zoukankan      html  css  js  c++  java
  • 爬虫工具代码

    #工具函数,整体测试不行
    import requests
    import time
    '''
    def get_html(url):
        # 代理服务器
        print("开始下载url : {}".format(url))
        proxyHost = "http-dyn.abuyun.com"
        proxyPort = "9020"

        # 代理隧道验证信息
        proxyUser = "H58G6G30137G865D"
        proxyPass = "043F1F63DA9899C8"

        proxyMeta = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
            "host": proxyHost,
            "port": proxyPort,
            "user": proxyUser,
            "pass": proxyPass,
        }

        proxies = {
            "http": proxyMeta,
            "https": proxyMeta,
        }
        from fake_useragent import UserAgent
        ua = UserAgent()
        print(ua.random)
        headers = {
            "User-Agent": ua.random
        }

        resp = requests.get(url, proxies=proxies, headers=headers)
        resp = resp.content.decode("utf-8")
        return resp
    '''

    #阿布云代理ip,此处后期改成ip池获取
    def get_html_0(url):
        # 代理服务器
        print("开始下载url : {}".format(url))
        proxies = {
            "http:" :"http://117.95.199.208:9999",
            "https" :"https://117.95.199.208:9999"        
        }
        from fake_useragent import UserAgent
        ua = UserAgent()
        print(ua.random)
        headers = {
            "User-Agent": ua.random
        }
        r = requests.get('http://icanhazip.com/',proxies=proxies)
        print(r.text)
        resp = requests.get(url, proxies=proxies, headers=headers)
        return resp


    #menu_text = get_html_0(url).content.decode('utf-8')

    #time.sleep(random.randint(0,2))

    # 用来try测试远程服务器的连接状况
    while True:
            try:
                res_text = requests.get(url).text
            except:
                time.sleep(3)
                print('间隔休眠时间,再次处理')
            else:
                break
  • 相关阅读:
    单播、广播和多播IP地址
    nagios安装部署及详细配置说明(转)
    centos6.5下cacti部署说明
    HAproxy配置详解
    mysql全量和增量备份详解(带脚本)
    lvs原理及安装部署详解(参考)
    curl命令的用法
    mysql日志解析
    MySQL查看和修改表的存储引擎
    mysql备份和还原
  • 原文地址:https://www.cnblogs.com/dog-and-cat/p/13291431.html
Copyright © 2011-2022 走看看