{"id":1080916,"date":"2025-01-08T12:34:43","date_gmt":"2025-01-08T04:34:43","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1080916.html"},"modified":"2025-01-08T12:34:45","modified_gmt":"2025-01-08T04:34:45","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%88%ac%e5%8f%96%e5%bd%a9%e7%a5%a8%e4%b8%ad%e5%a5%96%e4%bf%a1%e6%81%af-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1080916.html","title":{"rendered":"\u5982\u4f55\u7528python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24183210\/efef366f-f626-485f-85b3-a1f9488aae98.webp\" alt=\"\u5982\u4f55\u7528python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\" \/><\/p>\n<p><p> <strong>\u5982\u4f55\u7528Python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f<\/strong><\/p>\n<\/p>\n<p><p><strong>\u7528Python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\uff0c\u9996\u5148\u9700\u8981\u9009\u62e9\u5408\u9002\u7684\u7f51\u7ad9\u3001\u4f7f\u7528\u9002\u5f53\u7684\u5e93\u8fdb\u884c\u7f51\u9875\u8bf7\u6c42\u548c\u89e3\u6790\u3001\u5904\u7406\u6570\u636e\u5e76\u5b58\u50a8\uff0c\u4ee5\u4e0b\u662f\u8be6\u7ec6\u6b65\u9aa4\uff1a\u9009\u62e9\u6570\u636e\u6e90\u7f51\u7ad9\u3001\u4f7f\u7528requests\u5e93\u8fdb\u884c\u7f51\u9875\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u63d0\u53d6\u5e76\u5904\u7406\u6570\u636e\u3001\u5b58\u50a8\u6570\u636e\u3002<\/strong>\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u6b65\u9aa4\u4e2d\u7684\u6bcf\u4e00\u6b65\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u9009\u62e9\u6570\u636e\u6e90\u7f51\u7ad9<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u4e4b\u524d\uff0c\u9996\u5148\u8981\u9009\u62e9\u4e00\u4e2a\u6570\u636e\u6e90\u7f51\u7ad9\uff0c\u8fd9\u4e2a\u7f51\u7ad9\u9700\u8981\u63d0\u4f9b\u8be6\u7ec6\u7684\u5f00\u5956\u4fe1\u606f\uff0c\u5e76\u4e14\u7f51\u9875\u7ed3\u6784\u76f8\u5bf9\u7b80\u5355\uff0c\u65b9\u4fbf\u89e3\u6790\u3002\u5e38\u89c1\u7684\u6570\u636e\u6e90\u5305\u62ec\u5b98\u65b9\u5f69\u7968\u7f51\u7ad9\u3001\u7b2c\u4e09\u65b9\u6570\u636e\u7edf\u8ba1\u7f51\u7ad9\u7b49\u3002\u9009\u62e9\u6570\u636e\u6e90\u65f6\uff0c\u9700\u8981\u786e\u4fdd\u8be5\u7f51\u7ad9\u7684\u5185\u5bb9\u5b9a\u671f\u66f4\u65b0\uff0c\u5e76\u4e14\u6709\u53ef\u9760\u7684\u5386\u53f2\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528requests\u5e93\u8fdb\u884c\u7f51\u9875\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>\u5728\u9009\u62e9\u597d\u6570\u636e\u6e90\u7f51\u7ad9\u540e\uff0c\u63a5\u4e0b\u6765\u9700\u8981\u4f7f\u7528Python\u7684requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002requests\u5e93\u662fPython\u4e2d\u5e38\u7528\u7684HTTP\u5e93\uff0c\u529f\u80fd\u5f3a\u5927\u4e14\u4f7f\u7528\u7b80\u5355\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com\/lottery-results&#39;  # \u66ff\u6362\u4e3a\u5b9e\u9645\u7684URL<\/p>\n<p>response = requests.get(url)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    page_content = response.content<\/p>\n<p>else:<\/p>\n<p>    print(&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve data&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5b9a\u4e49\u4e86\u76ee\u6807URL\uff0c\u7136\u540e\u4f7f\u7528requests.get()\u65b9\u6cd5\u53d1\u9001GET\u8bf7\u6c42\u3002\u5982\u679c\u8bf7\u6c42\u6210\u529f\uff08\u72b6\u6001\u7801\u4e3a200\uff09\uff0c\u5219\u5c06\u9875\u9762\u5185\u5bb9\u5b58\u50a8\u5728page_content\u53d8\u91cf\u4e2d\uff0c\u5426\u5219\u8f93\u51fa\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u5230\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u9700\u8981\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790HTML\u6587\u6863\u3002BeautifulSoup\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684Python\u5e93\uff0c\u80fd\u591f\u65b9\u4fbf\u5730\u63d0\u53d6HTML\u548cXML\u6587\u4ef6\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(page_content, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u8fdb\u4e00\u6b65\u89e3\u6790\u5177\u4f53\u7684\u5f00\u5956\u4fe1\u606f<\/strong><\/h2>\n<h2><strong>\u5047\u8bbe\u6211\u4eec\u8981\u63d0\u53d6\u7684\u5f00\u5956\u4fe1\u606f\u5728\u4e00\u4e2a\u7279\u5b9a\u7684\u8868\u683c\u4e2d<\/strong><\/h2>\n<p>table = soup.find(&#39;table&#39;, {&#39;id&#39;: &#39;lottery-results&#39;})<\/p>\n<p>rows = table.find_all(&#39;tr&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5c06\u9875\u9762\u5185\u5bb9\u4f20\u9012\u7ed9BeautifulSoup\u5bf9\u8c61\uff0c\u5e76\u6307\u5b9a\u89e3\u6790\u5668\u4e3a&#39;html.parser&#39;\u3002\u7136\u540e\uff0c\u901a\u8fc7find()\u65b9\u6cd5\u627e\u5230\u5305\u542b\u5f00\u5956\u4fe1\u606f\u7684\u8868\u683c\uff0c\u5e76\u4f7f\u7528find_all()\u65b9\u6cd5\u83b7\u53d6\u8868\u683c\u4e2d\u7684\u6240\u6709\u884c\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u63d0\u53d6\u5e76\u5904\u7406\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u5728\u627e\u5230\u5305\u542b\u5f00\u5956\u4fe1\u606f\u7684\u8868\u683c\u540e\uff0c\u63a5\u4e0b\u6765\u9700\u8981\u63d0\u53d6\u5177\u4f53\u7684\u6570\u636e\u3002\u5047\u8bbe\u6bcf\u884c\u6570\u636e\u5bf9\u5e94\u4e00\u6b21\u5f00\u5956\u4fe1\u606f\uff0c\u6211\u4eec\u53ef\u4ee5\u904d\u5386\u6240\u6709\u884c\uff0c\u63d0\u53d6\u6bcf\u4e2a\u5355\u5143\u683c\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">lottery_results = []<\/p>\n<p>for row in rows[1:]:  # \u8df3\u8fc7\u8868\u5934<\/p>\n<p>    cells = row.find_all(&#39;td&#39;)<\/p>\n<p>    draw_date = cells[0].text.strip()<\/p>\n<p>    winning_numbers = cells[1].text.strip()<\/p>\n<p>    lottery_results.append({&#39;date&#39;: draw_date, &#39;numbers&#39;: winning_numbers})<\/p>\n<p>print(lottery_results)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u904d\u5386\u8868\u683c\u4e2d\u7684\u6bcf\u4e00\u884c\uff0c\u5e76\u4f7f\u7528find_all()\u65b9\u6cd5\u83b7\u53d6\u6bcf\u884c\u4e2d\u7684\u6240\u6709\u5355\u5143\u683c\u3002\u7136\u540e\uff0c\u63d0\u53d6\u5f00\u5956\u65e5\u671f\u548c\u4e2d\u5956\u53f7\u7801\uff0c\u5e76\u5c06\u5176\u5b58\u50a8\u5728\u5b57\u5178\u4e2d\uff0c\u6700\u540e\u5c06\u6240\u6709\u5b57\u5178\u5b58\u50a8\u5728\u4e00\u4e2a\u5217\u8868\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u5b58\u50a8\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u63d0\u53d6\u5e76\u5904\u7406\u597d\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u9009\u62e9\u5c06\u6570\u636e\u5b58\u50a8\u5230\u672c\u5730\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002\u5e38\u89c1\u7684\u5b58\u50a8\u65b9\u5f0f\u5305\u62ecCSV\u6587\u4ef6\u3001JSON\u6587\u4ef6\u3001SQLite\u6570\u636e\u5e93\u7b49\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b58\u50a8\u4e3aCSV\u6587\u4ef6<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">import csv<\/p>\n<p>with open(&#39;lottery_results.csv&#39;, &#39;w&#39;, newline=&#39;&#39;) as file:<\/p>\n<p>    writer = csv.DictWriter(file, fieldnames=[&#39;date&#39;, &#39;numbers&#39;])<\/p>\n<p>    writer.writeheader()<\/p>\n<p>    writer.writerows(lottery_results)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u5b58\u50a8\u4e3aJSON\u6587\u4ef6<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">import json<\/p>\n<p>with open(&#39;lottery_results.json&#39;, &#39;w&#39;) as file:<\/p>\n<p>    json.dump(lottery_results, file, indent=4)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3\u3001\u5b58\u50a8\u5230SQLite\u6570\u636e\u5e93<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">import sqlite3<\/p>\n<p>conn = sqlite3.connect(&#39;lottery_results.db&#39;)<\/p>\n<p>cursor = conn.cursor()<\/p>\n<p>cursor.execute(&#39;&#39;&#39;CREATE TABLE IF NOT EXISTS results<\/p>\n<p>                  (date TEXT, numbers TEXT)&#39;&#39;&#39;)<\/p>\n<p>for result in lottery_results:<\/p>\n<p>    cursor.execute(&quot;INSERT INTO results (date, numbers) VALUES (?, ?)&quot;,<\/p>\n<p>                   (result[&#39;date&#39;], result[&#39;numbers&#39;]))<\/p>\n<p>conn.commit()<\/p>\n<p>conn.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4ee5\u4e0a\u662f\u7528Python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u7684\u8be6\u7ec6\u6b65\u9aa4\uff0c\u4ece\u9009\u62e9\u6570\u636e\u6e90\u7f51\u7ad9\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u63d0\u53d6\u6570\u636e\u5230\u5b58\u50a8\u6570\u636e\uff0c\u6bcf\u4e00\u6b65\u90fd\u6709\u8be6\u7ec6\u7684\u4ee3\u7801\u793a\u4f8b\u3002\u901a\u8fc7\u8fd9\u4e9b\u6b65\u9aa4\uff0c\u60a8\u53ef\u4ee5\u8f7b\u677e\u5730\u722c\u53d6\u5e76\u5b58\u50a8\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u7684\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0crequests\u5e93\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u8fd9\u4e9b\u52a8\u6001\u5185\u5bb9\u3002\u8fd9\u65f6\u5019\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u83b7\u53d6\u5b8c\u6574\u7684\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5Selenium\u5e93\u548c\u5bf9\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8<\/h4>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0b\u8f7d\u5e76\u5b89\u88c5\u5bf9\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff08\u5982ChromeDriver\u3001GeckoDriver\uff09\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\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from selenium.webdriver.chrome.service import Service<\/p>\n<p>from webdriver_manager.chrome import ChromeDriverManager<\/p>\n<h2><strong>\u8bbe\u7f6e\u6d4f\u89c8\u5668\u9a71\u52a8<\/strong><\/h2>\n<p>service = Service(ChromeDriverManager().install())<\/p>\n<p>driver = webdriver.Chrome(service=service)<\/p>\n<p>url = &#39;https:\/\/example.com\/lottery-results&#39;  # \u66ff\u6362\u4e3a\u5b9e\u9645\u7684URL<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n<p>import time<\/p>\n<p>time.sleep(5)  # \u6839\u636e\u9700\u8981\u8c03\u6574\u7b49\u5f85\u65f6\u95f4<\/p>\n<h2><strong>\u83b7\u53d6\u9875\u9762\u5185\u5bb9<\/strong><\/h2>\n<p>page_content = driver.page_source<\/p>\n<p>driver.quit()<\/p>\n<h2><strong>\u89e3\u6790\u9875\u9762\u5185\u5bb9<\/strong><\/h2>\n<p>soup = BeautifulSoup(page_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u6253\u5f00\u76ee\u6807URL\u5e76\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\u3002\u7136\u540e\uff0c\u901a\u8fc7page_source\u5c5e\u6027\u83b7\u53d6\u5b8c\u6574\u7684\u9875\u9762\u5185\u5bb9\uff0c\u5e76\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e03\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u4f7f\u7528\u53cd\u722c\u866b\u673a\u5236\u6765\u9632\u6b62\u81ea\u52a8\u5316\u811a\u672c\u8bbf\u95ee\u3002\u5e38\u89c1\u7684\u53cd\u722c\u866b\u673a\u5236\u5305\u62ec\u4f7f\u7528CAPTCHA\u3001\u9650\u5236\u8bf7\u6c42\u9891\u7387\u3001\u68c0\u6d4b\u7528\u6237\u4ee3\u7406\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u5e94\u5bf9\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><h4>1\u3001\u4f7f\u7528\u968f\u673a\u7528\u6237\u4ee3\u7406<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u66f4\u6539HTTP\u8bf7\u6c42\u5934\u4e2d\u7684User-Agent\u5b57\u6bb5\uff0c\u53ef\u4ee5\u4f2a\u88c5\u6210\u4e0d\u540c\u7684\u6d4f\u89c8\u5668\u548c\u64cd\u4f5c\u7cfb\u7edf\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import random<\/p>\n<p>user_agents = [<\/p>\n<p>    &#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>    &#39;Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36&#39;,<\/p>\n<p>    &#39;Mozilla\/5.0 (X11; Linux x86_64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36&#39;,<\/p>\n<p>]<\/p>\n<p>headers = {<\/p>\n<p>    &#39;User-Agent&#39;: random.choice(user_agents)<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee3\u7406\u670d\u52a1\u5668\u53ef\u4ee5\u9690\u85cf\u771f\u5b9e\u7684IP\u5730\u5740\uff0c\u5e76\u7ed5\u8fc7IP\u9650\u5236\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/your_proxy_ip:port&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;https:\/\/your_proxy_ip:port&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3\u3001\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\uff0c\u53ef\u4ee5\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u89e6\u53d1\u53cd\u722c\u866b\u673a\u5236\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>urls = [&#39;https:\/\/example.com\/page1&#39;, &#39;https:\/\/example.com\/page2&#39;, &#39;https:\/\/example.com\/page3&#39;]<\/p>\n<p>for url in urls:<\/p>\n<p>    response = requests.get(url, headers=headers)<\/p>\n<p>    # \u5904\u7406\u54cd\u5e94\u5185\u5bb9<\/p>\n<p>    time.sleep(random.uniform(1, 5))  # \u968f\u673a\u7b49\u5f851\u52305\u79d2<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516b\u3001\u5904\u7406\u590d\u6742\u7f51\u9875\u7ed3\u6784<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u7684\u7f51\u9875\u7ed3\u6784\u6bd4\u8f83\u590d\u6742\uff0c\u53ef\u80fd\u5305\u542b\u5d4c\u5957\u7684HTML\u6807\u7b7e\u548c\u5927\u91cf\u7684JavaScript\u4ee3\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5904\u7406\u590d\u6742\u7f51\u9875\u7ed3\u6784\u7684\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><h4>1\u3001\u4f7f\u7528XPath<\/h4>\n<\/p>\n<p><p>XPath\u662f\u4e00\u79cd\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u4fe1\u606f\u7684\u8bed\u8a00\uff0c\u4e5f\u53ef\u4ee5\u7528\u4e8eHTML\u6587\u6863\u3002\u901a\u8fc7XPath\u53ef\u4ee5\u65b9\u4fbf\u5730\u5b9a\u4f4d\u548c\u63d0\u53d6\u590d\u6742\u7ed3\u6784\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from lxml import etree<\/p>\n<p>tree = etree.HTML(page_content)<\/p>\n<h2><strong>\u4f7f\u7528XPath\u5b9a\u4f4d\u548c\u63d0\u53d6\u6570\u636e<\/strong><\/h2>\n<p>draw_date = tree.xpath(&#39;\/\/table[@id=&quot;lottery-results&quot;]\/tr[1]\/td[1]\/text()&#39;)<\/p>\n<p>winning_numbers = tree.xpath(&#39;\/\/table[@id=&quot;lottery-results&quot;]\/tr[1]\/td[2]\/text()&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u7ed3\u5408\u6b63\u5219\u8868\u8fbe\u5f0f<\/h4>\n<\/p>\n<p><p>\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u6587\u672c\u5339\u914d\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u4e8e\u4ece\u590d\u6742\u7684\u7f51\u9875\u7ed3\u6784\u4e2d\u63d0\u53d6\u7279\u5b9a\u6a21\u5f0f\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import re<\/p>\n<p>pattern = re.compile(r&#39;&lt;td&gt;(\\d{4}-\\d{2}-\\d{2})&lt;\/td&gt;&lt;td&gt;(\\d{1,2},\\d{1,2},\\d{1,2},\\d{1,2},\\d{1,2},\\d{1,2})&lt;\/td&gt;&#39;)<\/p>\n<p>matches = pattern.findall(page_content)<\/p>\n<p>for match in matches:<\/p>\n<p>    draw_date, winning_numbers = match<\/p>\n<p>    print(f&#39;Date: {draw_date}, Numbers: {winning_numbers}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u5904\u7406\u590d\u6742\u7f51\u9875\u7ed3\u6784\u4e2d\u7684\u6570\u636e\u63d0\u53d6\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h3>\u4e5d\u3001\u5b9a\u671f\u722c\u53d6\u548c\u81ea\u52a8\u5316<\/h3>\n<\/p>\n<p><p>\u4e3a\u4e86\u5b9a\u671f\u83b7\u53d6\u6700\u65b0\u7684\u5f00\u5956\u4fe1\u606f\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b9a\u65f6\u4efb\u52a1\u6765\u81ea\u52a8\u5316\u722c\u53d6\u8fc7\u7a0b\u3002\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528\u64cd\u4f5c\u7cfb\u7edf\u7684\u5b9a\u65f6\u4efb\u52a1\u5de5\u5177\uff08\u5982cron\u3001Windows Task Scheduler\uff09\u6216\u4f7f\u7528Python\u7684\u5b9a\u65f6\u4efb\u52a1\u5e93\uff08\u5982schedule\u3001APScheduler\uff09\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u4f7f\u7528schedule\u5e93<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">import schedule<\/p>\n<p>import time<\/p>\n<p>def job():<\/p>\n<p>    # \u722c\u53d6\u6570\u636e\u7684\u4ee3\u7801<\/p>\n<p>    pass<\/p>\n<h2><strong>\u6bcf\u5929\u4e0a\u534810\u70b9\u6267\u884c\u4e00\u6b21<\/strong><\/h2>\n<p>schedule.every().day.at(&quot;10:00&quot;).do(job)<\/p>\n<p>while True:<\/p>\n<p>    schedule.run_pending()<\/p>\n<p>    time.sleep(1)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u4f7f\u7528APScheduler\u5e93<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">from apscheduler.schedulers.blocking import BlockingScheduler<\/p>\n<p>def job():<\/p>\n<p>    # \u722c\u53d6\u6570\u636e\u7684\u4ee3\u7801<\/p>\n<p>    pass<\/p>\n<p>scheduler = BlockingScheduler()<\/p>\n<p>scheduler.add_job(job, &#39;interval&#39;, days=1)  # \u6bcf\u5929\u6267\u884c\u4e00\u6b21<\/p>\n<p>scheduler.start()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u5b9a\u65f6\u4efb\u52a1\uff0c\u53ef\u4ee5\u786e\u4fdd\u5b9a\u671f\u83b7\u53d6\u6700\u65b0\u7684\u5f00\u5956\u4fe1\u606f\uff0c\u5e76\u81ea\u52a8\u5316\u6574\u4e2a\u722c\u53d6\u8fc7\u7a0b\u3002<\/p>\n<\/p>\n<p><h3>\u5341\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528Python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u6d89\u53ca\u9009\u62e9\u6570\u636e\u6e90\u7f51\u7ad9\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u63d0\u53d6\u548c\u5904\u7406\u6570\u636e\u3001\u5b58\u50a8\u6570\u636e\u3001\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9\u3001\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236\u3001\u5904\u7406\u590d\u6742\u7f51\u9875\u7ed3\u6784\u548c\u5b9a\u671f\u722c\u53d6\u4e0e\u81ea\u52a8\u5316\u7b49\u591a\u4e2a\u6b65\u9aa4\u3002\u901a\u8fc7\u7ed3\u5408requests\u3001BeautifulSoup\u3001Selenium\u3001XPath\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7b49\u5de5\u5177\u548c\u6280\u672f\uff0c\u53ef\u4ee5\u5b9e\u73b0\u5bf9\u5404\u79cd\u7c7b\u578b\u7684\u7f51\u9875\u5185\u5bb9\u7684\u722c\u53d6\u548c\u6570\u636e\u63d0\u53d6\u3002\u5e0c\u671b\u4ee5\u4e0a\u5185\u5bb9\u5bf9\u60a8\u4e86\u89e3\u548c\u5b9e\u73b0\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u722c\u53d6\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684\u5e93\u6765\u8fdb\u884cPython\u722c\u866b\uff1f<\/strong><br \/>\u5728Python\u4e2d\uff0c\u6709\u591a\u4e2a\u5e93\u53ef\u4ee5\u7528\u4e8e\u7f51\u9875\u722c\u866b\uff0c\u5176\u4e2d\u6700\u5e38\u7528\u7684\u662fRequests\u548cBeautifulSoup\u3002Requests\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u5bf9\u4e8e\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u7684\u722c\u53d6\uff0c\u4f7f\u7528\u8fd9\u4e24\u4e2a\u5e93\u7ed3\u5408\u80fd\u6709\u6548\u83b7\u53d6\u548c\u5904\u7406\u6570\u636e\u3002<\/p>\n<p><strong>\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u52a1\u5fc5\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u3002\u8bb8\u591a\u7f51\u7ad9\u5728\u5176robots.txt\u6587\u4ef6\u4e2d\u58f0\u660e\u4e86\u722c\u866b\u8bbf\u95ee\u7684\u89c4\u5219\uff0c\u5c0a\u91cd\u8fd9\u4e9b\u89c4\u5b9a\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u6b64\u5916\uff0c\u9891\u7e41\u8bf7\u6c42\u67d0\u4e2a\u7f51\u7ad9\u53ef\u80fd\u4f1a\u5bfc\u81f4\u670d\u52a1\u5668\u8d1f\u62c5\u8fc7\u91cd\uff0c\u751a\u81f3\u88ab\u5c01\u7981\u3002\u56e0\u6b64\uff0c\u5408\u7406\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u548c\u9891\u7387\uff0c\u4fdd\u6301\u722c\u866b\u7684\u201c\u793c\u8c8c\u201d\u975e\u5e38\u5173\u952e\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u722c\u53d6\u8fc7\u7a0b\u4e2d\u53ef\u80fd\u51fa\u73b0\u7684\u5f02\u5e38\u60c5\u51b5\uff1f<\/strong><br \/>\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u7f51\u7edc\u8fde\u63a5\u95ee\u9898\u3001\u7f51\u9875\u7ed3\u6784\u53d8\u5316\u6216\u6570\u636e\u683c\u5f0f\u4e0d\u4e00\u81f4\u7b49\u60c5\u51b5\u3002\u4f7f\u7528try-except\u8bed\u53e5\u53ef\u4ee5\u6709\u6548\u6355\u83b7\u548c\u5904\u7406\u5f02\u5e38\uff0c\u786e\u4fdd\u722c\u866b\u7684\u7a33\u5b9a\u6027\u3002\u6b64\u5916\uff0c\u5b9a\u671f\u68c0\u67e5\u548c\u66f4\u65b0\u722c\u866b\u4ee3\u7801\uff0c\u4ee5\u9002\u5e94\u7f51\u7ad9\u7684\u53d8\u5316\uff0c\u80fd\u591f\u63d0\u5347\u722c\u53d6\u7684\u6210\u529f\u7387\u548c\u6548\u7387\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u7528Python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f \u7528Python\u722c\u53d6\u5f69\u7968\u4e2d\u5956\u4fe1\u606f\uff0c\u9996\u5148\u9700\u8981\u9009\u62e9\u5408\u9002\u7684\u7f51\u7ad9\u3001\u4f7f\u7528\u9002\u5f53\u7684\u5e93\u8fdb\u884c\u7f51 [&hellip;]","protected":false},"author":3,"featured_media":1080926,"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\/1080916"}],"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=1080916"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1080916\/revisions"}],"predecessor-version":[{"id":1080931,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1080916\/revisions\/1080931"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1080926"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1080916"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1080916"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1080916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}