from pyspider.libs.base_handler import * class Handler(BaseHandler): user_url = "http://weibo.cn/" crawl_config = { 'itag': 'v1', 'headers': { 'User-Agent':'Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1', "Host": "weibo.cn", "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "Accept-Language": "zh-CN,zh-TW;q=0.8,zh-HK;q=0.6,en-US;q=0.4,en;q=0.2", "Accept-Encoding": "gzip, deflate", "DNT": "1", "Connection": "keep-alive" }, 'cookies':{ "_T_WM":"791e0d5962c38c757bead1a106a4dcc5", " ALF":"1489404939", " SCF":"AmNkSminRmi2L6WiP0tbn2H_p-TOZQIRRTLwEL5OhwHOohm56wHRk_9Jy1w7iXftduUAJihNuU3B-8cYnWBT3Lk.", " SUB":"_2A251modoDeRxGeNG7VEV9ibIyT6IHXVXZCkgrDV6PUJbktBeLXXZkW2HyTgXsruSYnviSU7hXUjfdGTOig..", " SUBP":"0033WrSXqPxfM725Ws9jqgMF55529P9D9W5wqBjzJ2m1XohsTfpMwPVx5JpX5o2p5NHD95Qf1hq0ShqRShzEWs4Dqcjci--fi-i8iK.7i--fi-2Xi-2Ni--fi-2Xi-2Ni--fi-2Xi-2Ni--fi-2Xi-2Ni--fi-zRiKnf", " SUHB":"0tKqtAdy5rivMy", " SSOLoginState":"1486812984" } } @every(minutes=60*24 * 60) def on_start(self): self.crawl(Handler.user_url, callback=self.index_page,method="GET") @config(age=1 * 24 * 60 * 60) def index_page(self, response): print(response.text)

用requests可以实现登录效果，但是用pyspider是一直访问的是默认的未登录的网页

在crawl_config 和在self.crawl 中设置cookies都不行