File contents

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
#
""" <kategory> <login> [<output>]
kategory: from www.eksperten
output  : file to placed the result. Defaults to <kategory>.data
"""

import urllib
import sys

def read_kategory(kategory="Sikkerhed", login="", output=""):
    working = ".oOo"
    loginStr = "bruger.phtml?navn=%(login)s" % vars()
    if output:
        out = open(output, "w")
    else:    
        out = open(kategory+".data", "w")


    url = 'http://www.eksperten.dk/spm/%(kategory)s/' % vars()
    i=-1
    while True:
        html = urllib.urlopen( url ).read()
        position = 0
        endpostion = len(html)
        while True:
            try:
                position = html.index('class="listbox"',position)+1
                endposition = html.index('class="listbox"',position)+1
            except:
                break
            hrefpos = position
            # print position
            while True:
                hrefpos = html.find( "href=" , hrefpos, endposition )+1
                if hrefpos == 0:
                    break
                startpos = html.find('"',hrefpos)+1
                endpos = html.find('"', startpos)
                href = "http://www.eksperten.dk%s/" % html[startpos:endpos]
                # print href
                question = urllib.urlopen(href).read()
                i+=1
                print working[i % len(working)],
                sys.stdout.flush()
                if question.find(loginStr) == -1:
                    continue

                qStr = '<meta name="description" content="'
                qstart = question.index(qStr) + len(qStr)
                qend = question.find('/>',qstart)
                # Question
                out.write(question[qstart:qend]+"\n")
                p_start = qend
                while True:
                    nameStr = 'link_black_spm"'
                    stop = len(nameStr)
                    p_start = question.find( nameStr, p_start ) + len(nameStr) + 1
                    p_end = question.find( "<", p_start )
                    if p_start == stop:
                        break
                    # besvaret af
                    out.write("Navn " + question[p_start:p_end] + "\n")
                    s_answerStr = 'spm-respons">'
                    try:
                        s_answer = question.index(s_answerStr, p_start) + len(s_answerStr)
                    except:
                        break
                    p_start = question.find("</td>",s_answer )
                    if p_start == -1:
                        break
                    # svar
                    out.write("Svar " +  question[s_answer:p_start] + "\n")
            endpos = html.find(">&gt;&gt;<")
            startpos = html.find('href="/spm/%(kategory)s' % vars(), 0, endpos)
            startx = html.find('"' ,startpos) + 1
            endx = html.find('"',startx )
            url = 'http://www.eksperten.dk' + html[startx:endx]

Kategorier = [
    "Databaser",
    "Design",
    "Diverse",
    "E-losninger",
    "Eksperten",
    "Generelt-IT",
    "Hardware",
    "Internet",
    "Job-opgaver",
    "Netvaerk",
    "Opgaver",
    "PDA",
    "Programmer",
    "Programmering",
    "Sikkerhed",
    "Styresystemer",
    ]


if __name__ == "__main__":
    if len(sys.argv ) == 1:
        print "Usage:", sys.argv[0], __doc__ , "\nKategorier er:\n\t", "\n\t".join(Kategorier)
        sys.exit(0)

    kategory = sys.argv[1]

    if len(sys.argv) > 2:
        login=sys.argv[2]

    if len(sys.argv) > 3:
        output=sys.argv[3]
    else:
        output=kategory + ".data"
    if kategory not in Kategorier:
        print "Wrong kategory\nUsage:", sys.argv[0], __doc__ , "\nKategorier er:\n\t", "\n\t".join(Kategorier)
        sys.exit(0)
    read_kategory(kategory=kategory, output=output, login=login)