#!/usr/bin/env python

import sys

import scrapy
from scrapy.http import Response
from scrapy.crawler import CrawlerProcess
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor


class TvShowItem(scrapy.Item):
    article_id = scrapy.Field()
    article_title = scrapy.Field()
    title = scrapy.Field()
    date = scrapy.Field()
    summary = scrapy.Field()
    image_url = scrapy.Field()
    download_url = scrapy.Field()


class TvShow(CrawlSpider):
    name = "rlsb_tvshow"
    allowed_domains = ["rlsbb.ru"]
    start_urls = ["https://rlsbb.ru/category/tv-shows/"]
    custom_settings = {
        'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
        'AUTOTHROTTLE_ENABLED': True,
        'DOWNLOAD_DELAY': 10,
    }
    rules = [
        Rule(LinkExtractor(allow=r"/tv-shows/page/"), callback="parse", follow=True)
    ]

    def parse(self, response):
        pass


def main():
    process = CrawlerProcess()
    process.crawl(TvShow)
    process.start()
    return 0


if __name__ == "__main__":
    sys.exit(main())