Programming

tut_links=list(set(tut_links))

tut_links = {}

for subdir, dirs, files in os.walk('./html/tutorials/blah'):
    for tut in files:
        if tut.endswith(".html"):
	    tut_links[tut] = []
            fpath = os.path.join("./html/tutorials/blah", tut)
            content = open(fpath, "r").read()
            file = BeautifulSoup(content, 'lxml')
            for links in file.find_all('a', href=True):
		urls = links.get('href')
	    	if urls.startswith('http' or 'https'):		
	           tut_links[tut].append(urls)
	    for dup in tut_links.values(): --> removes duplicate urls from the dictionary value list
    		dup[:] = list(set(dup))

'bigbadwolf.htlm' : ['https://www.blah.com', 'http://www.blahblah.com','http://www.blahblahblah.com']