未经过验证的在scrapy中获取cookies

Access session cookie in scrapy spiders
def parse(self, response):


        return [FormRequest.from_response(response,
                formname='login_form',
                formdata={'email': '...', 'pass':'...'},
                callback=self.after_login)]

def after_login(self, response):


        # process response
        .....


        # access the cookies of that session to access another URL in the
        # same domain with the autehnticated session.
        # Something like:
        session_cookies = XXX.get_session_cookies()
        data = another_function(url,cookies)

def after_login(self, response):


        # testing to see if I can get the session cookies
        cookieJar = response.meta.setdefault('cookie_jar', CookieJar())
        cookieJar.extract_cookies(response, response.request)
        cookies_test = cookieJar._cookies
        print "cookies - test:",cookies_test


        # URL access with authenticated session
        url = "http://site.org/?id=XXXX"     
        request = Request(url=url,callback=self.get_pict)   
        return [request]

cookies - test: {}
2012-01-02 22:44:39-0800 [myspider] DEBUG: Sending cookies to: <GET http://www.facebook.com/profile.php?id=529907453>
    Cookie: xxx=3..........; yyy=34.............; zzz=.................; uuu=44..........

from scrapy.http.cookies import CookieJar


class MySpider(BaseSpider):


    def parse(self, response):


        cookieJar = response.meta.setdefault('cookie_jar', CookieJar())
        cookieJar.extract_cookies(response, response.request)
        request = Request(nextPageLink, callback = self.parse2,
                      meta = {'dont_merge_cookies': True, 'cookie_jar': cookieJar})
        cookieJar.add_cookie_header(request) # apply Set-Cookie ourselves

class CookiesMiddleware(object):
    def _debug_cookie(self, request, spider):
        if self.debug:
            cl = request.headers.getlist('Cookie')
            if cl:
                msg = "Sending cookies to: %s" % request + os.linesep
                msg += os.linesep.join("Cookie: %s" % c for c in cl)
                log.msg(msg, spider=spider, level=log.DEBUG)
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值