#! /usr/bin/env python3

"""This program was inspired by Jaimes Subroto who had written a
program that worked with the 2018 billboard html format.  Billboard
has changed its html format quite completely in 2023, so this is a
re-implementation that handles the new format.
"""

import urllib.request
from bs4 import BeautifulSoup as soup

def main():
    url = 'https://www.billboard.com/charts/hot-100'
    # url = 'https://web.archive.org/web/20180415100832/https://www.billboard.com/charts/hot-100/'

    # boiler plate stuff to load in an html page from its URL
    url_client = urllib.request.urlopen(url)
    page_html = url_client.read()
    url_client.close()

    # let us save it to a local html file, using utf-8 decoding so
    # that we turn the byte stream into simple ascii text
    open('page_saved.html', 'w').write(page_html.decode('utf-8'))

    # boiler plate use of beautiful soup: use the html parser on the file
    page_soup = soup(page_html, "html.parser")

    # now for the part where you need to know the structure of the
    # html file.  by inspection I found that in 2023 they use <ul>
    # list elements with the attribute "o-chart-restults-list-row", so
    # this is how you find those elements in beautiful soup:
    list_elements = page_soup.select('ul[class*=o-chart-results-list-row]') # *= means contains
    # now that we have our list are ready to read things in, we also prepare 
    outfname = 'billboard_hot_100.csv'
    with open(outfname, 'w') as fp:
        headers = 'Song, Artist, Last Week, Peak Position, Weeks on Chart\n'
        fp.write(headers)
        # Loops through each list element
        for element in list_elements:
            handle_single_row(element, fp)
    print(f'\nBillboard hot 100 table saved to {outfname}')

def handle_single_row(element, fp):
    all_list_items = element.find_all('li')
    title_and_artist = all_list_items[4]
    # try to separate out the title and artist.  title should be an
    # <h3> element, artist is a <span> element
    title = title_and_artist.find('h3').text.strip()
    artist = title_and_artist.find('span').text.strip()
    # now the rest of the columns
    last_week = all_list_items[7].text.strip()
    peak_pos = all_list_items[8].text.strip()
    weeks_on_chart = all_list_items[9].text.strip()
    # we have enough to write an entry in the csv file
    csv_line = f'"{title}", "{artist}", {last_week}, {peak_pos}, {weeks_on_chart}'
    print(csv_line)
    fp.write(csv_line + '\n')


if __name__ == '__main__':
    main()