Created
August 13, 2020 22:59
-
-
Save bl4ckbo7/26f1866c1a8a2aae12ae1061cec598cd to your computer and use it in GitHub Desktop.
A scraper for https://udemy.pundeermaza.xyz/?/Udemy%20-%20The%20Complete%20Networking%20Fundamentals%20Course/
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
#!/usr/bin/env python3 | |
#Title: Scraper 1.0 (Just wanted to share, you might want to use it when downloading various courses from this repository. Enjoy. ;)) | |
#Author: bl4ckbo7 | |
#Date/Time: Aug 13, 2020 | 23:43 HRS | |
import requests | |
from bs4 import BeautifulSoup | |
import re | |
def parser(url, tag, selector): | |
try: | |
r = requests.get(url) | |
page = r.text | |
except: | |
print("Error opening the url") | |
soup = BeautifulSoup(page, 'html.parser') | |
output = soup.select(tag, selector) | |
outputname = [] | |
for i in output: | |
outputname.append(i.text) | |
outputname.remove('..') | |
outputname.sort() | |
return outputname | |
def main(): | |
#the url of index repository | |
url = "https://udemy.pundeermaza.xyz/?/Udemy%20-%20The%20Complete%20Networking%20Fundamentals%20Course/" | |
""" | |
List the repository's directories | |
""" | |
dirs = [] | |
dirs = parser(url, 'a', {"class":"icon icon-dir"}) | |
for i in dirs: | |
print(i) | |
#saving directory names into the file | |
with open('repos.txt', 'w') as file: | |
for i in dirs: | |
file.write(i) | |
""" | |
Download a directory's file(s) | |
""" | |
savedir = input("\nChoose the name of directory you want to download its files: (Format: XXX. directory name/)") | |
try: | |
dirs.index(savedir) | |
saveurl = url + savedir + "/" | |
except ValueError: | |
print("No such directory in the repository!\n") | |
exit() | |
files = [] | |
files = parser(saveurl, 'a', {"class":"icon-file"}) | |
for thisfile in files: | |
print("Downloading \"{0}\" ...".format(thisfile)) | |
r = requests.get(saveurl + thisfile, allow_redirects=True) | |
open(thisfile, 'wb').write(r.content) | |
print("Finished downloading \"{0}\". \n\n".format(thisfile)) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment