scrapy.py

mail@pastecode.io avatar
unknown
python
7 months ago
845 B
1
Indexable
Never
import requests
import os

# URL of the website you want to clone
url = "https://www.example.com"

# Directory where you want to save the downloaded files
save_directory = "path/to/save-directory"

# Create the save directory if it doesn't exist
if not os.path.exists(save_directory):
    os.makedirs(save_directory)

# Send a GET request to the website
response = requests.get(url)

# Retrieve the content type of the response
content_type = response.headers['Content-Type']

# Extract the file extension from the content type
file_extension = content_type.split("/")[-1]

# Save the response content to a file
file_path = os.path.join(save_directory, f"index.{file_extension}")
with open(file_path, "wb") as file:
    file.write(response.content)

# Print the file path where the file is saved
print(f"File saved successfully to: {file_path}")