Created
May 20, 2024 22:08
Download bulk images, PDFs, mp3s, etc. from multiple URLs on a txt file, using Python 3
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import urllib | |
def download_url(file_url): | |
print("downloading: ",file_url) | |
# find "/" then assume that all the rest of the charaters after that represents the filename | |
# if url is www.test.com/abc/xyz/filename.jpg, the file name will be filename.jpg | |
file_name_start_pos = file_url.rfind("/") + 1 | |
file_name = file_url[file_name_start_pos:] | |
r = requests.get(file_url, stream=True) | |
if r.status_code == requests.codes.ok: | |
with open(file_name, 'wb') as f: | |
for data in r: | |
f.write(data) | |
with open('files.txt', 'r') as urls: | |
for url in urls.readlines(): | |
# go through all the URLs on the txt file separated by new line. | |
# remove newline character from the URL | |
url = url.rstrip("\n") | |
download_url(url) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
https://pinoyitsolution.com/wp-content/uploads/2019/06/Tulips.jpg | |
https://pinoyitsolution.com/wp-content/uploads/2019/02/SEO-optimization.jpg | |
https://pinoyitsolution.com/wp-content/uploads/2019/10/sample-pdf.pdf | |
https://pinoyitsolution.com/wp-content/uploads/2019/10/16-11025u.wav |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment