import urllib2
import string
import re
import xmlrpclib
from SimpleXMLRPCServer import SimpleXMLRPCServer


def getPage(url):
    req = urllib2.Request(url)
    responce = urllib2.urlopen(req)
    return responce.read()

def getLinks(content):
    if (re.search('CONTENT="text/html;', content, flags=re.IGNORECASE)): #Check if document is defined as HTML
        p = re.compile('<a *[^>]*>.*</a>')
        raw_links = p.findall(content)

        print raw_links # Debug

        if raw_links == []:
            return "No Links"

        links = []
        s = re.compile('=".*">')

        for n in range(0, len(raw_links)):
            temp = s.search(raw_links[n]).group()
            temp = temp[2:-2]
            print temp
            links.append(temp)

        return links

def filterPages(links, filterstring):
    filteredlinks = []

    for n in range(0, len(links)):
        content = getPage(links[n])

        if re.search(filterstring, content):
            filteredlinks.append(links[n])

    return filteredlinks

def ServerB(url, searchterm):
    content = getPage(url)
    print content # Debug
    linklist = getLinks(content)

    if linklist == "No Links":
        return [["No Links"]]

    if searchterm != None and searchterm != "":
        print "Search string is valid"
        linklist = filterPages(linklist, searchterm)

    else:
        print "Search string is not valid"

    searchterm = ""

    return linklist

server = SimpleXMLRPCServer(("localhost", 8000))
print "Listening on port 8000..."
server.register_function(ServerB, "ServerB")
server.serve_forever()