#!/usr/bin/env python
# By: Raymond Myers    License: GPL 3

# Import everything we need from the core libraries:
import random, sys, urllib, HTMLParser, re

##################################################
# CONFIGURATION CONSTANTS:

# This url represents a search for all items between 0 and 5 USD that have both
# free shipping, and a "buy it now" option, and that have more than an hour left
# to go... (So that we don't get in many races..."
START_URL = "http://shop.ebay.com/i.html?_nkw=a+b+c+d+e+f+g+h+i+j+k+l+m+n+o+p"+\
            "+q+r+s+t+u+v+w+x+y+z&_in_kw=2&_ex_kw=&_sacat=See-All-Categories&"+\
            "_okw=a+b+c+d+e+f+g+h+i+j+k+l+m+n+o+p+q+r+s+t+u+v+w+x+y+z&_oexkw="+\
            "&_mPrRngCbx=1&_udlo=0&_udhi=5&LH_BIN=1&LH_IncludeSIF=1&_LH_Time="+\
            "1&_ftrt=902&_ftrv=1&_sabdlo=&_sabdhi=&_samilow=&_samihi=&LH_FS=1"+\
            "&_sadis=200&_fpos=Zip+code&_fsct=&LH_SALE_CURRENCY=0&_fss=1&_sas"+\
            "lop=1&_sasl=&fsradio=%26LH_TopRatedSellers%3D1&_sop=1&_dmd=1&_ip"+\
            "g=200"

# These are all of the possible user agents... just to obfuscate the fact that
# this is, indeed, a script. Long ones are broken up, cause they're long:
AGENTS = \
["Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.6) " + \
     "Gecko/20070725 Firefox/2.0.0.6",\
 "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",\
 "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; " + \
     ".NET CLR 2.0.50727; .NET CLR 3.0.04506.30)",\
 "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.1.4322)",\
 "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT 5.1; .NET CLR 1.1.4322)"]

##################################################
# CLASS DEFINITIONS:

# Override the urllib user-agent with a random one:
class WebNabber(urllib.FancyURLopener):
	version = random.choice(AGENTS)
urllib._urlopener = WebNabber()

# Override the HTML parser:
class EbayParser(HTMLParser.HTMLParser):
	def __init__(self):
		self.output = []
		self.in_entry, self.in_name, self.in_price = False, False, False
		self.eurl, self.ename, self.eprice = "","",""
		
		HTMLParser.HTMLParser.__init__(self)
	
	def handle_starttag(self, tag, attrs):
		if self.in_entry:
			# Is this the link with the name?
			if tag == "a" and ('class', 'v4lnk') in attrs:
				# Yes, so note that data should be the name:
				self.in_name = True
				
				# Now, we get the link url:
				for i in attrs:
					if i[0] == "href":
						self.eurl = i[1]
			
			# Is this the price div?
			elif tag == "div" and ('class', 'g-b') in attrs:
				self.in_price = True
		
		else:
			# Is this a table entry for an item in the search results:
			if tag == "table" and ('class', 'lview nol') in attrs:
				self.in_entry = True
				self.eurl, self.ename, self.eprice = "","",""
				
	def handle_endtag(self, tag):
		if self.in_entry:
			# Is this the end of the name link?
			if tag == "a" and self.in_name:
				self.in_name = False
			
			# Is this the end of the price div?
			elif tag == "div" and self.in_price:
				self.in_price = False
			
			# Are we done with our table?
			elif tag == "table":
				# Yes, so append the current parse results to the output list:
				self.output += [ (self.eurl, self.ename, self.eprice) ]
				self.in_entry = False
				
	def handle_data(self, data):
		if   self.in_name:  self.ename += data
		elif self.in_price: self.eprice += data


##################################################
# FUNCTION DEFINITIONS:

# This will return the HTML code that makes up a page:
def get_html(url):
	try:
		conn = urllib.urlopen(url)
		html = conn.read()
		conn.close()
	except:
		raise Exception("Failed to get page.")
	else:
		return html

# This will take the HTML data from ebay, and return a nice list:
def parse_ebay(html):
	
	# Filter out irregular stuff, like Javascript and CSS:
	script_regex = re.compile("<script.*?</script>", re.IGNORECASE | re.DOTALL)
	style_regex  = re.compile("<style.*?</style>",  re.IGNORECASE | re.DOTALL)
	html         = script_regex.sub("", html)
	html         = style_regex.sub("", html)
	
	# Parse the HTML document
	p = EbayParser()
	p.feed(html)
	p.close()
	
	# Return the cool stuff:
	return p.output
	
if __name__=="__main__":
	
	# Grab the page:
	html = get_html(START_URL)
	
	# Parse the search results:
	ebay = parse_ebay(html)
	
	# Make a random selection, and print it out:
	buyme = random.choice(ebay)
	for i in buyme:
		print i