import scrapy,logging,time,os
from Comics.items import ComicItem
from Comics.loader import ComicLoader
from Comics.utils import ComicPath
from Comics.settings import PROJECT_KEY
import skip

class RmComicSpider(scrapy.Spider):
    name = 'yh_comic'
    allowed_domains = ['www.shuanglilock.com.cn']
    main_url = 'https://'+allowed_domains[0]
    start_urls = main_url+'/info'
    
    def start_requests(self):
#        for x in range(0,60):
            yield scrapy.Request("https://www.shuanglilock.com.cn/info/27145/", callback=self.parse_comic)

    # 获取多个漫画信息
#    def books_comic(self, response):
#        comics = ComicLoader(item=ComicItem(), response=response)
#        data = comics.get_xpath('//script[@id="__NEXT_DATA__"]/text()')[0]
#        for book in comics.get_exec(data, str_exec="props.pageProps.books"):
#            comics.add_value('link', self.start_urls+"/"+book['id'])
#            if book['name'] not in skip.skip_comic:
#                yield scrapy.Request(url=self.start_urls+"/"+book['id'], callback=self.parse_comic)

    # 获取某个漫画的相关数据
    # 获取到多个章节链接后进入下个流程
    def parse_comic(self, response):
        comic_item = ComicLoader(item=ComicItem(), response=response)
        comic_item.project_name(self.name)
        comic_item.name(xpath='//div[@class="comics-detail__info"]/h1[@class="comics-detail__title"]/text()')
        comic_item.icon(xpath='//div[@class="pure-u-1-1 pure-u-sm-1-3 pure-u-md-1-6"]/img/@src')
        comic_item.author(xpath='//div[@class="comics-detail__info"]/h2[@class="comics-detail__author"]/text()')
        comic_item.tags(xpath='//div[@class="tag-list"]/a[@class="tag"]/text()')
        comic_item.dep(xpath='//p[contains(@class,"comics-detail__desc")]/text()')
        #comic_item.date(xpath='//div[contains(@class,"bookid_bookInfo")]/p[5]/small/text()', index=1)
        comic_item.genre(value="樱花漫画")
        #comic_item.age_rating(value="R18+")
        chapter_href = comic_item.get_xpath('//div[contains(@id,"chapter-items")]'
                                               '//a[@class="comics-chapters__item"]/@href')
        chapters = comic_item.get_xpath('//div[contains(@id,"chapter-items")]'
                                           '//a[@class="comics-chapters__item"]//span/text()')
        for chapter, link in zip(chapters, chapter_href):
            comic_item.chapters(value=chapters)
            comic_item.chapter(value=chapter)
            item = comic_item.load_item()
            cbz_path = ComicPath(item).get_file_path(result_type="cbz", convert=True)
            if os.path.exists(cbz_path):
                logging.info(f"漫画 {cbz_path} 已存在, 跳过中...")
                yield item
            else:
                yield scrapy.Request(self.main_url+link, meta={'item': item}, callback=self.parse_chapter)


    # 读取某章节下的所有图片
    def parse_chapter(self, response):
        comic_item = ComicLoader(item=response.meta['item'], response=response)
        comic_item.image_urls(xpath='//div[@class="comiclist"]/div[@class="comicpage"]/div/img/@data-original')
        comic_item.images(xpath='//div[@class="comiclist"]/div[@class="comicpage"]/div/img/@data-original')
        comic = comic_item.load_item()
        yield comic 

    def parse(self, response):
        raise NotImplementedError
    
    def error_parse(self, response):
        raise NotImplementedError