网页提取所有邮箱

import re
from urllib import request

# 挖掘邮箱
def getEmailsByLine(url):
    """按行提取邮箱"""
    emailregex = re.compile(r"([a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+)", re.IGNORECASE)#忽略异常情况和大小写
    for line in request.urlopen(url):
        emaillist = emailregex.findall(line.decode("utf-8"))
        if emaillist:#不为空
            print(emaillist)

def getEmailsByAll(url):
    """一次读取,一次提取所有邮箱"""
    emailregex = re.compile(r"([a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+)", re.IGNORECASE)#忽略异常情况和大小写
    html = request.urlopen(url).read().decode("utf-8")
    emaillist = emailregex.findall(html)
    if emaillist:
        print(emaillist)
    
    
if __name__ == "__main__":
    url = "http://bbs.tianya.cn/post-140-393973-1.shtml"
    # getEmailsByLine(url)
    getEmailsByAll(url)

posted on 2019-12-15 21:38  行之间  阅读(724)  评论(0编辑  收藏  举报