crawler: Get external page

[Truman]

this piece of code can be added too:

# Collects a list of all external URLs found on the site
allExtLinks = set()
allIntLinks = set()
def getAllExternalLinks(siteUrl):
	html = requests.get(siteUrl)
	domain = requests.utils.urlparse(siteUrl).scheme+"://"+requests.utils.urlparse(siteUrl).netloc
	bsObj = BeautifulSoup(html.content, 'html.parser')
	internalLinks = getInternalLinks(bsObj, domain)
	externalLinks = getAllExternalLinks(bsObj, domain)
	
for link in externalLinks:
    if link not in allExtLinks:
        allExtLinks.add(link)
        print(link)
for link in internalLinks:
	if link not in allIntLinks:
		allIntLinks.add(links)
		getAllExternalLinks(link)
			
allIntLinks.add("http://oreilly.com")
getAllExternalLinks("http://oreilly.com")

question: why do we need both bsObj and domain if they parse the same webpage?