Question

我不断收到此错误。当我使用下面的代码将值附加到项目时。注意，我没有包含蜘蛛类，start_requests函数或第一个解析函数，但我认为那里没有错误，因为它们都可以正常运行。

from folder.items import fd
import scrapy
from bs4 import BeautifulSoup

 def parsenestedgame(self, response):
        nested_url = response.url
        nested_html = response.text
        nested_soup = BeautifulSoup(nested_html, "html.parser")

        odds_results = (nested_soup.find_all("button", "_32ge9K w0u0II _2D_dGb"))
        team_results = (nested_soup.find_all("span", "_2I4p8L"))

        sports = ["Basketball", "Hockey",
                  "Major League Baseball",
                  "Tennis", "Boxing / MMA",
                  "American Football"]
        sportsurls = ["url1", "url2",
                      "url3",
                      "url4", "url5",
                      "url6"]
        sportsdict = dict(zip(sportsurls, sports))
        for key in sportsdict:
            if key in nested_url:
                sport = sportsdict[key]
        teams_list = []
        odds_list = []

        for result in odds_results:
            odds_list.append(result.text)

        for team in team_results:
            teams_list.append(team.text)

        if not teams_list:
            print(f"There were no teams found at {nested_url}.")

        else:

            game = f"{teams_list[0]} vs {teams_list[1]}"

            bookie_list = ["bookie1", "bookie2", "bookie3", "bookie4", "bookie5", "bookie6", "bookie7",
                           "bookie8", "bookie10", "bookie11", "bookie12", "bookie13", "bookie14",
                           "bookie15", "bookie16", "bookie17",
                           "bookie18", "bookie19"]
            if len(odds_list) == 18:

                odds_list1 = [odds_list[0], odds_list[1], odds_list[2], odds_list[3], odds_list[4],
                              odds_list[5], odds_list[6],
                              odds_list[7], odds_list[8]]
                odds_list2 = [odds_list[9], odds_list[10], odds_list[11], odds_list[12], odds_list[13],
                              odds_list[14],
                              odds_list[15], odds_list[16], odds_list[17]]

                odds_list1P = [1, 2, 3, 4, 5, 6, 7, 8, 9]
                odds_list2P = [1, 2, 3, 4, 5, 6, 7, 8, 9]

                x, y = 0, 0
                for entries1 in odds_list1:
                    if not entries1:
                        odds_list1[x] = 0
                        odds_list1P[x] = 0
                    else:
                        odds_list1[x] = int(entries1)
                        entries1 = float(entries1)
                        if entries1 > 0:
                            odds_list1P[x] = ((entries1 / 100) + 1)
                        if entries1 < 0:
                            odds_list1P[x] = ((100 / abs(entries1)) + 1)
                        # odds_list1P[x] = (abs(int(entries1)))/(abs(int(entries1))+100)
                    x += 1
                for entries2 in odds_list2:
                    if not entries2:
                        odds_list2[y] = 0
                        odds_list2P[y] = 0
                    else:
                        odds_list2[y] = int(entries2)
                        entries2 = float(entries2)
                        if entries2 > 0:
                            odds_list2P[y] = ((entries2 / 100) + 1)
                        if entries2 < 0:
                            odds_list2P[y] = ((100 / abs(entries2)) + 1)
                        # odds_list2P[y] = (abs(int(entries2)))/(abs(int(entries2))+100)
                    y += 1

                # I now have all the lists I need to pass to items
                print(type(game))
                print(type(teams_list[0]))
                print(type(teams_list[1]))
                print(type(odds_list1[0]))
                print(type(odds_list2[0]))
                print(type(odds_list1P[0]))
                print(type(odds_list2P[0]))
                print(type(bookie_list[0]))
                print(type(sport))

                fd = fd()

                fd["game"] = game

                fd["team1"] = teams_list[0]

                fd["team2"] = teams_list[1]

                fd["odds1a"] = odds_list1[0]

                fd["odds2a"] = odds_list2[0]

                fd["odds1d"] = odds_list1P[0]

                fd["odds2d"] = odds_list2P[0]

                fd["bookie"] = b_list[0]

                fd["sport"] = sport

                yield fd

这是我下面的物品。

import scrapy


class fd(scrapy.Item):
    game = scrapy.Field()
    team1 = scrapy.Field()
    team2 = scrapy.Field()
    odds1a = scrapy.Field()
    odds2a = scrapy.Field()
    odds1d = scrapy.Field()
    odds2d = scrapy.Field()
    bookie = scrapy.Field()
    sport = scrapy.Field()

当我在上面的代码行的前面打印出类型时，您会得到这个。

输出

<class 'str'>
<class 'str'>
<class 'str'>
<class 'int'>
<class 'int'>
<class 'int'>
<class 'int'>
<class 'str'>
<class 'str'>
2020-06-11 16:58:26 [scrapy.core.scraper] ERROR: Spider must return Request, BaseItem, dict or None, got 'tuple' in <GET URL>

我不明白，请帮助！如果需要，我将提供更多代码。

Answer 1

我相信您在代码中调用import matplotlib.pyplot as plt import random as rand from pylab import *类时会发生错误：

folder.item

您要使用与fd = fd()类相同的方式来命名变量，我建议重命名该变量：

folder.item

当然，这意味着您还必须更改代码的以下部分：

item_data = fd()

希望这将为您指明正确的方向。另外，我不确定您为什么同时使用item_data["game"] = game item_data["team1"] = teams_list[0] item_data["team2"] = teams_list[1] . . . item_data["sport"] = sport yield fd(**item_data)和beautiful soup，据我所知，如果有特定原因，我很高兴知道关于它的更多信息。请随时提出任何问题！：D

错误：Spider必须返回Request，BaseItem，dict或None，得到“元组”

1 个答案: