Created
August 27, 2019 09:34
-
-
Save drego85/b667315348d3959ef3b7d7904215741c to your computer and use it in GitHub Desktop.
Simple python3 script for downloading all free issues of Linux Journal
This file contains 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
# | |
# | |
# Simple python3 script for downloading all free issues of Linux Journal | |
# The script will download all the available versions: pdf, epub and mobi | |
# | |
# Powered By Andrea Draghetti | |
# | |
# | |
#!/usr/bin/python3 | |
import os | |
import requests | |
from bs4 import BeautifulSoup | |
headerdesktop = {"User-Agent": "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)", | |
"Accept-Language": "en-EN"} | |
timeoutconnection = 120 | |
url = "https://secure2.linuxjournal.com/pdf/dljdownload.php" | |
page = requests.get(url, headers=headerdesktop, timeout=timeoutconnection) | |
soup = BeautifulSoup(page.text, "html.parser") | |
for link in soup.find_all("a"): | |
destinantion_directory = "./ljdownload" | |
if not os.path.exists(destinantion_directory): | |
os.makedirs(destinantion_directory) | |
if link.get("href"): | |
if "download" in link.get("href"): | |
downloadurl = link.get("href") + "&action=spit" | |
filename = downloadurl.split("-")[2] | |
fileextension = downloadurl.split("=")[2].split("-")[0] | |
print("Download: %s.%s" % (filename, fileextension)) | |
r = requests.get(downloadurl, headers=headerdesktop, timeout=timeoutconnection, stream=True) | |
if r.status_code is 200: | |
with open(destinantion_directory + "/" + filename + "." + fileextension, "wb") as f: | |
f.write(r.content) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment