如何确保Python Queue的线程和进程安全性：使用锁的技巧

import threading
import requests
from queue import Queue
from bs4 import BeautifulSoup

# 设置代理IP相关信息（使用爬虫代理加强版 www.16yun.cn）
proxy_host = "代理服务器域名"  # 例如："proxy.einiuyun.com"
proxy_port = "代理服务器端口"  # 例如："12345"
proxy_username = "代理用户名"  # 例如："your_username"
proxy_password = "代理密码"  # 例如："your_password"

proxy_url = f"http://{proxy_username}:{proxy_password}@{proxy_host}:{proxy_port}"
proxies = {
    "http": proxy_url,
    "https": proxy_url,
}

# 设置User-Agent和Cookie
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",
    "Cookie": "your_cookie_data"  # 这里替换为实际的cookie
}

# 初始化队列和锁
queue = Queue()
lock = threading.Lock()

# 多线程数据采集函数
def fetch_data(url):
    with lock:  # 使用锁确保线程安全
        try:
            response = requests.get(url, headers=headers, proxies=proxies)
            if response.status_code == 200:
                # 将数据放入队列
                queue.put(response.text)
                print(f"成功采集数据：{url}")
            else:
                print(f"采集失败：{url}，状态码：{response.status_code}")
        except Exception as e:
            print(f"请求发生错误：{e}")

# 解析个人简历信息并存储为文档
def parse_and_save(html_content, resume_id):
    soup = BeautifulSoup(html_content, 'html.parser')
    
    # 假设的简历字段，实际需要根据51job的页面结构进行调整
    name = soup.find('div', class_='name').text.strip() if soup.find('div', class_='name') else "未提供"
    contact = soup.find('div', class_='contact').text.strip() if soup.find('div', class_='contact') else "未提供"
    experience = soup.find('div', class_='experience').text.strip() if soup.find('div', class_='experience') else "未提供"
    
    # 构建简历信息文本
    resume_content = f"姓名: {name}\n联系方式: {contact}\n工作经验: {experience}\n"
    
    # 将简历信息保存到文档
    with open(f'resume_{resume_id}.txt', 'w', encoding='utf-8') as file:
        file.write(resume_content)
    
    print(f"简历 {resume_id} 已保存.")

# 多线程爬虫实现
def multi_thread_scraping(url_list):
    threads = []
    resume_id = 1
    for url in url_list:
        thread = threading.Thread(target=fetch_data, args=(url,))
        thread.start()
        threads.append(thread)

    for thread in threads:
        thread.join()

    # 读取Queue内容并处理数据
    while not queue.empty():
        html_content = queue.get()
        parse_and_save(html_content, resume_id)
        resume_id += 1

# 示例URL列表（假设这些URL指向简历页面）
urls = [
    "https://www.51job.com/resume_example1",
    "https://www.51job.com/resume_example2",
    "https://www.51job.com/resume_example3",
    # 添加更多简历URL
]

# 启动多线程爬虫
multi_thread_scraping(urls)