python网页信息爬取，爬取QQ号

import urllib.request
import ssl
import os
import re
from collections import deque


def writeFileByte(htmlBytes,toPath):
    with open(toPath,"wb") as f:
        f.write(htmlBytes)
def writeFileStr(htmlBytes,toPath):
    with open(toPath,"w") as f:
        f.write(str(htmlBytes))

def getHtmlBytes(url):
    headers = {

        "User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50"
    }
    # 请求头
    req = urllib.request.Request(url, headers=headers)
    context=ssl._create_unverified_context()
    # 请求体
    response = urllib.request.urlopen(req,context=context)

    return response.read()

#爬取网页信息+文件存储目录文件
def qqCrawler(url,toPath):
    htmlBytes=getHtmlBytes(url)
    writeFileByte(htmlBytes,r"存文件目录\file1.html")
    writeFileStr(htmlBytes,r"存文件目录\file2.txt")
    htmlStr=str(htmlBytes)



#找qq号
    #pat=r'</li>\n<li class="d_name" data-field=(.*?)}'
    pat=r"[1-9]\d{4,9}"
    re_qq=re.compile(pat)

    qqList=re_qq.findall(htmlStr)
    #去重复
    qqList=list(set(qqList))

    f=open(toPath,"a")
    for qqStr in qqList:
        f.write(qqStr+"\n")
    f.close()


    #找网址
    pat1=r'(((http|ftp|https?)://)(([a-zA-Z0-9\._-]+\.[a-zA-Z]{2,6})|([0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}))(:[0-9]{1,4})*(/[a-zA-Z0-9\&%_\./-~-]*)?)'
    re_url=re.compile(pat1)
    urlsList=re_url.findall(htmlStr)
    #去重
    urlsList=list(set(urlsList))


    return urlsList


def center(url,toPath):
    queue=deque()

    queue.append(url)

    while len(queue)!=0:
        targetUrl=queue.popleft()
        urlList=qqCrawler(targetUrl,toPath)
        for item in urlList:
            tempUrl=item[0]
            queue.append(tempUrl)

#爬取地址
url="http://xxx.xxx.com"

#QQ存储目录文件
toPath=r"文件目录\qqFile.txt"
center(url,toPath)