您的位置:首页 > 编程语言 > Python开发

python使用urllib模块和pyquery实现阿里巴巴排名查询

2014-01-16 00:00 1251 查看
urllib基础模块的应用,通过该类获取到url中的html文档信息,内部可以重写代理的获取方法

class ProxyScrapy(object):
    def __init__(self):
        self.proxy_robot = ProxyRobot()
        self.current_proxy = None
        self.cookie = cookielib.CookieJar()

    def __builder_proxy_cookie_opener(self):        
        cookie_handler = urllib2.HTTPCookieProcessor(self.cookie)        
        handlers = [cookie_handler]

        if PROXY_ENABLE:
            self.current_proxy = ip_port = self.proxy_robot.get_random_proxy()
            proxy_handler = urllib2.ProxyHandler({'http': ip_port[7:]})
            handlers.append(proxy_handler)

        opener = urllib2.build_opener(*handlers)
        urllib2.install_opener(opener)
        return opener

    def get_html_body(self,url):
        opener = self.__builder_proxy_cookie_opener()

        request=urllib2.Request(url)
        #request.add_header("Accept-Encoding", "gzip,deflate,sdch")
        #request.add_header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
        #request.add_header("Cache-Control", "no-cache")
        #request.add_header("Connection", "keep-alive")

        try:
            response = opener.open(request,timeout=2)

            http_code = response.getcode()
            if http_code == 200:
                if PROXY_ENABLE:
                    self.proxy_robot.handle_success_proxy(self.current_proxy)
                html = response.read()
                return html
            else:
                if PROXY_ENABLE:
                    self.proxy_robot.handle_double_proxy(self.current_proxy)
                return self.get_html_body(url)
        except Exception as inst:
            print inst,self.current_proxy
            self.proxy_robot.handle_double_proxy(self.current_proxy)
            return self.get_html_body(url)
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: