from bs4 import BeautifulSoup
import pandas as pd

# Open and read the HTML file
with open("giffords.html", 'r', encoding='utf-8') as file:
    html_content = file.read()


# Parse the HTML content
soup = BeautifulSoup(html_content, 'html.parser')


# Find all div elements
h3 = soup.find_all('h3', class_='gif-card__title')


# Initialize a list to store the data
data = []
for link in h3:
    name = link.find('a').text.strip()
    data.append(name)


len(data)
# Make dataframe
df = pd.DataFrame(data)
df["Endorsed by"] = "Education Votes"


# Clean candidate name
df["Candidate"] = df["Candidate"].str.replace('\xa0(D)', '')
df["Candidate"] = df["Candidate"].str.replace('Rep. ', '')

# write to csv
df.to_csv("edu_endorsements.csv", index = False)