Weeke

import scrapy
from urllib.parse import urljoin

class FormEnumeratorSpider(scrapy.Spider):
    name = "form_enum"
    allowed_domains = ["example.com"]      # change to your target domain
    start_urls = ["https://example.com/"]  # entry point

    custom_settings = {
        'ROBOTSTXT_OBEY': False,     # ignore robots.txt
        'DOWNLOAD_DELAY': 0.5,       # be polite-ish
        'CONCURRENT_REQUESTS': 8,
        'USER_AGENT': 'Mozilla/5.0 (X11; Linux x86_64) Scrapy/1.8 (+https://scrapy.org)'
    }

    def parse(self, response):
        # Extract and follow all internal links
        for href in response.css('a::attr(href)').getall():
            url = urljoin(response.url, href)
            if self.allowed_domains[0] in url:
                yield scrapy.Request(url, callback=self.parse_forms)

    def parse_forms(self, response):
        # On each page, find 
 elements
        for form in response.css('form'):
            action = form.attrib.get('action', '')
            full_action = urljoin(response.url, action)
            inputs = []
            for inp in form.css('input'):
                name = inp.attrib.get('name')
                typ  = inp.attrib.get('type', 'text')
                if name:
                    inputs.append({'name': name, 'type': typ})

            yield {
                'page_url': response.url,
                'form_action': full_action,
                'method': form.attrib.get('method', 'GET').upper(),
                'inputs': inputs
            }