scrapy下 爬虫爬取 子页面详细信息部分 代码出错

Question

问题遇到的现象和发生背景

问题相关代码，请勿粘贴截图

运行结果及报错内容

我的解答思路和尝试过的方法

我想要达到的结果

用python写爬虫，目标是获取排行总页面的作品名和排名，再获取该作品详情页部分信息。在生成详情页请求的代码处提示出错：

运行时的报错：

恳请指教 谢谢！急

from scrapy import Request
from scrapy.spiders import Spider


class AniRank(Spider):
    name = 'AniRank'
    this_page = 1

    def __init__(self, name=None, ):
        super().__init__(name)
        self.inner_parse = None

    def start_requests(self):
        url = 'https://bangumi.tv/anime/browser?sort=rank'
        yield Request(url)  # 生成请求对象

    def parse(self, response, **kwargs, ):

        list_selector = response.xpath("//li/div[@class='inner']")

        for one_selector in list_selector:

            anime_rank = one_selector.xpath("span/text()").extract()[0]
            anime_name = one_selector.xpath("h3/a/text()").extract()[0]
            anime_year = one_selector.xpath("p/text()").extract()[0]

            anime_year = anime_year.split('/')
            for n in anime_year:
                n = n.strip()
                if ((n.find("年") == 4) and (n.find("月") >= 0)) or (n.find("-") == 4):
                    anime_year = n

            rank_dict = {"bangumi排名": anime_rank,
                         "名称": anime_name,
                         "放送日期": anime_year, }

            url = 'https://bangumi.tv' + one_selector.xpath("h3/a/@href").extract()[0]    #生成详情页url

            yield Request(url,
                          rank_dict,
                          callback=self.inner_parse,)    #此处提示错误

    def inner_parse(self, response):
        anime_co = response.xpath("//ul[@id='infobox']//*[string()='动画制作']/../a/text()").extract()
        rank_dict["制作公司"] = anime_co
        yield rank_dict

        self.this_page += 1
        if self.this_page <= 6:
            next_url = "https://bangumi.tv/anime/browser?sort=rank&page=%d" % self.this_page
            yield Request(next_url, self.parse)

Answer 1

流程通了细节没改

import copy

from scrapy import Request
from scrapy.spiders import Spider


class AniRank(Spider):
    name = 'AniRank'
    this_page = 1

    def __init__(self):
        super(AniRank).__init__()

    def start_requests(self):
        url = 'https://bangumi.tv/anime/browser?sort=rank'
        yield Request(url)  # 生成请求对象

    def parse(self, response, **kwargs, ):
        list_selector = response.xpath("//li/div[@class='inner']")
        for one_selector in list_selector:
            anime_rank = one_selector.xpath("span/text()").extract()[0]
            anime_name = one_selector.xpath("h3/a/text()").extract()[0]
            anime_year = one_selector.xpath("p/text()").extract()[0]
            anime_year = anime_year.split('/')
            for n in anime_year:
                n = n.strip()
                if ((n.find("年") == 4) and (n.find("月") >= 0)) or (n.find("-") == 4):
                    anime_year = n
            rank_dict = {"bangumi排名": anime_rank,
                         "名称": anime_name,
                         "放送日期": anime_year, }
            url = 'https://bangumi.tv' + one_selector.xpath("h3/a/@href").extract()[0]  # 生成详情页url
            yield Request(url, meta={"rank_dict": copy.deepcopy(rank_dict)},
                          callback=self.inner_parse, )  # 此处提示错误

    def inner_parse(self, response):
        rank_dict = response.meta['rank_dict']
        anime_co = response.xpath("//ul[@id='infobox']//*[string()='动画制作']/../a/text()").extract()
        rank_dict["制作公司"] = anime_co
        yield rank_dict
        self.this_page += 1
        if self.this_page <= 6:
            next_url = "https://bangumi.tv/anime/browser?sort=rank&page=%d" % self.this_page
            yield Request(next_url, self.parse)