Download specific files in a directory recursively

Question

https://repo1.maven.org/maven2/

This folder contains lots of subdirectories and files. I want to download only maven-metadata.xml files using Python. I tried that answer but it doesn't traverse subdirectories recursively.

Answer 1

i would recommend using beautiful soup as well.. you could do something like this, whereas my test, if it's a directory is very, very simple (just, if the link ands with a '/'):

from urllib.request import urlopen
import re
from bs4 import BeautifulSoup
import requests


def isDirectory(url):
    if(url.endswith('/')):
        return True
    else:
        return False

def findLinks(url):
    page = requests.get(url).content
    bsObj = BeautifulSoup(page, 'html.parser')
    maybe_directories = bsObj.findAll('a', href=True)

    for link in maybe_directories:
        print(link['href'])
        print(isDirectory(link['href']))
        if(isDirectory(link['href'])):
            newUrl = url + link['href']         
            findLinks(newUrl) #recursion happening here
        else:
            if(link['href'].endswith('maven-metadata.xml')):
                print("GOTCHA!") #now safe and download

startUrl = "https://repo1.maven.org/maven2/"
findLinks(startUrl)