rough proof-of-concept for alt-text of https://xkcd.com/903/

xkcd-philosophy.py

#!/usr/bin/python

# dependencies: BeautifulSoup, requests
from BeautifulSoup import BeautifulSoup
import requests

# starting page
url = raw_input("Wikipedia URL: ")
pagename = ''

while not "Philosophy" in pagename:
 page = requests.get(url).content
 soup = BeautifulSoup(page)

 # main content
 mc = soup.findAll(attrs={'id':'mw-content-text'})[0]
 # first top-level paragraph in main content
 pg = mc.findChild(name='p', recursive=False)
 # first top-level hyperlink in paragraph
 hl = pg.findChild(name='a', recursive=False)
 # href of hyperlink
 uri = hl['href']
 # compose URL
 url = "http://en.wikipedia.org" + uri
 
 print uri.split('/')[2] + " -> "