homework06

import requests
import re

headers = {
‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36’
}
#网页源代码
url = ‘https://www.baidu.com/s?wd=%E7%95%99%E4%B8%8B%E9%82%AE%E7%AE%B1’
response = requests.get(url,headers=headers)
html = response.text
str_ = html
#利用正则表达式,爬取所有http,爬成一个列表
regex = re.compile(’.?"(http.?//.?)".*?’)
res = regex.findall(str_)
#将能用的网址放到列表ress中
ress = []
for i in res:
if ‘cache.baiducontent’ in i:
ress.append(i)
del ress[0]

#利用子进程爬出邮箱并插入
for http in ress:
response1 = requests.get(http,headers=headers)
html1 = response1.text
regex1 = re.compile("[\w!# %&'*+/=?^_`{|}~-]+(?:\.[\w!# %&’+/=?^_`{|}~-]+)@(?:\w?.)+\w?")
res1 = regex1.findall(html1)
print(res1)

结果

[‘geniexiaoye@163.com’, ‘geniexiaoye@163.com’, ‘geniexiaoye@163.com’, ‘1263688089@qq.comÐ’, ‘1924697163@qq.com’, ‘297985763@qq.com’, ‘1027289784@qq.com’, ‘1027289784@qq.com’, ‘maidejianai@sina.com’, ‘382221145@qq.com’, ‘2936387949@qq.com’, ‘337697322@qq.com’, ‘1142955088@qq.com’, ‘973856368@qq.comºÃÈËƽ’, ‘313386248@qq.com’, ‘13415326766@163.com’, ‘flyhigh253@sina.com’, ‘563182761@qq.com’, ‘409753504@qq.com’, ‘1197386474@qq.com’, ‘15203042093@163.com’]
[‘maming1989@126.com’, ‘1607548724@qq.com’, ‘516110546@qq.com’, ‘919706245@qq.com’, ‘jennifer012@yeah.net’, ‘1120978510@qq.com’, ‘Spencer721@163.com’, ‘chaiyya@163.com’, ‘735281660@qq.com’, ‘511611285@qq.com’, ‘2066192310@qq.com’, ‘2913980130@qq.com’, ‘18846190597@163.com’, ‘1134906240@qq.com’, ‘1937894408@qq.com’, ‘76224365@qq.com’, ‘pjiyan@outlook.com’, ‘17603227720@163.com’, ‘15967242526@163.com’, ‘mac1023@sina.com’, ‘1790443368@qq.com’, ‘putao891011@163.com’, ‘tsuabasayi@qq.com’, ‘1115656777@qq.com’, ‘zuoyexiongzhi@163.com’, ‘912333880@qq.com’, ‘t_sdam@163.com’, ‘771479801@qq.com’, ‘1975805867@qq.com’, ‘1435540787@qq.com’, ‘623025701@qq.com’, ‘401023798@qq.com’, ‘1451235943@qq.com’, ‘1253099965@qq.com’, ‘719886686@qq.com’, ‘1696063991@qq.com’, ‘1599603841@qq.com’, ‘910798479@qq.com’, ‘1084928422@qq.cm’, ‘754432791@qq.com’, ‘743512682@qq.com’, ‘441948935@qq.com’, ‘2778529189@qq.com’, ‘1552445663@qq.com’, ‘future_Michael@Sina.com’, ‘lazarro1002@gmail.com’,
‘228775969@qq.com’, ‘344615525@qq.com’, ‘815989503@qq.com’, ‘2913980130@qq.com’, ‘18825073461@qq.com’, ‘1286553850@qq.com’, ‘zui0134589@163.com’, ‘1921174267@qq.com’, ‘1635036743@qq.com’, ‘415630920@qq.com’, ‘1224469333@qq.com’, ‘2541971289@qq.com’, ‘li813549282@icloud.com’, ‘2261610491@qq.com’, ‘657860729@qq.com’, ‘623554043@qq.com’, ‘985663493@qq.com’, ‘fionaning95@foxmail.com’, ‘1923660403@qq.comÆÚ’, ‘362372580@qq.com’, ‘931390596@qq.com’, ‘327144892@qq.com’, ‘244553797@qq.comÐ’, ‘2547429661@qq.com’, ‘maming1989@126.com’, ‘maming1989@126.com’, ‘aby501@163.com’, ‘1451739284@qq.com’, ‘xunzhaoweizhi9@163.com’, ‘26545527@qq.com’, ‘2548491967@qq.com’]
[‘ºhz@maxthon.net’, ‘ºjubao@maxthon.net’]
[]
[]
[‘89494679@qq.com’, ‘2516151316@qq.com’, ‘2516151316@qq.com’]
[‘address+v2ex@gmail.com’]

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值