import uuid
from os.path import exists
from bs4 import BeautifulSoup
import requests

'''
 - Error handing
 - Look if alternative to main tag is needed. Provide error message if main tag is not found.
 - Menus are li tags with a tags within.
 - li tags with text and tags should be exported
 - Find divs that have text or p tags maybe other tags like divs
 - Export the text
'''

# Make request and get html content.
def get_soup( url ):
    file_path = 'web-pages/' + uuid.uuid5( uuid.NAMESPACE_URL, url ).hex + '.html'
    if exists( file_path ):
        with open( file_path, 'r' ) as web_page:
            html = web_page.read()
    else:
        headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36'}
        response = requests.get( url, headers=headers )
        response.raise_for_status()
        if not response.text:
            raise Exception('HTML empty.')
        html = response.text
        with open( file_path, 'w' ) as file:
            file.write( html )

    return BeautifulSoup(html, 'html.parser')

# Extract content from main tag.
def get_main( soup ):
    return soup.main

def get_deepest_divs( tag ):
    # Get all the divs from within a tag.
    return [div for div in tag.findAll('div') if not div.find('div')]

def get_tag_text( tags ):
    text = ''
    for tag in tags:
        print(tag.find_all('li'))
        # text += [p.get_text() for p in tag.find_all('p)]
    return text

def get_list_text( tags ):
    list_items = []
    for tag in tags:
        list_items = tag.find_all(find_direct_text)
    return list_items

def find_direct_text( tag ):
    return tag.name == 'li' or tag.name == 'p' or tag.name == 'h2' or tag.name == 'h3' or tag.name == 'span' or find_div_text( tag )

def find_div_text( tag ):
    return tag.name == 'div' or tag.find( text=True, recursive=False ) and tag.find( text=True, recursive=False ).strip()

def get_tags_text( soup ):
    text = ''
    tags = soup.find_all( find_direct_text )
    for tag in tags:
        if tag.name == 'div' and tag.find( text=True, recursive=False ) :
            for div in tag.find_all(text=True, recursive=False):
                text += div.get_text().strip() + ' '
        else :
            text += tag.get_text().strip() + ' '
    return text

def extract_content( url ):
    try :
        soup = get_soup( url )
    except Exception as exception:
        raise exception

    if soup is None:
        raise Exception('No content found.')

    main = get_main( soup )
    if main is None :
        raise Exception('No main tag found.')

    return get_tags_text( main )
    # return ''.join([' ' + tag.get_text().strip() for tag in main.find_all( find_direct_text )])

if __name__ == '__main__':
  url = 'https://www.cms.gov/Medicare/Billing/ElectronicBillingEDITrans'
  print(extract_content(url))