form_extractor.py

from bs4 import BeautifulSoup
from requests_html import HTMLSession
from pprint import pprint

# initialize an HTTP session
session = HTMLSession()


def get_all_forms(url):
    """Returns all form tags found on a web page's `url` """
    # GET request
    res = session.get(url)
    # for javascript driven website
    # res.html.render()
    soup = BeautifulSoup(res.html.html, "html.parser")
    return soup.find_all("form")


def get_form_details(form):
    """Returns the HTML details of a form,
    including action, method and list of form controls (inputs, etc)"""
    details = {}
    # get the form action (requested URL)
    action = form.attrs.get("action").lower()
    # get the form method (POST, GET, DELETE, etc)
    # if not specified, GET is the default in HTML
    method = form.attrs.get("method", "get").lower()
    # get all form inputs
    inputs = []
    for input_tag in form.find_all("input"):
        # get type of input form control
        input_type = input_tag.attrs.get("type", "text")
        # get name attribute
        input_name = input_tag.attrs.get("name")
        # get the default value of that input tag
        input_value =input_tag.attrs.get("value", "")
        # add everything to that list
        inputs.append({"type": input_type, "name": input_name, "value": input_value})
    # put everything to the resulting dictionary
    details["action"] = action
    details["method"] = method
    details["inputs"] = inputs
    return details


if __name__ == "__main__":
    import sys
    # get URL from the command line
    url = sys.argv[1]
    # get all form tags
    forms = get_all_forms(url)
    # iteratte over forms
    for i, form in enumerate(forms, start=1):
        form_details = get_form_details(form)
        print("="*50, f"form #{i}", "="*50)
        pprint(form_details)