I'm sure we've all heard the joke about "eating the rich" so here's the menu! It scrapes the Wikipedia page of richest Americans, then scrapes their wikipedia pages for their net worth, then saves it all as a csv. Please not this is NOT how I actually name variables, I just thought it was funny :). Something I whipped up for a job application at…

the_menu.py

from bs4 import BeautifulSoup
import csv
import requests

url = "https://en.wikipedia.org/wiki/List_of_Americans_by_net_worth"

req = requests.get(url)

soup = BeautifulSoup(req.content, 'html5lib')

tables = soup.find("div", attrs={"id":"mw-content-text"})

edible = []

for row in tables.findAll("li"):
    try:
        ref = row.a["href"]
        if ref.find("List") == -1 and ref.find("#") == -1:
            edible.append(ref)
    except KeyError:
        pass

bills = edible[0:146]
def clean_name(url):
    return url[len("/wiki/"):].replace("_"," ")

def clean_money(net_worth):
    
    if net_worth == "Not Found":
        print("Net worth not found")
        return 0.0
    else:
        fil = lambda char : char.isdigit() or char == "."
        net_worth = net_worth[0:net_worth.find("b")]
        clean_worth = ''.join(filter(fil, net_worth))
        clean_worth = clean_worth[:4]
        clean_worth = round(float(clean_worth),1)

    return clean_worth


def scrape_net_worth(wiki_url):
    req = requests.get("https://en.wikipedia.org" + wiki_url)

    soup = BeautifulSoup(req.content, 'html5lib')

    # The card is the info brief below individuals pictures, you know.
    card = soup.find("tbody") 

    # Text from each row of the Bio
    texts = []

    for row in card.findAll("tr"):
        texts.append(row.text)

    net_worth = "Not Found"

    for i in range(0,len(texts)):
        if texts[i].find("Net") == 0:
            net_worth = texts[i]

    return net_worth


with open("the_menu.csv", "w") as menu:
    writer = csv.writer(menu)

    writer.writerow(["Name", "Net Worth"])

    for bill in bills:
        name = clean_name(bill)
        value = clean_money(scrape_net_worth(bill))

        writer.writerow([name, value])