因此,我已经通过Scrapy中的经过身份验证的会话阅读并且我被挂断了,我99%确定我的解析代码是正确的,我只是不相信登录是重定向并且成功.
我也遇到了check_login_response()的问题,不知道它正在检查哪个页面.虽然"注销"会有意义.
======更新======
from scrapy.contrib.spiders.init import InitSpider
from scrapy.http import Request, FormRequest
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders import Rule
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from linkedpy.items import LinkedPyItem
class LinkedPySpider(InitSpider):
name = 'LinkedPy'
allowed_domains = ['linkedin.com']
login_page = 'https://www.linkedin.com/uas/login'
start_urls = ["http://www.linkedin.com/csearch/results?type=companies&keywords=&pplSearchOrigin=GLHD&pageKey=member-home&search=Search#facets=pplSearchOrigin%3DFCTD%26keywords%3D%26search%3DSubmit%26facet_CS%3DC%26facet_I%3D80%26openFacets%3DJO%252CN%252CCS%252CNFR%252CF%252CCCR%252CI"]
def init_request(self):
#"""This function is called before crawling starts."""
return Request(url=self.login_page, callback=self.login)
def login(self, response):
#"""Generate a login request."""
return FormRequest.from_response(response,
formdata={'session_key': 'user@email.com', 'session_password': 'somepassword'},
callback=self.check_login_response)
def check_login_response(self, response):
#"""Check …