Wikigame - Get to Philosophy from any given article

wikigame.py

import urllib2
import sys

# Used for formating wiki links
wiki_endpoint = "http://en.wikipedia.org/wiki/"
# Count how many links were visited on the way
counter = 0
# Content HTML
c_html = '<div id="mw-content-text" lang="en" dir="ltr" class="mw-content-ltr">'

def remove_parentheses(data):
	''' We want the first link that is not in parentheses, so we make sure it's not '''
	first = data.split('<a href="')
	# If the paragraph dosen't contain parentheses, return the first wiki link
	if not ('(' in first[0] or ')' in first[0]):
		return [x for x in first if x.startswith('/wiki/') and not 'File:' in x][0]
	# Else, find the first link after the parentheses
	total = first[0]
	for i in range(len(first)):
		if total.count('(') == total.count(')'):
			# Make sure it's a wiki link
			return [x for x in first[i:] if x.startswith('/wiki/')][0]
		if i > 0:
			total += first[i]


def get_next(url):
	''' Get the first link from the article '''
	# Get the HTML
	data = urllib2.urlopen(url).read()
	# Split to paragraphs
	data = data.split(c_html)[1]
	if '<table class="infobox biota"' in data:
		data = data.split('</table>')[1]
	while data.startswith('<table'):
		data = '</table>'.join(data.split('</table>')[1:])
	p = data.split('<p>')
	paragraph = ''
	pars = []
	# Find the first paragraph with a link in it
	for index, i in enumerate(p[1:]):
		if "<a href" in i.split('</p>')[0]:
			pars.append(i)
	for i in pars:
		pa = i.split('</p>')[0]
		if (pa[:2] in ['<b', '<i', '<a']) or (pa[0] != '<'):
			paragraph = pa
			break
	# Get the next article's title
	link = remove_parentheses(paragraph).split('"')[0].split('/')[-1]
	return link

def next_url(title):
	''' URL formatting '''
	return wiki_endpoint + urllib2.quote(title).replace('%20', '_')

def nextPage(name):
	global counter
	''' Recursive function to get from a given article to the Philosophy article '''
	if name == "Philosophy":
		return
	counter += 1
	# Get the title of the next article
	url = next_url(name)
	# Format it to a URL
	title = get_next(url)
	# Log to the user
	print "{0} reached.".format(title.replace('_', ' '))
	# Make a recursive call
	nextPage(title)


def main():
	''' Get the first article's title from the user and run the code for it '''
	title = ' '.join(sys.argv[1:])
	try:
		nextPage(title)
		print 'Number of articles visited: %s' % str(counter)
	except KeyboardInterrupt:
		print 'User has stopped.'
	except Exception, e:
		print 'ERROR: {0}'.format(str(e))

if __name__ == '__main__':
	main()

For a less reliable version which only use pure Python, please go here:
https://gist.github.com/OzTamir/4fd0ca8ff8ef8783412b/3b01e3d317a569235e909e7fca96ade50027c34f