#!/usr/bin/env python3
import requests
import re
from pyquery import PyQuery as pq

BASEURL = "https://www.avito.ru"

urls = ["https://www.avito.ru/rossiya/noutbuki",
        "https://www.avito.ru/sankt-peterburg/noutbuki",
        "https://www.avito.ru/moskva/noutbuki",
        "https://www.avito.ru/sankt-peterburg/tovary_dlya_kompyutera/komplektuyuschie/zhestkie_diski",
        "https://www.avito.ru/sankt-peterburg/tovary_dlya_kompyutera/perenosnye_zhestkie_diski",

       ]

regexes = {"[xXхХ]220": {},
           "[xXхХ] 220": {},
           r"^(?!.*(зарядн|салазк|адапте|ultrabook|mac|шлейф|ультрабу|игровой|ide)).*(usb|внешни)":
               {'price_max': 3000},
          }

class Adtuple(tuple):
    def __str__(self):
        return "{}\t{}\t{}".format(self[1], self[0], BASEURL+self[2])
    
def safe_cast(val, to_type, default=0):
    try:
        val = val.replace(' руб.', '').replace(' ', '')
        return to_type(val)
    except (ValueError, TypeError):
        return default


def find_good(adlist):
    good_list = []
    for ad in adlist:
        #print(ad[0])
        for regex in regexes:
            if re.search(regex, ad[0], re.IGNORECASE):
                if (regexes[regex].get('price_min') and (safe_cast(ad[1], int) >= regexes[regex].get('price_min'))) or \
                   (regexes[regex].get('price_max') and (safe_cast(ad[1], int) <= regexes[regex].get('price_max'))):
                    #if re.search("[Ii]ntel", ad[0]):
                    good_list.append(ad)
    return good_list

for url in urls:
    tree = pq(url)
    posts = tree("div.description")

    ads = []
    for post in posts:
        title = pq(post)('h3.title>a').text().strip()
        link = pq(post)('h3.title>a').attr('href')
        price = pq(post)('div.about').text().strip()
        ads.append(Adtuple((title, price, link)))

    for good_ad in find_good(ads):
            print(good_ad)