Extract all links from a web page using python

Question

Following Introduction to Computer Science track at Udacity, I'm trying to make a python script to extract links from page, below is the code I used:

I got the following error

NameError: name 'page' is not defined

Here is the code:

def get_page(page):
    try:
        import urllib
        return urllib.urlopen(url).read()
    except:
        return ''

start_link = page.find('<a href=')
start_quote = page.find('"', start_link)
end_quote = page.find('"', start_quote + 1)
url = page[start_quote + 1:end_quote]

def get_next_target(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)

(url, end_pos) = get_next_target(page)

page = page[end_pos:]

def print_all_links(page):
    while True:
        (url, end_pos) = get_next_target(page)
        if url:
            print(url)
            page = page[:end_pos]
        else:
            break

print_all_links(get_page("http://xkcd.com/"))

Answer 1

page is undefined and that is the cause of error.

For web scraping like this, you can simply use beautifulSoup:

from bs4 import BeautifulSoup, SoupStrainer
import requests

url = "http://stackoverflow.com/"

page = requests.get(url)    
data = page.text
soup = BeautifulSoup(data)

for link in soup.find_all('a'):
    print(link.get('href'))