import requests
cookies = {    'PHPSESSID': 'juntbj9ejl8dnroa8qa4r7pbnu',}
headers = {    'Connection': 'keep-alive',    'Pragma': 'no-cache',    'Cache-Control': 'no-cache',    'Upgrade-Insecure-Requests': '1',    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',    'Sec-Fetch-Site': 'same-origin',    'Sec-Fetch-Mode': 'navigate',    'Sec-Fetch-User': '?1',    'Sec-Fetch-Dest': 'document',    'Referer': 'https://www.guo68.com/market?',    'Accept-Language': 'zh-CN,zh;q=0.9',    # 'Cookie': 'PHPSESSID=juntbj9ejl8dnroa8qa4r7pbnu',}
resp = requests.get('https://www.guo68.com/market', cookies=cookies, headers=headers).textprint(resp)

from lxml import etreehtml = etree.HTML(resp) #建立解析对象table = html.xpath('/html/body/div[3]/div/div[1]/div[3]/div[2]/ul/a/li/text()')  #注意这里需要手动微调，删去多余的索引值print(table)

def spider(url):    resp = requests.get(url, cookies=cookies, headers=headers).text    html = etree.HTML(resp)    table = html.xpath('/html/body/div[3]/div/div[1]/div[3]/div[2]/ul/a')    for tr in table : #table仍保留了xpath属性，我们可以借此生成工整的信息格式        txt = tr.xpath('./li/text()') #在此将每个<a>标签中的文字信息提取        csv.writerow(list(txt)) #将一组<a>标签中的信息以列表形式传入
if __name__ == '__main__':    f = open('data.csv', encoding='utf-8', mode='w', newline='')  #newline去除空行    csv = csv.writer(f) #提前打开为对象，避免反复打开文件耗时    start=time.time() #可以提前import time进行测试的计时操作    for i in range(1, 200):        url=f'https://www.guo68.com/market?page={i}'        spider(url)    end=time.time()    print(f"耗时：{end-start}s")

D:\Anaconda\python.exe "D:/pycharm project/test.py"耗时：47.112051486968994sProcess finished with exit code 0

from concurrent.futures import ThreadPoolExecutor #导包
def spider(url):    resp = requests.get(url, cookies=cookies, headers=headers).text    html = etree.HTML(resp)    table = html.xpath('/html/body/div[3]/div/div[1]/div[3]/div[2]/ul/a')    for tr in table :        txt = tr.xpath('./li/text()')        csv.writerow(list(txt))
if __name__ == '__main__':    f = open('data.csv', encoding='utf-8', mode='w', newline='')    csv = csv.writer(f)    start=time.time()    with ThreadPoolExecutor(50) as t: #开辟线程        for i in range(1, 200):            t.submit(spider, f'https://www.guo68.com/market?page={i}') #开始线程    end=time.time()    print(f"耗时：{end-start}s")    t.shutdown(wait= True) #关闭线程

D:\Anaconda\python.exe "D:/pycharm project/test.py"耗时：13.467449502944946sProcess finished with exit code 0

#输出结果有随机数据污染（多刷新几次）from threading import Thread
def task(count: int):    for n in range(count):        print(n)        thread1 = Thread(target=task, args=(10,))thread2 = Thread(target=task, args=(20,))
thread1.start()thread2.start()
thread1.join()thread2.join()
print("Main threads is end")