python使用urllib模块和pyquery实现阿里巴巴排名查询

程序员文章站 2022-04-06 18:49:37

...

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

复制代码代码如下:

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)