main_code

import os
import re
import argparse
from collections import deque
import requests
import bs4
from bs4 import BeautifulSoup
from colorama import init, Fore


print(bs4.__version__)

tags_for_show =   [ 'p', 'h1',   'h2', 'h3', 'h4', 'h5', 'h6', 'a', 'ul', 'ol', 'li']
viewd_tabs = deque()

def print_url_soup(text):
    global tags_for_show
    soup = BeautifulSoup(text, 'html.parser')
    # paragraphs = soup.find_all(tags_for_show )
    # url_with_no_tags =  []
    # for p in paragraphs:
    #     url_with_no_tags.append(p.text + '\n')
    #
    # print( "".join(url_with_no_tags))
    # return "".join(url_with_no_tags)

    text_list = []
    for tag in soup.find_all(tags_for_show):
        text = tag.get_text()
        if tag.name == 'a':
            text = Fore.BLUE + text
        text_list.append(text)

    print('\n'.join(text_list))
    return '\n'.join(text_list)

def read_urls_to_text(user_input):
    header_dict = {
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    try:
        r = requests.get(user_input, headers=header_dict)
    except(requests.exceptions.ConnectionError):
        print("Incorrect URL")
        return ("ERROR")

    if r.ok:
        return(r)
    else:
        return("ERROR")

def save_page_to_file(filepath, text_from_site):
    with open(filepath, "w" ,encoding="utf-8") as f:
        f.write(text_from_site)
    return

def read_page_from_file_and_print(filepath, text_from_site):
    with open(filepath, "r",encoding="utf-8") as f:
            lines = f.readlines()
            for line in lines:
                print(line.strip())

# THIS IS THE MOCK SITE - here is the data is storef and we need name for each file

 #python browser.py dir-for-files
# write your code here

parser = argparse.ArgumentParser()
parser.add_argument("dir_for_files")
args = parser.parse_args()

#EW CREATE DIR FOR THE FILEAS
if not os.access(args.dir_for_files, os.F_OK):
    os.mkdir(args.dir_for_files)
else:
    print ("FileExistsError:")

#                           NAMES
urls = {"default": ""}
# WE STORE THE FILES IN OUR COMPUTER


def input_into_filename(name):
    try:
        filename = name.split(".")
    except:
        print("Error: Incorrect URL")

    name = ".".join(filename )
    return name

def input_into_url(name):
    if re.match("https://", name):
        site_url = name
    else:
        site_url = "https://" + name

    return site_url

##########  main
while True:
    user_info = input()

    if user_info == "exit":
        exit()

    if user_info == "back":
        raise("2")

        if len(viewd_tabs) == 1:     #default
            pass
        else:
            old_tab = viewd_tabs.pop()
            old_tab = viewd_tabs.pop()

            #filepath is url + path  - fikes for writing the site in the files
            filepath = os.path.join(args.dir_for_files, file_name)

    page_name = user_info.split(".")[0]
    site_url = input_into_url(user_info)
    file_name = input_into_filename(user_info)

    url_object = read_urls_to_text(site_url)
    if url_object == "ERROR":
        continue
    urls[page_name] = url_object.text

    if page_name in viewd_tabs:            #means we are recorded the tabs
        raise("o")
        read_page_from_file_and_print(filepath, text_from_site)

    else:
        text_from_site = urls[page_name]
        viewd_tabs.append(file_name)
        filepath = os.path.join(args.dir_for_files, file_name)
        text_from_site = print_url_soup(text_from_site)
        save_page_to_file(filepath, text_from_site)