extracting and soupifying

extractor.py

import requests
from sys import argv
from bs4 import BeautifulSoup

script, landing = argv  # landing is the first URI for this script

def extractor(landing):  # extractor uses requests to GET pages
    r = requests.get(landing)  # and assigns them variables for use
    response = r.status_code
    c = r.text
    soup = BeautifulSoup(c)

    print response  # Making sure the server's responding (200 is good)

def linksearch(soup):  # Looking for links in the soup from extractor
    for link in soup.find_all('a'):
        print(link.get('href'))  # Shows the links

# The idea is to output the items found on a landing page into
# BeautifulSoup, and output them flexibly (i.e. into a file for
#                                          each sometimes 
#                                          prettified)
# Need a way to take each link, and run it through extractor.
# A link should only be extractorified if it is from the landing
# domain (so if 'href' is "http" and contains the domain from argv)?
# This would crawl through the site, ignoring links to other domains
# for extraction.


# r = requests.get(landing)
# response = r.status_code
# c = r.text
# soup = BeautifulSoup(c)

# pretty = soup.prettify()