Python - Scrapy Login form

[Baggelhsk95]

Hello guyes....i was messing with my script to login in this website but seems doesnt work....i'll like to login first to loggin_url and then request the rest urls to get data

# -*- coding: utf-8 -*-
import scrapy


class StrongbotSpider(scrapy.Spider):
name = 'StrongBot'
login_url = 'https://www.strongflex.eu/en/login?back=my-account'
start_urls = ['https://www.strongflex.eu/en/a3-96-03-8l-fwd/298-221077b-front-wishbone-rear-bush-5902553512151.html?search_query=221077&results=5']

def parse(self, response):
data = {
'email': '[email protected]',
'passwd': 'example',
}
yield scrapy.FormRequest(url=self.login_url, formdata=data, callback=self.after_login)


def after_login(self, response):
for item in response.css('div.pb-right-column.col-xs-12.col-sm-4.col-md-3'):
yield {
'Price' : item.css('#our_price_display::text').extract()
}

[stranac]

Your spider is doing a few things wrong:

1. It starts by opening search url (from start_urls) before login is even attempted
   
2. Submits the form request with some missing data (SubmitLogin is required)
   
3. Tries to parse the resulting page instead of the search page
   

I'd suggest using an InitSpider and doing it like this:

# -*- coding: utf-8 -*-
import scrapy
from scrapy.spiders.init import InitSpider


class StrongbotSpider(InitSpider):
    name = 'StrongBot'
    login_url = 'https://www.strongflex.eu/en/login'
    start_urls = [
        'https://www.strongflex.eu/en/a3-96-03-8l-fwd/'
        '298-221077b-front-wishbone-rear-bush-5902553512151.html'
        '?search_query=221077&results=5'
    ]

    def init_request(self):
        return scrapy.Request(
            url=self.login_url,
            callback=self.login,
        )

    def login(self, response):
        yield scrapy.FormRequest.from_response(
            response=response,
            formid='login_form',
            formdata={
                'email': '[email protected]',
                'passwd': 'gorosucks',
            },
            callback=self.initialized,
        )

    def parse(self, response):
        for item in response.css('div.pb-right-column.col-xs-12.col-sm-4.col-md-3'):
            yield {
                'Price': item.css('#our_price_display::text').extract()
            }

[Baggelhsk95]

im getting the price in zl, we can use request for euro?

[stranac]

Sure, just submit the form for currency selection (the dropdown on the top of the page).
That should set a cookie, and you should get the desired result.

[Baggelhsk95]

i was trying to do the same thing with different website, but seems doesn't work as i wanted to....

# -*- coding: utf-8 -*-
import scrapy


class TabotSpider(scrapy.Spider):
    name = 'TaBot'
    login_url = 'https://www.tatechnix.de/tatechnix/gx/?language=en'
    start_urls = ['https://www.tatechnix.de/tatechnix/gx/product_info.php?info=p44235_ta-technix-sport-suspension-kit-opel-astra-h-caravan-2-0t-1-7-1-9cdti--without-level-control-type-a-h-30-30mm.html',]

    def init_request(self):
        return scrapy.Request(
            url=self.login_url,
            callback=self.login,
        )

    def login(self, response):
        yield scrapy.FormRequest.from_response(
            response=response,
            formid='loginbox',
            formdata={
                'text': 'example',
                'password': 'example',
            },
            callback=self.initialized,
        )

    def parse(self, response):
        for content in response.css('#gm_attr_calc_price'):
            yield {
                'Price' : content.css('span[itemprop="price"]::Text').extract()
            }