from pywappalyzer import Pywappalyzer


wappalyzer = Pywappalyzer()

data = wappalyzer.analyze(url="https://www.python.org/")
print(data)

>>> {'Web servers': ['Nginx'], 'Reverse proxies': ['Nginx'], 'Caching': ['Varnish'], 
>>>  'Analytics': ['Google Analytics'], 'JavaScript libraries': ['jQuery UI', 'Modernizr', 'jQuery']

import json

from pywappalyzer import Pywappalyzer


with open("path_to_file.json", "w") as f:
    technologies = json.load(f)

wappalyzer = Pywappalyzer()
wappalyzer.use(technologies=technologies)  # method for replace default `technologies` and `categories` dictionaries

data = wappalyzer.analyze(url="https://www.python.org/")
print(data)

>>> {'Web servers': ['Nginx'], 'Reverse proxies': ['Nginx'], 'Caching': ['Varnish'], 
>>>  'Analytics': ['Google Analytics'], 'JavaScript libraries': ['jQuery UI', 'Modernizr', 'jQuery']}

import requests
from pywappalyzer import Pywappalyzer


wappalyzer = Pywappalyzer()
response = requests.get("https://python.org/")

data = wappalyzer.analyze_html(response.content)
print(data)

>>> {'Analytics': ['Google Analytics'], 'JavaScript libraries': ['Modernizr', 'jQuery UI', 'jQuery']}

import requests
from pywappalyzer import Pywappalyzer


wappalyzer = Pywappalyzer()
response = requests.get("https://python.org/")

data = wappalyzer.analyze_html(file="path_to_file")
print(data)

>>> {'Analytics': ['Google Analytics'], 'JavaScript libraries': ['Modernizr', 'jQuery UI', 'jQuery']}

from typing import Optional, Union

from selenium import webdriver
from selenium.webdriver.chrome.options import Options

from pywappalyzer import Site


class MySite(Site):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
    
    def get_html(
        self, url: Optional[str] = None, *, as_text: bool = False
    ) -> Union[bytes, str]:
        """
        Scrape site's html
        :param url: Site's url
        :param as_text: Return html as string
        :return: Site's HTML as bytes or string
        """
        if url is None:
            url = self.url

        options = Options()
        options.add_argument("--headless")
        with webdriver.Chrome(options=options) as driver:
            driver.get(url)
            page_source = driver.page_source
            self.handle_js(driver)

        if as_text:
            return page_source
        return page_source.encode("utf-8")