c\u53d6\u7f51\u9875\u4e0d\u540c\u5b57\u6bb5\u7684\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528requests\u6a21\u5757\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u6216lxml\u89e3\u6790HTML\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e\u3001\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002<\/strong> \u672c\u6587\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u65b9\u6cd5\u6765\u722c\u53d6\u7f51\u9875\u7684\u4e0d\u540c\u5b57\u6bb5\u3002\u91cd\u70b9\u4ecb\u7ecdrequests\u6a21\u5757\u548cBeautifulSoup\u5e93\u7684\u7ec4\u5408\uff0c\u4ee5\u4fbf\u4e8e\u65b0\u624b\u66f4\u5bb9\u6613\u4e0a\u624b\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528requests\u6a21\u5757\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u4f7f\u7528requests\u6a21\u5757\u83b7\u53d6\u7f51\u9875\u7684\u5185\u5bb9\u3002requests\u662f\u4e00\u4e2a\u975e\u5e38\u7b80\u5355\u548c\u6613\u4e8e\u4f7f\u7528\u7684HTTP\u5e93\u3002\u901a\u8fc7\u5b83\uff0c\u6211\u4eec\u53ef\u4ee5\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/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<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684Python\u5e93\u3002\u5b83\u63d0\u4f9b\u4e86\u7b80\u5355\u7684API\u6765\u63d0\u53d6HTML\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5BeautifulSoup<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528pip\u6765\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p>pip install lxml<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u89e3\u6790HTML<\/h4>\n<\/p>\n<p><p>\u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff0c\u4f7f\u7528BeautifulSoup\u89e3\u6790\u6211\u4eec\u4ecerequests\u83b7\u53d6\u7684HTML\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;lxml&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u4e0d\u540c\u5b57\u6bb5<\/h3>\n<\/p>\n<p><h4>1\u3001\u63d0\u53d6\u6807\u9898<\/h4>\n<\/p>\n<p><p>\u7f51\u9875\u7684\u6807\u9898\u901a\u5e38\u5728<code>&lt;title&gt;<\/code>\u6807\u7b7e\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6765\u63d0\u53d6\u8fd9\u4e2a\u6807\u7b7e\u7684\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">title = soup.title.string<\/p>\n<p>print(&#39;Title:&#39;, title)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u63d0\u53d6\u6240\u6709\u94fe\u63a5<\/h4>\n<\/p>\n<p><p>\u7f51\u9875\u4e2d\u7684\u94fe\u63a5\u901a\u5e38\u5728<code>&lt;a&gt;<\/code>\u6807\u7b7e\u7684<code>href<\/code>\u5c5e\u6027\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6765\u63d0\u53d6\u6240\u6709\u94fe\u63a5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">links = soup.find_all(&#39;a&#39;)<\/p>\n<p>for link in links:<\/p>\n<p>    print(&#39;Link:&#39;, link.get(&#39;href&#39;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3\u3001\u63d0\u53d6\u7279\u5b9a\u5b57\u6bb5<\/h4>\n<\/p>\n<p><p>\u5047\u8bbe\u6211\u4eec\u60f3\u63d0\u53d6\u7279\u5b9a\u7684\u5b57\u6bb5\uff0c\u6bd4\u5982\u7f51\u9875\u4e2d\u7684\u65b0\u95fb\u6807\u9898\u3002\u8fd9\u4e9b\u6807\u9898\u53ef\u80fd\u5728\u7279\u5b9a\u7684HTML\u6807\u7b7e\u4e2d\uff0c\u4f8b\u5982<code>&lt;h1&gt;<\/code>\u3001<code>&lt;h2&gt;<\/code>\u6216\u5e26\u6709\u7279\u5b9aclass\u7684<code>&lt;div&gt;<\/code>\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u7684\u67e5\u627e\u51fd\u6570\u6765\u63d0\u53d6\u8fd9\u4e9b\u5b57\u6bb5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">news_titles = soup.find_all(&#39;h2&#39;, class_=&#39;news-title&#39;)<\/p>\n<p>for title in news_titles:<\/p>\n<p>    print(&#39;News Title:&#39;, title.string)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u6709\u65f6\uff0c\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u66f4\u7075\u6d3b\u5730\u63d0\u53d6\u6570\u636e\u3002Python\u7684re\u6a21\u5757\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u64cd\u4f5c\u529f\u80fd\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import re<\/p>\n<p>html_content = requests.get(url).text<\/p>\n<p>em<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>ls = re.findall(r&#39;[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Za-z]{2,}&#39;, html_content)<\/p>\n<p>for email in emails:<\/p>\n<p>    print(&#39;Email:&#39;, email)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u4e00\u4e9b\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528Selenium\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002Selenium\u53ef\u4ee5\u63a7\u5236\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u64cd\u4f5c\uff0c\u5e76\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5Selenium<\/h4>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u4f7f\u7528Selenium<\/h4>\n<\/p>\n<p><p>\u4e0b\u9762\u662f\u4e00\u4e2a\u4f7f\u7528Selenium\u6253\u5f00\u7f51\u9875\u5e76\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(&#39;http:\/\/example.com&#39;)<\/p>\n<h2><strong>\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n<p>driver.implicitly_wait(10)<\/p>\n<h2><strong>\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9<\/strong><\/h2>\n<p>dynamic_content = driver.find_element_by_id(&#39;dynamic-content&#39;).text<\/p>\n<p>print(&#39;Dynamic Content:&#39;, dynamic_content)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u722c\u53d6\u7f51\u9875\u7684\u5b8c\u6574\u793a\u4f8b<\/h3>\n<\/p>\n<p><p>\u4e0b\u9762\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\uff0c\u4f7f\u7528requests\u548cBeautifulSoup\u6765\u722c\u53d6\u7f51\u9875\u7684\u4e0d\u540c\u5b57\u6bb5\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<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<h2><strong>\u89e3\u6790HTML<\/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<p>print(&#39;Title:&#39;, title)<\/p>\n<h2><strong>\u63d0\u53d6\u6240\u6709\u94fe\u63a5<\/strong><\/h2>\n<p>links = soup.find_all(&#39;a&#39;)<\/p>\n<p>for link in links:<\/p>\n<p>    print(&#39;Link:&#39;, link.get(&#39;href&#39;))<\/p>\n<h2><strong>\u63d0\u53d6\u7279\u5b9a\u5b57\u6bb5<\/strong><\/h2>\n<p>news_titles = soup.find_all(&#39;h2&#39;, class_=&#39;news-title&#39;)<\/p>\n<p>for title in news_titles:<\/p>\n<p>    print(&#39;News Title:&#39;, title.string)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e03\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u5f88\u591a\u7f51\u7ad9\u4f1a\u6709\u53cd\u722c\u866b\u673a\u5236\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u53cd\u722c\u866b\u673a\u5236\u548c\u5e94\u5bf9\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><h4>1\u3001User-Agent<\/h4>\n<\/p>\n<p><p>\u7f51\u7ad9\u53ef\u4ee5\u901a\u8fc7\u68c0\u67e5User-Agent\u6765\u8bc6\u522b\u722c\u866b\u3002\u6211\u4eec\u53ef\u4ee5\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\u6765\u7ed5\u8fc7\u8fd9\u4e2a\u68c0\u67e5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">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\/58.0.3029.110 Safari\/537.3&#39;}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001Cookies<\/h4>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u901a\u8fc7\u68c0\u67e5Cookies\u6765\u8bc6\u522b\u722c\u866b\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7requests\u5e93\u7684<code>Session<\/code>\u5bf9\u8c61\u6765\u4fdd\u6301\u4f1a\u8bdd\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">session = requests.Session()<\/p>\n<p>response = session.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3\u3001IP\u5c01\u7981<\/h4>\n<\/p>\n<p><p>\u5bf9\u4e8e\u9891\u7e41\u8bbf\u95ee\u7684\u722c\u866b\uff0c\u7f51\u7ad9\u53ef\u80fd\u4f1a\u5c01\u7981IP\u3002\u89e3\u51b3\u65b9\u6cd5\u53ef\u4ee5\u662f\u4f7f\u7528\u4ee3\u7406IP\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/yourproxy.com:port&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/yourproxy.com:port&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4\u3001\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9<\/h4>\n<\/p>\n<p><p>\u5982\u524d\u6587\u6240\u8ff0\uff0c\u5bf9\u4e8e\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><h3>\u516b\u3001\u6570\u636e\u5b58\u50a8<\/h3>\n<\/p>\n<p><p>\u722c\u53d6\u5230\u7684\u6570\u636e\u53ef\u4ee5\u5b58\u50a8\u5728\u4e0d\u540c\u7684\u5730\u65b9\uff0c\u5982\u6587\u4ef6\u3001\u6570\u636e\u5e93\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u5b58\u50a8\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><h4>1\u3001\u5b58\u50a8\u5230\u6587\u4ef6<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">with open(&#39;data.txt&#39;, &#39;w&#39;) as file:<\/p>\n<p>    file.write(html_content)<\/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\u7528\u6570\u636e\u5e93\u5982MySQL\u3001MongoDB\u7b49\u6765\u5b58\u50a8\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u5b58\u50a8\u5230MySQL\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import mysql.connector<\/p>\n<p>conn = mysql.connector.connect(<\/p>\n<p>    host=&#39;localhost&#39;,<\/p>\n<p>    user=&#39;user&#39;,<\/p>\n<p>    password=&#39;password&#39;,<\/p>\n<p>    database=&#39;database&#39;<\/p>\n<p>)<\/p>\n<p>cursor = conn.cursor()<\/p>\n<p>sql = &quot;INSERT INTO table (column1, column2) VALUES (%s, %s)&quot;<\/p>\n<p>values = (value1, value2)<\/p>\n<p>cursor.execute(sql, values)<\/p>\n<p>conn.commit()<\/p>\n<p>cursor.close()<\/p>\n<p>conn.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e5d\u3001\u5904\u7406\u5f02\u5e38<\/h3>\n<\/p>\n<p><p>\u5728\u722c\u866b\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u3002\u6211\u4eec\u9700\u8981\u5904\u7406\u8fd9\u4e9b\u5f02\u5e38\uff0c\u4ee5\u786e\u4fdd\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">try:<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    response.raise_for_status()<\/p>\n<p>except requests.exceptions.RequestException as e:<\/p>\n<p>    print(&#39;Error:&#39;, e)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u5341\u3001\u9075\u5b88\u722c\u866b\u7684\u6cd5\u5f8b\u548c\u4f26\u7406<\/h3>\n<\/p>\n<p><p>\u6700\u540e\uff0c\u722c\u866b\u9700\u8981\u9075\u5b88\u76f8\u5173\u7684\u6cd5\u5f8b\u548c\u4f26\u7406\u3002\u4e0d\u8981\u722c\u53d6\u654f\u611f\u4fe1\u606f\uff0c\u4e0d\u8981\u9891\u7e41\u8bbf\u95ee\u7f51\u7ad9\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from urllib.robotparser import RobotFileParser<\/p>\n<p>rp = RobotFileParser()<\/p>\n<p>rp.set_url(&#39;http:\/\/example.com\/robots.txt&#39;)<\/p>\n<p>rp.read()<\/p>\n<p>if rp.can_fetch(&#39;*&#39;, url):<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>else:<\/p>\n<p>    print(&#39;Not allowed to crawl this URL&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4ee5\u4e0a\u5185\u5bb9\u8be6\u7ec6\u4ecb\u7ecd\u4e86Python\u5982\u4f55\u722c\u53d6\u7f51\u9875\u4e0d\u540c\u7684\u5b57\u6bb5\uff0c\u5305\u62ec\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u89e3\u6790HTML\u3001\u63d0\u53d6\u6570\u636e\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\u3001\u6570\u636e\u5b58\u50a8\u548c\u5f02\u5e38\u5904\u7406\u7b49\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u548c\u5e94\u7528Python\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u6570\u636e\u5b57\u6bb5\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u53ef\u4ee5\u5229\u7528\u5e93\u5982BeautifulSoup\u548cRequests\u6765\u63d0\u53d6\u7279\u5b9a\u5b57\u6bb5\u3002\u9996\u5148\uff0c\u4f7f\u7528Requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\uff0c\u6700\u540e\u901a\u8fc7\u67e5\u627e\u7279\u5b9a\u7684\u6807\u7b7e\u6216\u5c5e\u6027\u6765\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u5b57\u6bb5\u3002\u4f8b\u5982\uff0c\u4f7f\u7528<code>find()<\/code>\u6216<code>find_all()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u5b9a\u4f4d\u5230\u7279\u5b9a\u7684HTML\u5143\u7d20\uff0c\u5e76\u63d0\u53d6\u5176\u6587\u672c\u6216\u5c5e\u6027\u503c\u3002<\/p>\n<p><strong>\u5bf9\u4e8e\u521d\u5b66\u8005\uff0c\u6709\u54ea\u4e9bPython\u5e93\u63a8\u8350\u7528\u4e8e\u7f51\u9875\u722c\u53d6\uff1f<\/strong><br \/>\u5bf9\u4e8e\u521d\u5b66\u8005\uff0c\u63a8\u8350\u4f7f\u7528Requests\u548cBeautifulSoup\u7ec4\u5408\u3002Requests\u5e93\u975e\u5e38\u9002\u5408\u5904\u7406HTTP\u8bf7\u6c42\uff0c\u80fd\u591f\u8f7b\u677e\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684HTML\u89e3\u6790\u529f\u80fd\uff0c\u5e2e\u52a9\u7528\u6237\u5feb\u901f\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002\u6b64\u5916\uff0cScrapy\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u9700\u8981\u66f4\u590d\u6742\u722c\u53d6\u4efb\u52a1\u7684\u7528\u6237\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u7f51\u9875\u65f6\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4e3a\u4e86\u9632\u6b62\u722c\u866b\uff0c\u4f1a\u91c7\u53d6\u53cd\u722c\u866b\u63aa\u65bd\uff0c\u5982\u9650\u5236\u8bf7\u6c42\u9891\u7387\u548c\u68c0\u6d4b\u7528\u6237\u4ee3\u7406\u3002\u4e3a\u5e94\u5bf9\u8fd9\u4e9b\u60c5\u51b5\uff0c\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff08\u5982User-Agent\uff09\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u4f7f\u7528\u968f\u673a\u7684\u8bf7\u6c42\u95f4\u9694\u6765\u964d\u4f4e\u88ab\u68c0\u6d4b\u7684\u98ce\u9669\uff0c\u751a\u81f3\u4f7f\u7528\u4ee3\u7406IP\u6765\u9690\u85cf\u771f\u5b9eIP\u5730\u5740\u3002\u6b64\u5916\uff0c\u4f7f\u7528selenium\u53ef\u4ee5\u6a21\u62df\u5b8c\u6574\u7684\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u5e2e\u52a9\u5904\u7406\u4e00\u4e9b\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e\u3002<\/p>\n<p><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u5982\u4f55\u5c06\u6570\u636e\u5b58\u50a8\u5230\u672c\u5730\u6587\u4ef6\u4e2d\uff1f<\/strong><br \/>\u5728\u722c\u53d6\u5230\u6240\u9700\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5185\u7f6e\u6587\u4ef6\u64cd\u4f5c\u529f\u80fd\u5c06\u6570\u636e\u4fdd\u5b58\u5230\u672c\u5730\u3002\u5e38\u89c1\u7684\u683c\u5f0f\u5305\u62ecCSV\u548cJSON\u3002\u4f7f\u7528<code>csv<\/code>\u6a21\u5757\u53ef\u4ee5\u5c06\u6570\u636e\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\uff0c\u800c\u4f7f\u7528<code>json<\/code>\u6a21\u5757\u5219\u9002\u5408\u4fdd\u5b58\u4e3aJSON\u683c\u5f0f\u3002\u8fd9\u4e24\u79cd\u683c\u5f0f\u90fd\u65b9\u4fbf\u540e\u7eed\u7684\u6570\u636e\u5904\u7406\u548c\u5206\u6790\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u7f51\u9875\u4e0d\u540c\u5b57\u6bb5\u7684\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528requests\u6a21\u5757\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u6216l [&hellip;]","protected":false},"author":3,"featured_media":1055674,"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\/1055641"}],"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=1055641"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1055641\/revisions"}],"predecessor-version":[{"id":1055681,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1055641\/revisions\/1055681"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1055674"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1055641"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1055641"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1055641"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}