问题
Not able to Login only this website in python scrapy project. I want to scrap a login require website and i have already login many websites in my project but not able to Login only this website in python scrapy project.I think i have problem in form response it's """Return the most likely field names for username and password""" but i am not sure and not able to solve this issue
from scrapy.selector import HtmlXPathSelector
from scrapy.contrib.spiders.init import InitSpider
from scrapy.http import Request, FormRequest
from scrapy.contrib.spiders import Rule
from scraping.articles import ArticleItem
from scrapy.spider import BaseSpider
from scrapy import log
class BestPriceGetCatUrl(InitSpider,BaseSpider):
name = "BestPriceGetCatUrl"
allowed_domains = ["bestpricewholesale.co.in"]
login_page = 'https://www.bestpricewholesale.co.in/Registration/login.aspx'
start_urls = ["http://www.bestpricewholesale.co.in/categories/Apparel--Home/cid-CK00002496.aspx"]
def start_requests(self):
return self.init_request()
def init_request(self):
return [Request(url=self.login_page, callback=self.login)]
def login(self, response):
log.msg("hello i am here in login....")
#args, url, method = fill_login_form(response.url, response.body, self.login_user, self.login_pass)
#return FormRequest(url, method=method, formdata=args, callback=self.check_login_response)
return FormRequest.from_response(response, formdata={'ctl00$ContentPlaceHolder1$ctl00$ctl01$Login1$UserName': 'username', 'ctl00$ContentPlaceHolder1$ctl00$ctl01$Login1$Password': 'passward'}, callback=self.check_login_response)
def check_login_response(self, response):
log.msg("in check login response : "+str(response))
if "Logout" in response.body:
for url in self.start_urls:
nUrl = self.make_requests_from_url(url)
yield Request("http://www.bestpricewholesale.co.in/categories/Apparel--Home/cid-CK00002496.aspx",callback=self.parseItems)
else:
self.log("Could not log in...")
def parseItems(self, response):
item = ArticleItem()
item['title'] = "ranvijay"
log.msg("*************** : "+str(response.xpath("//*[@id='lblUserName']/label[@id='lblusrN']/text()").extract()))
item['url'] = response.xpath("//*[@id='lblusrN']/text()").extract()
item['name1'] = response.xpath("//*[@id='ctl00_ContentPlaceHolder1_ctl00_ctl01_lblUserName']/text()").extract()
yield item
from scrapy.item import Item, Field
class ArticleItem(Item):
title = Field()
url = Field()
name1 = Field()
来源：https://stackoverflow.com/questions/27313663/not-able-to-login-this-website-https-www-bestpricewholesale-co-in-registration