Nokogiri在XML中抓取错误的节点数据？

Question

我正在使用Nokogiri解析XML文件，它不起作用。

当我试图从三个级别的节点抓取时，它正在从类型的第一个节点抓取数据。我已经调试了它，它所在的节点应该是获得我需要的数据的正确节点，但它仍然从该类型的第一个节点中提取数据。

不在较高级别的节点中的项目正在输出到文件中，但是当我开始向上移动树时，它正在向文件写入错误的数据。

require 'nokogiri'

f = File.new("grammystext.txt", "w+")
x = File.open("items.xml", "r")
doc = Nokogiri::XML(x)
x.close

doc.xpath('//CWItemExport//ItemExportData//CWItem//ProductID//ItemColor//ItemSize').each_with_index do |item, i|
  f << item.parent.parent.parent.at_xpath('//CWVendor//VendorCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//CWVendor//VendorName').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemStyle').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemDescription').content + ", "
  f << item.parent.parent.parent.at_xpath('//TaxID//TaxIDCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemDepartment//ItemDeptCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemDepartment//ItemDeptName').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemClass//ItemClassCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemClass//ItemClassName').content + ", "

  f << item.attr("MainSize") + ", "
  f << item.at_xpath('Sku').content + ", "
  f << item.at_xpath('//ReplacementCost').content + ", "
  f << item.at_xpath('//CurrentRetail').content + "\n"

  puts item.parent.parent.parent if i == 6

  break if i == 7
end

f.close

XML:

<CWItem action="New">
  <CWVendor>
   <VendorCode>5TH</VendorCode>
   <VendorName>5TH SUN</VendorName>
    <VendorAddress />
    <VendorAddress2 />
    <VendorCity />
    <VendorZip />
    <VendorPhone />
  </CWVendor>
 <ItemStyle>AMM024-B105</ItemStyle>
 <ItemDescription>CALVERY</ItemDescription>
  <ItemBoolPLU>N</ItemBoolPLU>
  <TaxID>
    <TaxIDCode TaxStore="1" TaxIDType="Normal">0</TaxIDCode>
    <ComponentTax TxID="0" TxType="Normal" TxStartAmt="0.00" TxEndAmt="100000000.00" TxGlPayAcct=" ">0.000</ComponentTax>
  </TaxID>
  <ItemDepartment>
   <ItemDeptCode>APPAR</ItemDeptCode>
   <ItemDeptName>APPAR</ItemDeptName>
  </ItemDepartment>
  <ItemClass>
    <ItemClassCode>TEE</ItemClassCode>
   <ItemClassName>TEE-SHIRTS</ItemClassName>
  </ItemClass>
  <ItemSizeRun SizeRunCode="RUN" SizeRunName="">
    <SizeDef SizeLabel="">
      <Size SizeLabel="XS" Sequence="0">XS</Size>
      <Size SizeLabel="S" Sequence="1">S</Size>
      <Size SizeLabel="M" Sequence="2">M</Size>
      <Size SizeLabel="L" Sequence="3">L</Size>
      <Size SizeLabel="XL" Sequence="4">XL</Size>
      <Size SizeLabel="XXL" Sequence="5">XXL</Size>
    </SizeDef>
  </ItemSizeRun>
<ProductID PID="">
  <ItemColor ColorCode="N/A" ColorName="">
   <ItemSize MainSize="L">
      <Sku>400100018477</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="M">
      <Sku>400100018460</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="S">
      <Sku>400100018453</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="XL">
      <Sku>400100018484</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="XS">
      <Sku>400100031704</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>0.00</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="XXL">
      <Sku>400100035801</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>0.00</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
  </ItemColor>
</ProductID>
</CWItem>
<CWItem action="New">
  <CWVendor>
    <VendorCode>5TH</VendorCode>
    <VendorName>5TH SUN</VendorName>
    <VendorAddress />
    <VendorAddress2 />
    <VendorCity />
    <VendorZip />
    <VendorPhone />
  </CWVendor>
  <ItemStyle>AMM025-B105</ItemStyle>
  <ItemDescription>WINGMAN</ItemDescription>
  <ItemBoolPLU>N</ItemBoolPLU>
  <TaxID>
    <TaxIDCode TaxStore="1" TaxIDType="Normal">0</TaxIDCode>
    <ComponentTax TxID="0" TxType="Normal" TxStartAmt="0.00" TxEndAmt="100000000.00" TxGlPayAcct=" ">0.000</ComponentTax>
  </TaxID>
  <ItemDepartment>
    <ItemDeptCode>APPAR</ItemDeptCode>
    <ItemDeptName>APPAR</ItemDeptName>
  </ItemDepartment>
  <ItemClass>
    <ItemClassCode>TEE</ItemClassCode>
    <ItemClassName>TEE-SHIRTS</ItemClassName>
  </ItemClass>
  <ItemSizeRun SizeRunCode="RUN" SizeRunName="">
    <SizeDef SizeLabel="">
      <Size SizeLabel="XS" Sequence="0">XS</Size>
      <Size SizeLabel="S" Sequence="1">S</Size>
      <Size SizeLabel="M" Sequence="2">M</Size>
      <Size SizeLabel="L" Sequence="3">L</Size>
      <Size SizeLabel="XL" Sequence="4">XL</Size>
      <Size SizeLabel="XXL" Sequence="5">XXL</Size>
    </SizeDef>
  </ItemSizeRun>
<ProductID PID="">
  <ItemColor ColorCode="N/A" ColorName="">
    <ItemSize MainSize="L">
      <Sku>400100018514</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="M">
      <Sku>400100018507</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="S">
      <Sku>400100018491</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="XL">
      <Sku>400100018521</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>44.80</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="XS">
      <Sku>400100031711</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>0.00</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
    <ItemSize MainSize="XXL">
      <Sku>400100035818</Sku>
      <Pricing Currency="USD">
        <ReplacementCost>44.80</ReplacementCost>
        <AverageCost>0.00</AverageCost>
        <LandedCost>0.00</LandedCost>
        <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
      </Pricing>
    </ItemSize>
  </ItemColor>
</ProductID>
</CWItem>

这是我第一次使用Nokogiri，所以我可能在这里做错了什么。

Answer 1

问题

问题是xpaths的开始与 //.这表示在文档中的任何位置定位节点。

在下面的简化示例中，您可以看到使用 // 导致返回相同的子项（而不是迭代项的子项）。

require 'nokogiri'

xml = %Q{
<root>
  <item>
    <subitem>1</subitem>
  </item>
  <item>
    <subitem>2</subitem>
  </item>  
</root>
}

doc = Nokogiri::XML(xml)
doc.xpath('//root//item').each_with_index do |item, i|
    puts item.at_xpath('//subitem').content
end
#=> 1
#=> 1

如果要查看特定节点内的任何位置，则需要从句点开始-即 .//.将此应用于简化示例，您可以看到我们得到预期的子项结果:

doc = Nokogiri::XML(xml)
doc.xpath('//root//item').each_with_index do |item, i|
    puts item.at_xpath('.//subitem').content
end
#=> 1
#=> 2

解决方案

对于您的具体问题，您应该在项目的迭代中更改xpaths以包括 . 一开始。例如行:

f << item.parent.parent.parent.at_xpath('//CWVendor//VendorCode').content + ", "

将更改为:

    f << item.parent.parent.parent.at_xpath('.//CWVendor//VendorCode').content + ", "

总的来说，这会给你:

doc.xpath('.//CWItemExport//ItemExportData//CWItem//ProductID//ItemColor//ItemSize').each_with_index do |item, i|
  f << item.parent.parent.parent.at_xpath('.//CWVendor//VendorCode').content + ", "
  f << item.parent.parent.parent.at_xpath('.//CWVendor//VendorName').content + ", "
  f << item.parent.parent.parent.at_xpath('.//ItemStyle').content + ", "
  f << item.parent.parent.parent.at_xpath('.//ItemDescription').content + ", "
  f << item.parent.parent.parent.at_xpath('.//TaxID//TaxIDCode').content + ", "
  f << item.parent.parent.parent.at_xpath('.//ItemDepartment//ItemDeptCode').content + ", "
  f << item.parent.parent.parent.at_xpath('.//ItemDepartment//ItemDeptName').content + ", "
  f << item.parent.parent.parent.at_xpath('.//ItemClass//ItemClassCode').content + ", "
  f << item.parent.parent.parent.at_xpath('.//ItemClass//ItemClassName').content + ", "

  f << item.attr("MainSize") + ", "
  f << item.at_xpath('Sku').content + ", "
  f << item.at_xpath('.//ReplacementCost').content + ", "
  f << item.at_xpath('.//CurrentRetail').content + "\n"

  puts item.parent.parent.parent if i == 6

  break if i == 7
end

随着结果:

5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, L, 400100018477, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, M, 400100018460, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, S, 400100018453, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, XL, 400100018484, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, XS, 400100031704, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, XXL, 400100035801, 44.80, 199.00
5TH, 5TH SUN, AMM025-B105, WINGMAN, 0, APPAR, APPAR, TEE, TEE-SHIRTS, L, 400100018514, 44.80, 199.00

注:我也建议使用单 / 而不是 // 除非结构不知道。该 / 检查直接子节点，如果您得到意外的结果，这使得调试更容易。

Answer 2

这将是一个有点 守则检讨, ，但希望它会帮助你与你未来的解析。

1. 如果你要创建CSV，我 高度 建议您使用CSV gem。它保证您不会创建损坏的CSV（您的代码将在其中一个字段包含逗号时创建）。此外，它允许您使用变量名称更具描述性。

2. 正如其他人提到的那样，不要使用 // 如果可以使用 /.在某些情况下，除了不是你真正想要的之外，还有一个性能损失。

3. 的扩散 item.parent.parent.parent 告诉我你走得太远了。利用XPath的谓词（在 []），以确保您处于正确的水平。

4. 此外，只要我们利用XPath，您就不需要索引或 break 当你告诉XPath不要给你超过前7个。我没有实现这一点，因为鉴于您的数据，我不确定您是否需要它。

例子：:

CSV.open("grammystext.csv", "wb") do |csv|
  items = doc.xpath('/CWItemExport/ItemExportData/CWItem[ProductID/ItemColor/ItemSize]')       items.each do |item|
    vendor_code = item.at_xpath('CWVendor/VendorCode').text
    vendor_name = item.at_xpath('CWVendor/VendorName').text
    item_style  = item.at_xpath('ItemStyle').text
    ...
    main_size = item.at_xpath('ProductID/ItemColor/ItemSize')['MainSize']
    sku       = item.at_xpath('ProductID/ItemColor/ItemSize/Sku').text

    csv << [vendor_code, vendor_name, item_style, ... , main_size, sku]
  end
end

Answer 3

您没有根元素cwitemexport和root子项：itemexportdata元素。如果将XML更改为：

<CWItemExport>
    <ItemExportData>


        <CWItem action="New">
            <CWVendor>
                <VendorCode>5TH</VendorCode>

                <VendorName>5TH SUN</VendorName>
                <VendorAddress />
                <VendorAddress2 />
                <VendorCity />
                <VendorZip />
                <VendorPhone />
            </CWVendor>
            <ItemStyle>AMM024-B105</ItemStyle>
            <ItemDescription>CALVERY</ItemDescription>
            <ItemBoolPLU>N</ItemBoolPLU>
            <TaxID>
                <TaxIDCode TaxStore="1" TaxIDType="Normal">0</TaxIDCode>
                <ComponentTax TxID="0" TxType="Normal" TxStartAmt="0.00" TxEndAmt="100000000.00" TxGlPayAcct="
                    ">0.000</ComponentTax>
            </TaxID>
            <ItemDepartment>
                <ItemDeptCode>APPAR</ItemDeptCode>
                <ItemDeptName>APPAR</ItemDeptName>
            </ItemDepartment>
            <ItemClass>
                <ItemClassCode>TEE</ItemClassCode>
                <ItemClassName>TEE-SHIRTS</ItemClassName>
            </ItemClass>
            <ItemSizeRun SizeRunCode="RUN" SizeRunName="">
                <SizeDef SizeLabel="">
                    <Size SizeLabel="XS" Sequence="0">XS</Size>
                    <Size SizeLabel="S" Sequence="1">S</Size>
                    <Size SizeLabel="M" Sequence="2">M</Size>
                    <Size SizeLabel="L" Sequence="3">L</Size>
                    <Size SizeLabel="XL" Sequence="4">XL</Size>
                    <Size SizeLabel="XXL" Sequence="5">XXL</Size>
                </SizeDef>
            </ItemSizeRun>
            <ProductID PID="">
                <ItemColor ColorCode="N/A" ColorName="">
                    <ItemSize MainSize="L">
                        <Sku>400100018477</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="M">
                        <Sku>400100018460</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="S">
                        <Sku>400100018453</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="XL">
                        <Sku>400100018484</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="XS">
                        <Sku>400100031704</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>0.00</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="XXL">
                        <Sku>400100035801</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>0.00</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                </ItemColor>
            </ProductID>
        </CWItem>
        <CWItem action="New">
            <CWVendor>
                <VendorCode>5TH</VendorCode>
                <VendorName>5TH SUN</VendorName>
                <VendorAddress />
                <VendorAddress2 />
                <VendorCity />
                <VendorZip />
                <VendorPhone />
            </CWVendor>
            <ItemStyle>AMM025-B105</ItemStyle>
            <ItemDescription>WINGMAN</ItemDescription>
            <ItemBoolPLU>N</ItemBoolPLU>
            <TaxID>
                <TaxIDCode TaxStore="1" TaxIDType="Normal">0</TaxIDCode>
                <ComponentTax TxID="0" TxType="Normal" TxStartAmt="0.00" TxEndAmt="100000000.00" TxGlPayAcct="
                    ">0.000</ComponentTax>
            </TaxID>
            <ItemDepartment>
                <ItemDeptCode>APPAR</ItemDeptCode>
                <ItemDeptName>APPAR</ItemDeptName>
            </ItemDepartment>
            <ItemClass>
                <ItemClassCode>TEE</ItemClassCode>
                <ItemClassName>TEE-SHIRTS</ItemClassName>
            </ItemClass>
            <ItemSizeRun SizeRunCode="RUN" SizeRunName="">
                <SizeDef SizeLabel="">
                    <Size SizeLabel="XS" Sequence="0">XS</Size>
                    <Size SizeLabel="S" Sequence="1">S</Size>
                    <Size SizeLabel="M" Sequence="2">M</Size>
                    <Size SizeLabel="L" Sequence="3">L</Size>
                    <Size SizeLabel="XL" Sequence="4">XL</Size>
                    <Size SizeLabel="XXL" Sequence="5">XXL</Size>
                </SizeDef>
            </ItemSizeRun>
            <ProductID PID="">
                <ItemColor ColorCode="N/A" ColorName="">
                    <ItemSize MainSize="L">
                        <Sku>400100018514</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="M">
                        <Sku>400100018507</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="S">
                        <Sku>400100018491</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="XL">
                        <Sku>400100018521</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>44.80</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="XS">
                        <Sku>400100031711</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>0.00</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                    <ItemSize MainSize="XXL">
                        <Sku>400100035818</Sku>
                        <Pricing Currency="USD">
                            <ReplacementCost>44.80</ReplacementCost>
                            <AverageCost>0.00</AverageCost>
                            <LandedCost>0.00</LandedCost>
                            <CurrentRetail MarkDowns=" ">199.00</CurrentRetail>
                        </Pricing>
                    </ItemSize>
                </ItemColor>
            </ProductID>
        </CWItem>
    </ItemExportData>
</CWItemExport>

.

在grammystext.txt文件中获得以下内容：

5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, L, 400100018477, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, M, 400100018460, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, S, 400100018453, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, XL, 400100018484, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, XS, 400100031704, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, XXL, 400100035801, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, L, 400100018514, 44.80, 199.00
5TH, 5TH SUN, AMM024-B105, CALVERY, 0, APPAR, APPAR, TEE, TEE-SHIRTS, M, 400100018507, 44.80, 199.00

. 或者，您可以在读取文件后添加所需元素：

require 'nokogiri'

f = File.new("grammystext.txt", "w+")
x = File.open("items.xml", "r")
xml = "<CWItemExport><ItemExportData>#{x.read}</CWItemExport></ItemExportData>"
doc = Nokogiri::XML(xml)
x.close

doc.xpath('//CWItemExport//ItemExportData//CWItem//ProductID//ItemColor//ItemSize').each_with_index do |item, i|
  f << item.parent.parent.parent.at_xpath('//CWVendor//VendorCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//CWVendor//VendorName').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemStyle').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemDescription').content + ", "
  f << item.parent.parent.parent.at_xpath('//TaxID//TaxIDCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemDepartment//ItemDeptCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemDepartment//ItemDeptName').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemClass//ItemClassCode').content + ", "
  f << item.parent.parent.parent.at_xpath('//ItemClass//ItemClassName').content + ", "

  f << item.attr("MainSize") + ", "
  f << item.at_xpath('Sku').content + ", "
  f << item.at_xpath('//ReplacementCost').content + ", "
  f << item.at_xpath('//CurrentRetail').content + "\n"

  puts item.parent.parent.parent if i == 6

  break if i == 7
end

f.close

.