python多线程爬虫爬取顶点小说内容（BeautifulSoup+urllib）

from bs4 import *
import socket
import time


#在小说章节页爬取所有章节链接
def get_html():
    
    #从你的浏览器控制台复制出http报文的header信息
    header = {'User-Agent':'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0'}
    url = 'https://www.dingdiann.com/ddk81000/'
    
    #发送一个http请求，读出网页内容存到html
    req = urllib.request.Request(url,headers=header)
    html = urllib.request.urlopen(req).read()

    #网页里有中文，需要decode
    html.decode('utf-8','ignore')
    
    #用BeautifulSoup处理html 不加‘lxml’参数会警告
    soup = BeautifulSoup(html,'lxml')
    
    #chapters用来存放所有章节的链接
    chapters = []
    
    dds = soup.find_all('dd')
    for dd in dds:
        chapters.append('https://www.dingdiann.com'+dd.a.get('href'))
        #print(dd.a.get('href'))
    return chapters

#获取章节文本信息
def get_text(url):
    header = {'User-Agent':'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0'}
    req = urllib.request.Request(url,headers=header)
    
    response = urllib.request.urlopen(req)
    html = response.read().decode('utf-8','igore')
    
    #关闭请求 防止服务器拒绝服务
    response.close()
    
    soup = BeautifulSoup(html,'lxml')
    
    
    #title = soup.find(class_='bookname').h1.text
    try:
        #找到章节名
        title = soup.find(class_='bookname').h1.text
        
        #为中文字符串构造正则表达式，识别出“第X章”
        str = title.encode('utf-8')
        filename = re.search(u'.*章'.encode('utf-8'),str).group().decode('utf-8')
        #用追加方式打开文件，文件名是“第X章”
        f = open('C:/Users/liuxu/Desktop/book/'+filename+ '.txt','w+')
        #写入标题
        f.write(title+'\n\n')
        #逐行写入小说段落
        text = soup.find(id='content').text
        lines = re.findall(r'\s{2}\S*',text)
        for line in lines:
            f.write(line+'\n')
        #关闭文件
        f.close()
    except:
        #异常处理 防止因为出错而中断爬取程序
        print('error in writing')
        
          
#socket.setdefaulttimeout(20) 
threads = [] 
for chapter in get_html():
    th = threading.Thread(target=get_text,args=(chapter,))
    threads.append(th)

for t in threads:
    t.start()
    #每两个进程之间间隔3秒 防止报出错误“[WinError 10054] 远程主机强迫关闭了一个现有的连接”
    time.sleep(3)