![\"\u5982\u4f55\u7528python\u722c\u53d6\u8003\u7814\u771f\u9898\"](\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24184111\/5a552f10-df2d-441a-83fc-14e6bd141d77.webp\")
<\/p>\n<\/p>\n
\u4f7f\u7528Python\u722c\u53d6\u8003\u7814\u771f\u9898\u7684\u6838\u5fc3\u6b65\u9aa4\u5305\u62ec\uff1a\u9009\u62e9\u5408\u9002\u7684\u76ee\u6807\u7f51\u7ad9\u3001\u5206\u6790\u7f51\u9875\u7ed3\u6784\u3001\u6a21\u62dfHTTP\u8bf7\u6c42\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u4fdd\u5b58\u6570\u636e<\/strong>\u3002\u4e0b\u9762\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u6b65\u9aa4\u3002<\/p>\n<\/p>\n \u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u76ee\u6807\u7f51\u7ad9 \u4e8c\u3001\u5206\u6790\u7f51\u9875\u7ed3\u6784 \u4e09\u3001\u6a21\u62dfHTTP\u8bf7\u6c42 url = '\u76ee\u6807\u7f51\u7ad9\u7684URL'<\/p>\n response = requests.get(url)<\/p>\n html_content = response.text<\/p>\n <\/code><\/pre>\n<\/p>\n \u56db\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9 soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n questions = soup.find_all('\u5177\u4f53\u7684\u6807\u7b7e\u6216\u7c7b\u540d')<\/p>\n for question in questions:<\/p>\n print(question.text)<\/p>\n <\/code><\/pre>\n<\/p>\n \u4e94\u3001\u4fdd\u5b58\u6570\u636e for question in questions:<\/p>\n file.write(question.text + '\\n')<\/p>\n <\/code><\/pre>\n<\/p>\n \u9009\u62e9\u5408\u9002\u7684\u76ee\u6807\u7f51\u7ad9\u662f\u722c\u53d6\u8003\u7814\u771f\u9898\u7684\u7b2c\u4e00\u6b65\u3002\u6211\u4eec\u9700\u8981\u786e\u4fdd\u7f51\u7ad9\u7684\u5185\u5bb9\u4e30\u5bcc\u4e14\u7f51\u9875\u7ed3\u6784\u7a33\u5b9a\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u8003\u7814\u771f\u9898\u7f51\u7ad9\uff1a<\/p>\n<\/p>\n \u5728\u9009\u62e9\u76ee\u6807\u7f51\u7ad9\u65f6\uff0c\u5e94\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n \u5728\u786e\u5b9a\u76ee\u6807\u7f51\u7ad9\u540e\uff0c\u9700\u8981\u5206\u6790\u7f51\u9875\u7684\u7ed3\u6784\uff0c\u4ee5\u4fbf\u7f16\u5199\u722c\u866b\u4ee3\u7801\u3002\u4f7f\u7528\u6d4f\u89c8\u5668\u7684\u5f00\u53d1\u8005\u5de5\u5177\uff08F12\uff09\u67e5\u770b\u7f51\u9875\u7684HTML\u4ee3\u7801\uff0c\u627e\u51fa\u5305\u542b\u771f\u9898\u5185\u5bb9\u7684\u5143\u7d20\u53ca\u5176\u8def\u5f84\u3002<\/p>\n<\/p>\n \u4f8b\u5982\uff0c\u5728\u8003\u7814\u5e2e\u7f51\u7ad9\u4e0a\uff0c\u8003\u7814\u771f\u9898\u53ef\u80fd\u4ee5\u5217\u8868\u7684\u5f62\u5f0f\u5c55\u793a\u3002\u6211\u4eec\u53ef\u4ee5\u53f3\u952e\u70b9\u51fb\u771f\u9898\u5185\u5bb9\uff0c\u9009\u62e9\u201c\u68c0\u67e5\u5143\u7d20\u201d\uff0c\u67e5\u770bHTML\u4ee3\u7801\u3002\u5047\u8bbe\u771f\u9898\u5185\u5bb9\u5728\u4e00\u4e2a <p>2019\u5e74\u8003\u7814\u6570\u5b66\u771f\u9898<\/p><\/p>\n <p>...<\/p><\/p>\n <\/div><\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u5206\u6790\u7f51\u9875\u7ed3\u6784\u65f6\uff0c\u8fd8\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n \u5728\u5206\u6790\u5b8c\u7f51\u9875\u7ed3\u6784\u540e\uff0c\u9700\u8981\u4f7f\u7528Python\u7684requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n requests\u5e93\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001GET\u548cPOST\u8bf7\u6c42\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u7684\u793a\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n url = '\u76ee\u6807\u7f51\u7ad9\u7684URL'<\/p>\n response = requests.get(url)<\/p>\n html_content = response.text<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u53d1\u9001HTTP\u8bf7\u6c42\u65f6\uff0c\u8fd8\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n \u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u540e\uff0c\u9700\u8981\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\uff0c\u4ece\u4e2d\u63d0\u53d6\u51fa\u9700\u8981\u7684\u771f\u9898\u4fe1\u606f\u3002<\/p>\n<\/p>\n BeautifulSoup\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u6807\u7b7e\u540d\u3001\u7c7b\u540d\u3001ID\u7b49\u65b9\u5f0f\u5b9a\u4f4d\u5143\u7d20\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u7684\u793a\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\uff1a<\/p>\n<\/p>\n soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n questions = soup.find_all('div', class_='exam-content')<\/p>\n for question in questions:<\/p>\n print(question.text)<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u8fd8\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n \u5c06\u722c\u53d6\u5230\u7684\u771f\u9898\u4fe1\u606f\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u4f7f\u7528\u3002\u53ef\u4ee5\u9009\u62e9\u4fdd\u5b58\u4e3a\u6587\u672c\u6587\u4ef6\u3001CSV\u6587\u4ef6\u6216\u5b58\u5165\u6570\u636e\u5e93\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u4fdd\u5b58\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n for question in questions:<\/p>\n file.write(question.text + '\\n')<\/p>\n <\/code><\/pre>\n<\/p>\n with open('kaoyan_zhenti.csv', 'w', newline='', encoding='utf-8') as csvfile:<\/p>\n writer = csv.writer(csvfile)<\/p>\n for question in questions:<\/p>\n writer.writerow([question.text])<\/p>\n <\/code><\/pre>\n<\/p>\n conn = sqlite3.connect('kaoyan_zhenti.db')<\/p>\n c = conn.cursor()<\/p>\n c.execute('''CREATE TABLE IF NOT EXISTS zhenti (id INTEGER PRIMARY KEY, content TEXT)''')<\/p>\n for question in questions:<\/p>\n c.execute("INSERT INTO zhenti (content) VALUES (?)", (question.text,))<\/p>\n conn.commit()<\/p>\n conn.close()<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u4fdd\u5b58\u6570\u636e\u65f6\uff0c\u8fd8\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n \u4e0b\u9762\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u8003\u7814\u771f\u9898\uff0c\u5e76\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u3002<\/p>\n<\/p>\n from bs4 import BeautifulSoup<\/p>\n def get_html(url):<\/p>\n headers = {<\/p>\n 'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.36'<\/p>\n }<\/p>\n response = requests.get(url, headers=headers)<\/p>\n return response.text<\/p>\n def parse_html(html):<\/p>\n soup = BeautifulSoup(html, 'html.parser')<\/p>\n questions = soup.find_all('div', class_='exam-content')<\/p>\n return [question.text for question in questions]<\/p>\n def save_to_file(data, filename):<\/p>\n with open(filename, 'w', encoding='utf-8') as file:<\/p>\n for item in data:<\/p>\n file.write(item + '\\n')<\/p>\n
\u5728\u5f00\u59cb\u7f16\u5199\u722c\u866b\u4e4b\u524d\uff0c\u9996\u5148\u9700\u8981\u9009\u62e9\u4e00\u4e2a\u5305\u542b\u8003\u7814\u771f\u9898\u7684\u7f51\u7ad9\u3002\u9009\u62e9\u7f51\u7ad9\u65f6\uff0c\u5e94\u786e\u4fdd\u8be5\u7f51\u7ad9\u7684\u5185\u5bb9\u4e30\u5bcc\u4e14\u7ed3\u6784\u7a33\u5b9a\u3002\u53ef\u4ee5\u901a\u8fc7\u7f51\u7edc\u641c\u7d22\u627e\u5230\u4e00\u4e9b\u63d0\u4f9b\u8003\u7814\u771f\u9898\u7684\u7f51\u7ad9\uff0c\u5982\u8003\u7814\u5e2e\u3001\u8003\u7814\u8bba\u575b\u7b49\u3002<\/p>\n<\/p>\n
\u4e86\u89e3\u76ee\u6807\u7f51\u7ad9\u7684\u7f51\u9875\u7ed3\u6784\u662f\u7f16\u5199\u722c\u866b\u7684\u5173\u952e\u3002\u4f7f\u7528\u6d4f\u89c8\u5668\u7684\u5f00\u53d1\u8005\u5de5\u5177\uff08F12\uff09\u67e5\u770b\u7f51\u9875\u7684HTML\u4ee3\u7801\uff0c\u627e\u51fa\u5305\u542b\u771f\u9898\u5185\u5bb9\u7684\u5143\u7d20\u53ca\u5176\u8def\u5f84\u3002\u901a\u5e38\uff0c\u771f\u9898\u4f1a\u4ee5\u8868\u683c\u3001\u5217\u8868\u6216\u6bb5\u843d\u7684\u5f62\u5f0f\u5c55\u793a\u5728\u7f51\u9875\u4e0a\u3002<\/p>\n<\/p>\n
\u4f7f\u7528Python\u7684requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002requests\u5e93\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001GET\u548cPOST\u8bf7\u6c42\u3002<\/p>\n<\/p>\nimport requests<\/p>\n
\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\uff0c\u4ece\u4e2d\u63d0\u53d6\u51fa\u9700\u8981\u7684\u771f\u9898\u4fe1\u606f\u3002BeautifulSoup\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u53ef\u4ee5\u901a\u8fc7\u6807\u7b7e\u540d\u3001\u7c7b\u540d\u3001ID\u7b49\u65b9\u5f0f\u5b9a\u4f4d\u5143\u7d20\u3002<\/p>\n<\/p>\nfrom bs4 import BeautifulSoup<\/p>\n\u6839\u636e\u7f51\u9875\u7ed3\u6784\u627e\u5230\u5305\u542b\u771f\u9898\u7684\u5143\u7d20<\/strong><\/h2>\n
\u5c06\u722c\u53d6\u5230\u7684\u771f\u9898\u4fe1\u606f\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u4f7f\u7528\u3002\u53ef\u4ee5\u9009\u62e9\u4fdd\u5b58\u4e3a\u6587\u672c\u6587\u4ef6\u3001CSV\u6587\u4ef6\u6216\u5b58\u5165\u6570\u636e\u5e93\u3002<\/p>\n<\/p>\nwith open('kaoyan_zhenti.txt', 'w', encoding='utf-8') as file:<\/p>\n\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u76ee\u6807\u7f51\u7ad9<\/h3>\n<\/p>\n
\n
\n
\u4e8c\u3001\u5206\u6790\u7f51\u9875\u7ed3\u6784<\/h3>\n<\/p>\n
<div><\/code>\u6807\u7b7e\u5185\uff0c\u7c7b\u540d\u4e3aexam-content<\/code>\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u5b9a\u4f4d\u8fd9\u4e2a\u5143\u7d20\u3002<\/p>\n<\/p>\n<div class="exam-content"><\/p>\n\n
<div><\/code>\u3001<p><\/code>\u3001<span><\/code>\u7b49\u3002<\/li>\n\u4e09\u3001\u6a21\u62dfHTTP\u8bf7\u6c42<\/h3>\n<\/p>\n
import requests<\/p>\n\n
\u56db\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n\u6839\u636e\u7f51\u9875\u7ed3\u6784\u627e\u5230\u5305\u542b\u771f\u9898\u7684\u5143\u7d20<\/strong><\/h2>\n
\n
\u4e94\u3001\u4fdd\u5b58\u6570\u636e<\/h3>\n<\/p>\n
\n
with open('kaoyan_zhenti.txt', 'w', encoding='utf-8') as file:<\/p>\n\n
import csv<\/p>\n\n
import sqlite3<\/p>\n\n
\u516d\u3001\u793a\u4f8b\u4ee3\u7801<\/h3>\n<\/p>\n
import requests<\/p>\n