main.py

import csv
import json
from bs4 import BeautifulSoup
from selenium import webdriver


BROWSER = webdriver.Chrome(executable_path="chromedriver.exe")
TOTAL_PERSONS = 100


def data_scraper():

    BROWSER.get("https://www.bloomberg.com/billionaires/")
    html_source = BROWSER.page_source
    BROWSER.close()

    soup = BeautifulSoup(html_source, 'html.parser')

    response_rank = soup.find_all('div', class_='table-cell t-rank')
    ranks = [rank.get_text().strip() for rank in response_rank][:TOTAL_PERSONS]

    response_name = soup.find_all('div', class_='table-cell t-name')
    names = [name.get_text().strip() for name in response_name][:TOTAL_PERSONS]

    links = [(name.find('a')['href']).replace("./", "") for name in response_name]

    response_worth = soup.find_all('div', class_='table-cell active t-nw')
    worths = [worth.get_text().strip()
              for worth in response_worth][1:TOTAL_PERSONS+1]

    response_last_change = soup.find_all('div', class_='t-lcd')
    last_changes = [change.get_text().strip()
                    for change in response_last_change][1:TOTAL_PERSONS+1]

    response_ytd = soup.find_all('div', class_='t-ycd')
    ytds = [ytd.get_text().strip() for ytd in response_ytd][1:TOTAL_PERSONS+1]

    response_country = soup.find_all('div', class_='table-cell t-country')
    countries = [country.get_text().strip()
                 for country in response_country][1:TOTAL_PERSONS+1]

    response_industry = soup.find_all('div', class_='table-cell t-industry')
    industries = [industry.get_text().strip()
                  for industry in response_industry][1:TOTAL_PERSONS+1]
    data_dict = {
        "ranks": ranks,
        "names": names,
        "links": links,
        "worths": worths,
        "last_changes": last_changes,
        "ytds": ytds,
        "countries": countries,
        "industries": industries
    }
    return data_dict


def write_to_csv(data: dict) -> None:
    columns = ['Rank', 'Name', 'Link',
               'Total net worth($)', '$ Last change', '$ YTD change', 'Country/Region', 'Industry']
    with open(f"top-{TOTAL_PERSONS}-persons.csv", "w", newline="") as csv_file:
        writer = csv.DictWriter(csv_file, fieldnames=columns)
        writer.writeheader()
        for i in range(TOTAL_PERSONS):
            temp = {
                "Rank": data["ranks"][i],
                "Name": data["names"][i],
                "Link": f"https://www.bloomberg.com/billionaires/{data['links'][i]}",
                "Total net worth($)": data["worths"][i],
                "$ Last change": data["last_changes"][i],
                "$ YTD change": data["ytds"][i],
                "Country/Region": data["countries"][i],
                "Industry": data["industries"][i]
            }
            writer.writerow(temp)


def write_to_json(data: dict) -> None:
    data_list = []
    for i in range(TOTAL_PERSONS):
        temp = {
            "Rank": data["ranks"][i],
            "Name": data["names"][i],
            "Link": f"https://www.bloomberg.com/billionaires/{data['links'][i]}",
            "Total net worth($)": data["worths"][i],
            "$ Last change": data["last_changes"][i],
            "$ YTD change": data["ytds"][i],
            "Country/Region": data["countries"][i],
            "Industry": data["industries"][i]
        }
        data_list.append(temp)
    with open(f"top-{TOTAL_PERSONS}-persons.json", "w") as json_file:
        json.dump(data_list, json_file)


if __name__ == '__main__':
    data = data_scraper()
    write_to_csv(data)
    write_to_json(data)