Exemple #1
0
def click_mapper(flist):
    for fn in flist:
        for line in open(fn, "r"):
            try:
                fields       = line.split(" ")
                machine, click_ex_msg, click_msg, score, why = fields[:5]
                score        = int(score)
                click_ex_obj = decode_click_ex(click_ex_msg)
                click_obj    = decode_click(click_msg)
            except Exception:
                traceback.print_exc()
                continue
            media_id = click_obj.display_info.media_id
            if media_id == 10140:
                referer = click_ex_obj.user_info.referer
                arg_idx = referer.find("?")
                ref_arg = referer
                if arg_idx != -1:
                    ref_arg = referer[arg_idx+1:]
                click_hash = urlutils.get_query_arg(ref_arg, "uctrac_clk_1")
                if "" == click_hash:
                    click_hash = urlutils.get_query_arg(ref_arg,"uctrac_clk")
                if "" != click_hash:
                    print("%s\tHOP\t%s" % (click_hash, line)),
            else:
                print("%016x\tCLICK\t%s" % (click_ex_obj.click_hash, line)),
Exemple #2
0
def click_mapper(flist):
    for fn in flist:
        for line in open(fn, "r"):
            try:
                fields = line.split(" ")
                machine, click_ex_msg, click_msg, score, why = fields[:5]
                score = int(score)
                click_ex_obj = decode_click_ex(click_ex_msg)
                click_obj = decode_click(click_msg)
            except Exception:
                traceback.print_exc()
                continue
            media_id = click_obj.display_info.media_id
            if media_id == 10140:
                referer = click_ex_obj.user_info.referer
                arg_idx = referer.find("?")
                ref_arg = referer
                if arg_idx != -1:
                    ref_arg = referer[arg_idx + 1:]
                click_hash = urlutils.get_query_arg(ref_arg, "uctrac_clk_1")
                if "" == click_hash:
                    click_hash = urlutils.get_query_arg(ref_arg, "uctrac_clk")
                if "" != click_hash:
                    print("%s\tHOP\t%s" % (click_hash, line)),
            else:
                print("%016x\tCLICK\t%s" % (click_ex_obj.click_hash, line)),
Exemple #3
0
def get_click(line):
    try:
        fields       = line[:-1].split(" ")
        machine, click_ex_msg, click_msg, score, why = fields[:5]
        score        = int(score)
        click_ex_obj = decode_click_ex(click_ex_msg)
        click_obj    = decode_click(click_msg)
    except Exception:
        logger.warn("Parse click line failed %s - %s", line, traceback.format_exc())
        return
    return (click_obj, click_ex_obj, score, why)