Scrape - parse and save the city of phoenix's FAQ questions to a CSV

phoenix_gov_faq.py

from bs4 import BeautifulSoup
import requests 
import pandas as pd

# function to remove non-ASCII
def remove_non_ascii(text):
    return ''.join(i for i in text if ord(i)<128)

def extract_question_text(s):
    html_tree = BeautifulSoup(s, "lxml").find("div")
    if html_tree is not None:
        return remove_non_ascii( html_tree.get_text() )
    return "-"

url = "https://www.phoenix.gov/faq"
r = requests.get(url = url) 
html = r.content
soup = BeautifulSoup(html, "lxml")
table = soup.find('table')

df = pd.read_html(str(table))
frame = df[0]
frame = frame[[2,3]]
frame.columns = ["question", "answer"]
temp = frame["answer"].apply(extract_question_text)
frame.loc[:,"answer"] = temp
frame.to_csv("~/Desktop/phoenix_gov_faq.csv")