bing国际版(bing 搜索)

#-*- coding:utf-8 -*-

import requests

import re

import sys

import os

from bs4 import BeautifulSoup

#定义 header 数据

def headers(referer):

headers = {User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0,

Accept: */*,

Accept-Language: en-US,en;q=0.5,

Accept-Encoding: gzip,deflate,

Referer: referer

}

return headers

#爬取bing搜索引擎数据

def bing_search(url,page,key_word):

referer = "http://cn.bing.com/search?q=email+site%3abaidu.com&qs=n&sp=-1&pq=emailsite%3abaidu.com&first=1&FORM=PERE1"

conn = requests.session() #保持会话

bing_url = "http://cn.bing.com/search?q=" + key_word + "+site%3a" + url + "&qs=n&sp=-1&pq=" + key_word + "site%3a" + url + "&first=" + str((page-1)*10) + "&FORM=PERE1" #设定接口

conn.get(http://cn.bing.com, headers=headers(referer)) #发起请求

r = conn.get(bing_url, stream=True, headers=headers(referer), timeout=8) #获取返回内容

emails = re.findall(r"[a-z0-9\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+",r.text,re.I) #晒选出目标邮箱

return emails

#爬取百度搜索引擎数据

def baidu_search(url,page,key_word):

email_list = []

emails = []

referer = "https://www.baidu.com/s?wd=email+site%3Abaidu.com&pn=1"

baidu_url = "https://www.baidu.com/s?wd="+key_word+"+site%3A"+url+"&pn="+str((page-1)*10)

conn = requests.session() #保持会话

conn.get(referer,headers=headers(referer))

r = conn.get(baidu_url, headers=headers(referer))

soup = BeautifulSoup(r.text, lxml) #解析网页中的元素

tagh3 = soup.find_all(h3) #查找标签

for h3 in tagh3:

href = h3.find(a).get(href)

try:

r = requests.get(href, headers=headers(referer),timeout=8)

emails = re.findall(r"[a-z0-9\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+",r.text,re.I)

except Exception as e:

pass

for email in emails:

email_list.append(email)

return email_list

if __name__ == __main__:

#获取总数据并去重用

email_slit = []

email_slits = []

try:

url = sys.argv[1]

page = sys.argv[2]

key_words = [email, mail, mailbox, 邮件, 邮箱, postbox]

print(开始收集邮箱请耐心等待:)

for key in key_words:

bing = bing_search(url,int(page),key)

baidu = baidu_search(url,int(page),key)

email = bing + baidu

email_slit = email + email_slit

for slit in email_slit: #做个去重处理

if slit not in email_slits:

email_slits.append(slit)

print(email_slits)

file_path = os.path.dirname(__file__) + "/" + url + ".txt" # 在当前目录创建文件，保存结果

fp = open(file_path, w, encoding=utf-8)

for i in email_slits:

fp.write(i + "\n")

print(------------------------------------------------)

print([+]扫描结束，结果保存至当前目录下，文件名：url.txt)

except Exception as ree:

print(使用命令：python3 email.py [url] [页数])