python网页信息爬取，爬取QQ号

最新推荐文章于 2023-12-22 11:52:52 发布

小天阔

最新推荐文章于 2023-12-22 11:52:52 发布

阅读量2.2k

点赞数

分类专栏： python

本文链接：https://blog.youkuaiyun.com/qq_41239950/article/details/89716332

版权

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'<