import scrapy
from loginform import fill_login_form
class MySpiderWithLogin(scrapy.Spider):
name = 'my-spider'
start_urls = [
'http://somewebsite.com/some-login-protected-page',
'http://somewebsite.com/another-protected-page',
]
login_url = 'http://somewebsite.com/login-page'
login_user = 'your-username'
login_password = 'secret-password-here'
def start_requests(self):
# let's start by sending a first request to login page
yield scrapy.Request(self.login_url, self.parse_login)
def parse_login(self, response):
# got the login page, let's fill the login form...
data, url, method = fill_login_form(response.url, response.body,
self.login_user, self.login_password)
# ... and send a request with our login data
return scrapy.FormRequest(url, formdata=dict(data),
method=method, callback=self.start_crawl)
def start_crawl(self, response):
# OK, we're in, let's start crawling the protected pages
for url in self.start_urls:
yield scrapy.Request(url)
def parse(self, response):
# do stuff with the logged in response
我设法让它在没有loginform库的情况下工作,我的解决方案如下。
loginform
只是一个库,与Scrapy完全分离。必须编写代码才能将其插入所需的蜘蛛中,可能是在回调方法中。
下面是执行此操作的结构示例:
相关问题 更多 >
编程相关推荐