Python 我想用scrapy刮取的数据打印一个合适的表格

因此，我已经将所有代码编写到了scrape表中[http://www.rarityguide.com/cbgames_view.php?FirstRecord=21][1] 但我得到的输出像

# the output that i get

{'EXG': (['17.00',
          '10.00',
          '90.00',
          '9.00',
          '13.00',
          '17.00',
          '16.00',
          '43.00',
          '125.00',
          '16.00',
          '11.00',
          '150.00',
          '17.00',
          '24.00',
          '15.00',
          '24.00',

  

'21.00',
          '36.00',
          '270.00',
          '280.00'],),
 'G': ['8.00',
       '5.00',
       '38.00',
       '2.00',
       '6.00',
       '7.00',
       '6.00',
       '20.00',
       '40.00',
       '7.00',
       '5.00',
       '70.00',
       '6.00',
       '12.00',
       '7.00',
       '12.00',
       '10.00',
       '15.00',
       '120.00',
       '140.00'],
 'company': (['Milton Bradley',
              'Lowell',
              'Milton Bradley',
              'Transogram',
              'Milton Bradley',
              'Transogram',
              'Standard Toykraft',
              'Ideal',
              'Game Gems',
              'Milton Bradley',
              'Parker Brothers',
              'CPC',
              'Parker Brothers',
              'Whitman',
              'Ideal',
              'Transogram',
              'King Features',
              'Westinghouse',
              'Parker Brothers',
              'Parker Brothers'],),
 'mnm': (['26.00',
          '19.00',
          '195.00',
          '15.00',
          '30.00',
          '29.00',
          '31.00',
          '65.00',
          '204.00',
          '25.00',
          '22.00',
          '250.00',
          '27.00',
          '42.00',
          '23.00',
          '37.00',
          '40.00',
          '57.00',
          '415.00',
          '435.00'],),
 'rarity': ([],),
 'title': (['Beat the Clock',
            'Beat the Clock',
            'Beatles - Flip Your Wig',
            'Ben Casey M.D.',
            'Bermuda Triangle',
            'Betsy Ross and the Flag',
            'Beverly Hillbillies',
            'Beware the Spider',
            'Bewitched',
            'Bewitched - Stymie Card Game',
            'Bionic Woman',
            'Blade Runner',
            'Blondie',
            'Blondie - Playing Card Game',
            'Blondie - Sunday Funnies',
            'Blondie - The Hurry Scurry Game',
            "Blondie and Dagwood's Race for the Office",
            'Blondie Goes to Leisureland',
            'Boom or Bust',
            'Boom or Bust'],),
 'year': (['1969',
           '1954',
           '1964',
           '1961',
           '1976',
           '1961',
           '1963',
           '1980',
           '1965',
           '1964',
           '1976',
           '1982',
           '1969',
           '1941',
           '1972',
           '1966',
           '1950',
           '1935',
           '1951',
           '1959'],)}

# the output that i want!
{"EXG": ["17.00"],
  "MNM": ["26.00"],
  "year": ["1969"],
  "company": ["Milton Bradley"],
  "Title": ["Beat the Clock"] }

{"EXG": ["10.00"],
  "MNM": ["19.00"],
  "year": ["1954"],
  "company": ["Lowell"],
  "Title": ["Beat the Clock"] }
and then so on for all values.

ayone能帮我实现这样的输出吗

# the output that i get

{'EXG': (['17.00',
          '10.00',
          '90.00',
          '9.00',
          '13.00',
          '17.00',
          '16.00',
          '43.00',
          '125.00',
          '16.00',
          '11.00',
          '150.00',
          '17.00',
          '24.00',
          '15.00',
          '24.00',

  

'21.00',
          '36.00',
          '270.00',
          '280.00'],),
 'G': ['8.00',
       '5.00',
       '38.00',
       '2.00',
       '6.00',
       '7.00',
       '6.00',
       '20.00',
       '40.00',
       '7.00',
       '5.00',
       '70.00',
       '6.00',
       '12.00',
       '7.00',
       '12.00',
       '10.00',
       '15.00',
       '120.00',
       '140.00'],
 'company': (['Milton Bradley',
              'Lowell',
              'Milton Bradley',
              'Transogram',
              'Milton Bradley',
              'Transogram',
              'Standard Toykraft',
              'Ideal',
              'Game Gems',
              'Milton Bradley',
              'Parker Brothers',
              'CPC',
              'Parker Brothers',
              'Whitman',
              'Ideal',
              'Transogram',
              'King Features',
              'Westinghouse',
              'Parker Brothers',
              'Parker Brothers'],),
 'mnm': (['26.00',
          '19.00',
          '195.00',
          '15.00',
          '30.00',
          '29.00',
          '31.00',
          '65.00',
          '204.00',
          '25.00',
          '22.00',
          '250.00',
          '27.00',
          '42.00',
          '23.00',
          '37.00',
          '40.00',
          '57.00',
          '415.00',
          '435.00'],),
 'rarity': ([],),
 'title': (['Beat the Clock',
            'Beat the Clock',
            'Beatles - Flip Your Wig',
            'Ben Casey M.D.',
            'Bermuda Triangle',
            'Betsy Ross and the Flag',
            'Beverly Hillbillies',
            'Beware the Spider',
            'Bewitched',
            'Bewitched - Stymie Card Game',
            'Bionic Woman',
            'Blade Runner',
            'Blondie',
            'Blondie - Playing Card Game',
            'Blondie - Sunday Funnies',
            'Blondie - The Hurry Scurry Game',
            "Blondie and Dagwood's Race for the Office",
            'Blondie Goes to Leisureland',
            'Boom or Bust',
            'Boom or Bust'],),
 'year': (['1969',
           '1954',
           '1964',
           '1961',
           '1976',
           '1961',
           '1963',
           '1980',
           '1965',
           '1964',
           '1976',
           '1982',
           '1969',
           '1941',
           '1972',
           '1966',
           '1950',
           '1935',
           '1951',
           '1959'],)}

# the output that i want!
{"EXG": ["17.00"],
  "MNM": ["26.00"],
  "year": ["1969"],
  "company": ["Milton Bradley"],
  "Title": ["Beat the Clock"] }

{"EXG": ["10.00"],
  "MNM": ["19.00"],
  "year": ["1954"],
  "company": ["Lowell"],
  "Title": ["Beat the Clock"] }
and then so on for all values.

基本上，我希望有一个包含所有键值对的字典，而不是每个键都有一个完整的字典。 这是我的蜘蛛代码

import scrapy
from ..items import RarityItem


class RarityScraper(scrapy.Spider):
    name = "rarity"
    start_urls = [
        "http://www.rarityguide.com/cbgames_view.php?FirstRecord=21"
    ]

    def parse(self, response):
        table = response.css(
            "form")

        items = RarityItem()

        for contents in table:
            title = contents.css("td:nth-child(2)::text").extract()
            company = contents.css("td:nth-child(3)::text").extract()
            year = contents.css("td:nth-child(4)::text").extract()
            rarity = contents.css("td:nth-child(5)::text").extract()
            mnm = contents.css("td:nth-child(6)::text").extract()
            EXG = contents.css("td:nth-child(7)::text").extract()
            G = contents.css("td:nth-child(8)::text").extract()

            items["title"] = title,
            items["company"] = company,
            items["year"] = year,
            items["rarity"] = rarity,
            items["mnm"] = mnm,
            items["EXG"] = EXG,
            items["G"] = G

            yield items

---

如果所有列表长度相同，则在此行之后

G=contents.css（“td:nth child（8）：：text”）.extract（）

：

添加此ode代码段：

arr = []
for _ in range(len(title)):
    arr.append({
        'EXP': title[_], 'company': company[_], 'year': year[_], 'rarity': rarity[_],
        'MNM': mnm[_], 'EXG': EXG[_], 'G': G[_]})

然后键入以下内容：

for _ in arr:
    print(_)

---

要查看输出数组，需要遍历表中的每一行并分别处理行数据。 由于所有行的长度相同，您可以使用列表解包将数据写入

dict

项：

def parse(self, response):
    table = response.css(
        "form table")

    for row in table.css("tr"):
        i = {}
        _, i["title"], i["company"], i["year"], _, i["mnm"], i["EXG"], i["G"] = row.css("td::text").extract()
        i["rarity"] = row.css("td img::alt").extract_first("")
        yield i

---

你能试着把这个

.extract（）

转换成这个

.extract（）[0]

@lapest吗？我知道我可以通过键入它的索引来获取第一项，但我不想只需要第一项，我希望所有数据都采用这种格式。为了更好的理解，我编辑了qstn。请检查我添加的答案。它给了Indexer