Question

获得以下代码：

from scrapy.http import Request, FormRequest
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from scrapy.selector import HtmlXPathSelector
from scrapy.http import FormRequest
import subprocess

class LoginSpider(CrawlSpider):
    name = 'loginspider'
    login_page = 'http://145.100.108.148/login5/login.php'
    start_urls = ['http://145.100.108.148/login5/index.php']
    url = 'http://145.100.108.148'
    username = 'test@hotmail.com'
    password = 'test'

    def init_request(self):
        return Request(url=self.login_page, callback=self.start_requests)

    def start_requests(self):
        yield Request(
        url = self.login_page,
        callback = self.login,
        dont_filter = True
        )

    def login(self, response):
        print('\n Response object here')
        print(response)
        if response.css("#captcha").extract_first() is not None:
            captchaImageLink = self.url + response.css("#captcha::attr(src)").extract_first()
            yield Request(captchaImageLink, callback = self.saveCaptchaImage)

    def saveCaptchaImage(self, response):
        output = open("image.png","wb")
        output.write(response.body)
        output.close()
        print('\n Response object here, it')
        print(response)
        captcha = 'abcdef'
        print ("\n Login is here! \n")
        return FormRequest.from_response(response,
        formdata={  'email': self.username,
                    'pass': self.password,
                    'CaptchaCode': captcha},
        callback=self.check_login_response)

    def check_login_response(self, response):
        print ("\n Check_login_response \n")
        if b"Learn" in response.body:
            print("Worked, logged in")
            #return self.parse_item
        else:
            print("Not logged in")
            return

执行此代码后，python将发出错误; 'Response' object has no attribute 'encoding'。原因是，formdata包含尝试填充对象的属性，例如encoding。

但是，自从我尝试下载图片后，该对象已从<200 http://145.100.108.148/login5/login.php>更改为<200 http://145.100.108.148/login5/simple-php-captcha.php?_CAPTCHA&t=0.65214000+1517496701>

如何在不执行其他请求的情况下将对象更改回原始状态？因为我想留在同一个会话中解决验证码。

Answer 1

必须按以下方式保存：

    self.loginpage = response

    return FormRequest.from_response(self.loginpage,
    formdata={  'email': self.username,
                'pass': self.password,
                'CaptchaCode': captcha},
    callback=self.check_login_response)

那是

Scrapy - 更改了对象请求

1 个答案: