[ERRO] HTTP Error 403: Forbidden

Tive o mesmo problema que você.

Não sei se essa é a melhor solução, mas funcionou pra mim.

Primeiro, eu notei que as urls estavam diferentes no site (talvez alguma versão atualizada), mas mesmo assim não funcionou.

Depois, atualizei as urls com as mais atuais de cada ano, e com a ajuda do chatGPT cheguei a esse código e rodou perfeitamente:

import requests
import os

def extract_data(url, local_file):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
    }
    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status()  # Raise HTTPError for bad responses
        # Ensure the local directory exists
        os.makedirs(os.path.dirname(local_file), exist_ok=True)
        # Save the content to the specified local file
        with open(local_file, 'wb') as file:
            file.write(response.content)
        print(f"Data saved to {local_file}")
    except requests.exceptions.HTTPError as e:
        print(f"HTTP Error: {e}")
    except Exception as e:
        print(f"Error: {e}")

# Test with your provided URLs
urls = [
    ("https://data.boston.gov/dataset/8048697b-ad64-4bfc-b090-ee00169f2323/resource/c9509ab4-6f6d-4b97-979a-0cf2a10c922b/download/tmphrybkxuh.csv", "data/dados_2015.csv"),
    ("https://data.boston.gov/dataset/8048697b-ad64-4bfc-b090-ee00169f2323/resource/b7ea6b1b-3ca4-4c5b-9713-6dc1db52379a/download/tmpzxzxeqfb.csv", "data/dados_2016.csv"),
    ("https://data.boston.gov/dataset/8048697b-ad64-4bfc-b090-ee00169f2323/resource/30022137-709d-465e-baae-ca155b51927d/download/tmpzccn8u4q.csv", "data/dados_2017.csv"),
    ("https://data.boston.gov/dataset/8048697b-ad64-4bfc-b090-ee00169f2323/resource/2be28d90-3a90-4af1-a3f6-f28c1e25880a/download/tmp7602cia8.csv", "data/dados_2018.csv"),
    ("https://data.boston.gov/dataset/8048697b-ad64-4bfc-b090-ee00169f2323/resource/ea2e4696-4a2d-429c-9807-d02eb92e0222/download/tmpcje3ep_w.csv", "data/dados_2019.csv"),
    ("https://data.boston.gov/dataset/8048697b-ad64-4bfc-b090-ee00169f2323/resource/6ff6a6fd-3141-4440-a880-6f60a37fe789/download/tmpcv_10m2s.csv", "data/dados_2020.csv"),
]

for url, file in urls:
    extract_data(url, file)