#!/usr/bin/env python3

from lxml.html import tostring, html5parser

namespaces = {'html': 'http://www.w3.org/1999/xhtml'}

def parsetable(url, path='//html:table'):
    html = html5parser.parse(url)
    table = html.find(path, namespaces=namespaces)

    headers = [header.text for header in table.findall('html:thead/html:tr/html:th', namespaces=namespaces)]
    rows = table.findall('html:tbody/html:tr', namespaces=namespaces)

    return [dict(zip(headers, [tostring(col, encoding=str, method='text') for col in row])) for row in iter(rows)]


def tagfilter(tags, gender, role, blacklist = []):
    tags = iter(tags)
    tag, thresh = next(tags)

    table = parsetable('http://rp.aryion.com/characters.php?term={}'.format(tag))

    for row in table:
        if row['Character'] in blacklist:
            continue
        if gender != row['Gender'] or int(row[role]) < thresh:
            blacklist.append(row['Character'])

    try:
        return tagfilter(tags, gender, role, blacklist)
    except StopIteration:
        return [row['Character'] for row in table if row['Character'] not in blacklist]

from sys import argv

args = argv

argv.pop(0)

gender = { 'female': 'F',
            'f': 'F',
            'fem': 'F',
            'male': 'M',
            'm': 'M',
            'herm': 'H',
            'h': 'H',
            'undefined': 'U',
            'u': 'U' }[argv.pop(0)]

role = {    'prey': 'For prey',
            'pred': 'For pred' }[argv.pop(0)]

tags = []

while len(argv) > 1:
    tag = argv.pop(0)
    thresh = int(argv.pop(0))
    tags.append((tag, thresh))


print(tags)

for i in tagfilter(tags, gender, role):
    print('https://profile.aryion.com/profile/{}'.format(i))