python多线程爬取电影天堂多页磁力链接（续）

利用多线程改进后代码

import time
from urllib import request
import re
import threading
from datetime import datetime


#按F12查看
'''
headers={
    'User-Agent':
    'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0'}

   User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134
   
'''
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE'
}



#获取网页源代码函数
def gethtml(url):
    url_request = request.Request(url, headers=headers)  # 加上头部
    response = request.urlopen(url_request)
    data = response.read().decode('gb2312','ignore')#解决中文乱码问题
    #print(data)  # 输出源代码
    return data

#查询函数,返回一个列表
def search(msg,html):
    list=re.findall(msg,html)#正则表达式查询所有符合条件的msg，保存在列表
    return list

#查询网页标题
def search_name(html):
    begin=html.find('title')
    end = html.find(')
    name = html[begin + 6:end]
    return name

#获取磁力链接
def get_ftp(html):
    begin = html.find('magnet')
    end = html.find('fannounce')
    ftp = html[begin:end+len('fannounce')]
    return ftp#">

#获取网页url函数
def get_url(num):
    #num=int(num)
    if num==1:
        return 'https://www.dytt8.net/html/gndy/dyzz/index.html'#最新电影分类的主页链接
    return 'https://www.dytt8.net/html/gndy/dyzz/list_23_'+str(num)+'.html'

# 线程操作函数
def thread_func(i):
    url=get_url(i)
    print(url)
    html = gethtml(url)
    #print(html)
    purl = '= search(purl, html)  # 查找符合条件的网页url
    for each in plist:
        pos = each.find('/html')
        each = 'https://www.dytt8.net' + each[pos:]
        html = gethtml(each)
        name = search_name(html)
        print('第' + str(i) + '页')
        print(name)
        # print(each)
        ftp = get_ftp(html)
        print(ftp)
        filename = '第' + str(i) + '页' + '.txt'
        f = open(filename, 'a', encoding='utf-8')
        f.write('第'+str(i) +'页'+'\n'+name + '\n' + ftp + '\n\n')


def many_thread(num):
    threads = []
    for i in range(num):  # 循环创建 num个线程
        t = threading.Thread(target=thread_func,args=(i+1,))#传参数，第一个是0，所以+1
        threads.append(t)#添加到列表

    for t in threads: # 循环启动 num个线程
        t.start()
    for t in threads:  #等待线程结束
        t.join()

#主函数
if __name__ == '__main__':
    num=input("输入页数<1~200>：")
    num=int(num)
    while num < 1 or num >200:
        num = input("输入正确页数<1~200>：")
        num = int(num)

    start = datetime.today().now()
    many_thread(num)
    duration = datetime.today().now()

    print('----------\nfinally')
    print('开始='+str(start))
    print('结束='+str(duration))
    print('耗时：'+str(duration-start))