i am new to scrapy and decided to try it out because of good online reviews. I am trying to login to a website with scrapy. I have successfully logged in with a combination of selenium and mechanize by collecting the needed cookies with selenium and adding them to mechanize. Now I am trying to do something similar with scrapy and selenium but cant seem to get anything to work. I cant really even tell if anything is working or not. Can anyone please help me. Below is what Ive started on. I may not even need to transfer the cookies with scrapy but i cant tell if the thing ever actually logs in or not. Thanks
from scrapy.spider import BaseSpider
from scrapy.http import Response,FormRequest,Request
from scrapy.selector import HtmlXPathSelector
from selenium import webdriver
class MySpider(BaseSpider):
name = 'MySpider'
start_urls = ['http://my_domain.com/']
def get_cookies(self):
driver = webdriver.Firefox()
driver.implicitly_wait(30)
base_url = "http://www.my_domain.com/"
driver.get(base_url)
driver.find_element_by_name("USER").clear()
driver.find_element_by_name("USER").send_keys("my_username")
driver.find_element_by_name("PASSWORD").clear()
driver.find_element_by_name("PASSWORD").send_keys("my_password")
driver.find_element_by_name("submit").click()
cookies = driver.get_cookies()
driver.close()
return cookies
def parse(self, response,my_cookies=get_cookies):
return Request(url="http://my_domain.com/",
cookies=my_cookies,
callback=self.login)
def login(self,response):
return [FormRequest.from_response(response,
formname='login_form',
formdata={'USER': 'my_username', 'PASSWORD': 'my_password'},
callback=self.after_login)]
def after_login(self, response):
hxs = HtmlXPathSelector(response)
print hxs.select('/html/head/title').extract()