模拟浏览器进行反爬虫之银行信息的获取

最新推荐文章于 2020-09-05 18:36:53 发布

qq_43279936

最新推荐文章于 2020-09-05 18:36:53 发布

阅读量347

点赞数

本文链接：https://blog.csdn.net/qq_43279936/article/details/88133826

版权

import random
import re

from urllib.request import urlopen, Request
from urllib.error import  URLError
def get_content(url):
    """获取页面内容， 反爬虫之模拟浏览器"""
    # 防止一个浏览器访问频繁被封掉;
    user_agents = [
        "Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Firefox/45.0",
        "Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Safari/535.19",
        "Mozilla/5.0 (Windows NT 6.2; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0",
    ]
    try:
        # reqObj = Request(url, headers={'User-Agent': user_agent})
        reqObj = Request(url)
        # 动态添加爬虫请求的头部信息， 可以在实例化时指定， 也可以后续通过add—header方法添加
        reqObj.add_header('User-Agent', random.choice(user_agents))
    except URLError as e:
        print(e)
        return  None
    else:
        content = urlopen(reqObj).read().decode('utf-8').replace('\t', ' ')
        return  content


def parser_content(content):
    """解析页面内容， 获取银行名称和官网URL地址"""
    pattern = r'<a href="(.*)" target="_blank"  style="color:#08619D">\s+(.*)\s+</a>'
    bankinfos = re.findall(pattern, content)
    if not bankinfos:
        raise  Exception("没有获取符合条件的信息")
    else:
        return  bankinfos

def main():
    url = "http://www.cbrc.gov.cn/chinese/jrjg/index.html"
    content = get_content(url)
    bankinfos = parser_content(content)
    with open('doc/bankinfo.txt', 'w') as f:
        # ('http://www.cdb.com.cn/', '国家开发银行\r')
        for bank in bankinfos:
            name = bank[1].rstrip()
            url = bank[0]
            # 根据正则判断银行的url地址是否合法， 如果合法才写入文件;
            pattern =  r'^((https|http|ftp|rtsp|mms)?:\/\/)\S+'
            if re.search(pattern, url):
                f.write('%s: %s\n' %(name, url))
            else:
                print("%s无官方网站" %(name))
        print("写入完成....")


if __name__ == '__main__':
    main()