自动化x站资源采集方案搭建：Python脚本编写与实战案例

import requests
from bs4 import BeautifulSoup
import sqlite3
import time
import random

def fetch_tech_news():
    url = ‘https://example-news.com/tech’
    headers = {‘User-Agent’: ‘你的浏览器UA’}
    try:
        resp = requests.get(url, headers=headers, timeout=10)
        resp.raise_for_status() # 检查请求是否成功
        soup = BeautifulSoup(resp.text， ‘html.parser’)
        news_items = soup.select(‘.article-list .item’) # 使用CSS选择器定位
        data_list = []
        for item in news_items:
            title = item.select_one(‘h2 a’).text.strip()
            link = item.select_one(‘h2 a’)[‘href’]
            date = item.select_one(‘.date’).text.strip()
            data_list.append((title， link， date))
        save_to_db(data_list)
        print(f“成功采集{len(data_list)}条数据。”)
    except Exception as e:
        print(f“采集失败: {e}”)
    time.sleep(random.uniform(1， 3)) # 礼貌性延时

def save_to_db(data_list):
    conn = sqlite3.connect(‘news.db’)
    c = conn.cursor()
    c.execute(‘‘‘CREATE TABLE IF NOT EXISTS tech_news
                 (id INTEGER PRIMARY KEY， title TEXT， link TEXT UNIQUE， date TEXT)’’’)
    for data in data_list:
        try:
            c.execute(“INSERT OR IGNORE INTO tech_news (title， link， date) VALUES (?, ?, ?)”， data)
        except sqlite3.Error as e:
            print(f“插入数据失败: {e}”)
    conn.commit()
    conn.close()

from apscheduler.schedulers.blocking import BlockingScheduler
scheduler = BlockingScheduler()
# 每天上午9点和下午5点各执行一次
scheduler.add_job(fetch_tech_news， ‘cron’， hour=‘9,17’)
print(‘自动化采集任务已启动，按 Ctrl+C 退出。’)
try:
    scheduler.start()
except (KeyboardInterrupt， SystemExit):
    pass