Thanks. I follow most of them.
15 karma · joined March 26, 2017
import requests from bs4 import BeautifulSoup
url = "http://www.python.org" response = requests.get(url)
page = str(BeautifulSoup(response.content))
def getURL(page): """
:param page: html of web page (here: Python home page)
:return: urls in that page
"""
start_link = page.find("a href")
if start_link == -1:
return None, 0
start_quote = page.find('"', start_link)
end_quote = page.find('"', start_quote + 1)
url = page[start_quote + 1: end_quote]
return url, end_quote
while True:
url, n = getURL(page)
page = page[n:]
if url:
print(url)
else:
break