python 批量爬取邮箱

Posted 2023-03-24 lixinliang

python 批量爬取邮箱地址

#coding: utf-8
import requests
import bs4 #解析网页
import lxml
import re

headers = 
\'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36\'


proxyip = 
     \'http\': \'121.13.252.61:41564\'


#获取该页面所有url 地址，包括分页地址，返回除了本页面以外的所有分页地址
def fetch_url():
    url_list = []
    page_obj = requests.get(\'https://www.douban.com/group/topic/165453665/?start=100&_i=9637470y8YseOC\',headers=headers,proxies=proxyip)
    bs4_obj = bs4.BeautifulSoup(page_obj.text,"lxml") #指定lxml 解析器
    #print(bs4_obj.text)
    #需要分析页面前端代码，div 以及标签选择器
    comment_else = bs4_obj.find_all(name="div",attrs="class":"paginator") #comment_else 是一个大的列表
    for element in comment_else:
      comment_else_url = element.find("a") #查找所有 a 标签
      
      #<a href="https://www.douban.com/group/topic/165453665/?start=0">1</a> ，获取地址 https://www.douban.com/group/topic/165453665/?start=0
      comment_else_url = comment_else_url.attrs.get("href") #未带class 属性,直接提取href,获取真实分页http 地址
      url_list.append(comment_else_url)
      #print(comment_else_url.attrs.get("href"))
    return url_list

def fetch_mail_address(url):
    page_obj = requests.get(url,headers=headers,proxies=proxyip)
    #print(page_obj.text)
    bs4_obj = bs4.BeautifulSoup(page_obj.text,"lxml") #指定lxml 解析器
    comment_else = bs4_obj.find_all(name="div",attrs="class":"reply-doc content") #comment_else 是一个大的列表
    #print(comment_else)
    #print(len(comment_else))
    # <span class="all ref-content">[e-mail]
    # <p class="reply-content">[e-mail]谢谢楼主</p>

    mail_list = []
    for ele in comment_else:
        comment_ele_p = ele.find("p",attrs="class":"reply-content")
        comment_ele_pubtime = ele.find("span", attrs="class": "pubtime")
        #print(comment_ele_p.text,"-------------")
        #re 正则匹配邮箱地址
        comment_ele_address = re.search("\\w+@\\w+.\\w+",comment_ele_p.text,flags=re.A) #flags防止匹配带上汉字
        #print(comment_ele_pubtime)
        if comment_ele_address:
            #print()
            mail_list.append([comment_ele_address.group(),comment_ele_pubtime.text])
    return mail_list


if __name__ == "__main__":
  url_list = fetch_url()
  mail_total_list = []
  for url in url_list:
    mail_list = fetch_mail_address(url)
    mail_total_list.append(mail_list)
  mail_now_page_mail = fetch_mail_address(\'https://www.douban.com/group/topic/165453665/?start=100&_i=9637470y8YseOC\')
  mail_total_list.append(mail_now_page_mail)
  #print(mail_total_list)
  print(\'----------------------------------------------\')

  mail_new_total_list = []
  for ilist in mail_total_list:
    for mail in ilist:
      #print(mail[0])
      mail_new_total_list.append(mail[0])
  
  print(mail_new_total_list)
  print(len(mail_new_total_list))