线程 实践 1

import requests
from  lxml import etree
import threading

# 单/多 线程爬取 当当书名 不保存

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}

urls = ['http://search.dangdang.com/?key=python+%C5%C0%B3%E6&act=input&page_index={}'.format(page) for page in range(1,11)]

i = 1



def get_mess(url):
    '''数据获取 书名'''
    resp = requests.get(url,headers=headers)
    html = etree.HTML(resp.text)
    names = html.xpath('//p[@class="name"]/a/@title')
    global i
    for name in names:
        print(i,name)
        i += 1

# 单线程
# def main():
#     for url in urls:
#         get_mess(url)





# 多线程
def main():
    a_list = []  #  空线程列表
    for url in urls:
        t = threading.Thread(target=get_mess,args=(url,))
        a_list.append(t)

    # 启动线程
    for a in a_list:
        a.start()

    # 等待所有线程结束
    for a in a_list:
        a.join()



if __name__ == '__main__':
    main()