懒人畅听网，有声小说类目数据采集，多线程速采案例，Python 爬虫 120 例之 23 例

http://www.lrts.me/book/category/1/recommend/1/20http://www.lrts.me/book/category/1/recommend/2/20

http://www.lrts.me/book/category/1/recommend/页码/20

import threadingimport time

def run(n, semaphore):    # 加锁    semaphore.acquire()    time.sleep(2)    print(f'正在运行线程{n}')    # 释放锁    semaphore.release()

if __name__ == '__main__':    num = 0    # 最多允许 3 个线程同时运行    semaphore = threading.BoundedSemaphore(3)    for i in range(10):        t = threading.Thread(target=run, args=(f'线程号：{i}', semaphore))        t.start()    while threading.active_count() != 1:        pass    else:        print('所有线程运行完毕')

import threadingfrom threading import Lock,Threadimport random,requestsfrom lxml import etree
def get_headers():    uas = [        "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",    ]    ua = random.choice(uas)    headers = {        "user-agent": ua,        "referer": "https://www.baidu.com/"    }    return headers

def run(url,semaphore):    headers = get_headers()    semaphore.acquire()   #加锁    res = requests.get(url,headers=headers,timeout=5)    if res:        text = res.text        element = etree.HTML(text)        titles = element.xpath('//a[@class="book-item-name"]/text()')        authors = element.xpath('//a[@class="author"]/text()')        weakens = element.xpath('//a[@class="g-user-shutdown"]/text()')        save(url,titles,authors,weakens)

    semaphore.release()    #释放
def save(url,titles,authors,weakens):    data_list = zip(titles,authors,weakens)    for item in data_list:        with open("./data.csv","a+",encoding="utf-8") as f:            f.write(f"{item[0]},{item[1]},{item[2]}\n")    print(url,"该URL地址数据写入完毕")if __name__== '__main__':    lock = Lock()    url_format = 'https://www.lrts.me/book/category/1/recommend/{}/20'    # 拼接URL，全局共享变量    urls = [url_format.format(i) for i in range(1, 1372)]    l = []    semaphore = threading.BoundedSemaphore(5)   # 最多允许5个线程同时运行    for url in urls:        t = threading.Thread(target=run,args=(url,semaphore))        t.start()    while threading.active_count() !=1:        pass    else:        print('所有线程运行完毕')