unstoppable_app / get_education_votes.py
veeps
adding education votes
adf23bb
raw
history blame
719 Bytes
from bs4 import BeautifulSoup
import pandas as pd
# Open and read the HTML file
with open("now_pac.html", 'r', encoding='utf-8') as file:
html_content = file.read()
# Parse the HTML content
soup = BeautifulSoup(html_content, 'html.parser')
# Find all article elements
divs = soup.find_all('div', class_='image-slide-title')
# Initialize a list to store the data
data = []
for div in divs:
name = div.text.strip().split(",")[0]
office = div.text.strip().split(",")[1]
# Append the extracted data to the list
data.append({'Candidate': name, 'Office': office})
# Add to table
df = pd.DataFrame(data)
df["Endorsed by"] = "NOW PAC"
# write to csv
df.to_csv("now_endorsements.csv", index = False)