python阿里巴巴排名_python使用urllib模块和pyquery实现阿里巴巴排名查询

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&#