python实现web邮箱扫描的示例(附源码)

from bs4 import BeautifulSoup #BeautifulSoup最主要的功能是从网页抓取数据，Beautiful Soup自动将输入文档转换为Unicode编码
import requests #requests是python实现的最简单易用的HTTP库
import requests.exceptions
import urllib.parse
from collections import deque #deque 是一个双端队列, 如果要经常从两端append 的数据, 选择这个数据结构就比较好了, 如果要实现随机访问,不建议用这个,请用列表. 
import re #是一个正则表达式的库

user_url=str(input('[+] Enter Target URL to Scan:'))
urls =deque([user_url]) #把目标地址放入deque对象列表

scraped_urls= set()#set() 函数创建一个无序不重复元素集，可进行关系测试，删除重复数据，还可以计算交集、差集、并集等。
emails = set()

count=0
try:
  while len(urls):  #如果urls有长度的话进行循环
    count += 1		#添加计数器来记录爬取链接的条数 
    if count ==101:
      break
    url = urls.popleft() #popleft（）会删除urls里左边第一条数据并传给url
    scraped_urls.add(url)

    parts = urllib.parse.urlsplit(url) # 打印 parts会显示：SplitResult(scheme='http', netloc='www.baidu.com', path='', query='', fragment='')
    base_url = '{0.scheme}://{0.netloc}'.format(parts)#scheme：协议；netloc：域名 

    path = url[:url.rfind('/')+1] if '/' in parts.path else url#提取路径
    print('[%d] Processing %s' % (count,url))
   
    try:
      head = {'User-Agent':"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11"}
      response = requests.get(url,headers = head)
    except(requests.exceptions.MissingSchema,requests.exceptions.ConnectionError):
      continue
    new_emails = set(re.findall(r'[a-z0-0\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+', response.text ,re.I))#通过正则表达式从获取的网页中提取邮箱，re.I表示忽略大小写
    emails.update(new_emails)#将获取的邮箱地址存在emalis中。

    soup = BeautifulSoup(response.text, features='lxml')

    for anchor in soup.find_all('a'):  #寻找锚点。在html中，<a>标签代表一个超链接，herf属性就是链接地址
      link = anchor.attrs['href'] if 'href' in anchor.attrs else '' #如果，我们找到一个超链接标签，并且该标签有herf属性，那么herf后面的地址就是我们需要锚点链接。
      if link.startswith('/'):#如果该链接以/开头，那它只是一个路径，我们就需要加上协议和域名，base_url就是刚才分离出来的协议+域名
        link = base_url + link
      elif not link.startswith('http'):#如果不是以/和http开头的话，就要加上路径。
        link =path + link
      if not link in urls and not link in scraped_urls:#如果该链接在之前没还有被收录的话，就把该链接进行收录。
        urls.append(link)
except KeyboardInterrupt:
  print('[+] Closing')

for mail in emails:
  print(mail)

from bs4 import BeautifulSoup
import requests
import requests.exceptions
import urllib.parse
from collections import deque
import re

user_url=str(input('[+] Enter Target URL to Scan:'))
urls =deque([user_url])

scraped_urls= set()
emails = set()


count=0
try:
  while len(urls):
    count += 1
    if count ==100:
      break
    url = urls.popleft()
    scraped_urls.add(url)

    parts = urllib.parse.urlsplit(url)
    base_url = '{0.scheme}://{0.netloc}'.format(parts)

    path = url[:url.rfind('/')+1] if '/' in parts.path else url

    print('[%d] Processing %s' % (count,url))
    try:
      head = {'User-Agent':"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11"}
      response = requests.get(url,headers = head)
    except(requests.exceptions.MissingSchema,requests.exceptions.ConnectionError):
      continue
    new_emails = set(re.findall(r'[a-z0-0\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+', response.text ,re.I))
    emails.update(new_emails)

    soup = BeautifulSoup(response.text, features='lxml')

    for anchor in soup.find_all('a'):
      link = anchor.attrs['href'] if 'href' in anchor.attrs else ''
      if link.startswith('/'):
        link = base_url + link
      elif not link.startswith('http'):
        link =path + link
      if not link in urls and not link in scraped_urls:
        urls.append(link)
except KeyboardInterrupt:
  print('[+] Closing')

for mail in emails:
  print(mail)