kvabapo · March 2, 2020 08:41
diff --git a/scrape_web_links.py b/scrape_web_links.py
 from bs4 import BeautifulSoup
 import urllib3
 import re

 http = urllib3.PoolManager()

 def getLinks(url):
    html_page = http.request('GET', url)
    soup = BeautifulSoup(html_page.data)
    links = []

    for link in soup.findAll('a', attrs={'href': re.compile("^http://")}):
        links.append(link.get('href'))

    return links
	from bs4 import BeautifulSoup
	import urllib3
	import re

	http = urllib3.PoolManager()

	def getLinks(url):
	html_page = http.request('GET', url)
	soup = BeautifulSoup(html_page.data)
	links = []

	for link in soup.findAll('a', attrs={'href': re.compile("^http://")}):
	links.append(link.get('href'))

	return links