一尘不染

Node.js puppeteer-从复杂的txt文件中获取内容

node.js

如何在puppeteer中下载,访问和处理复杂的txt文件?

我可以访问xml文件[Node.js puppeteer-下载/访问xml文件并处理内容),如下所示:

await page.goto(myPage, {waitUntil: 'load'});

const newPage = await page.evaluate(() => {

    var columns = document.getElementsByTagName("VALUEA");

    var values = {"values":[]};

    for(let f in columns){
        values.values.push(columns[f].innerText);
    }

    return JSON.stringify(values);

});

console.log(JSON.parse(newPage))

这给了我想要的值。但是,如果我要访问如下所示的txt文件…,并且要进行测试以获取所有“ VALUEA”,我会得到:

{"values":[null,null,null]}

那就是我正在查看的TXT文件:

<XYZ-DOCUMENT>117.txt : 20180824
<XYZ-HEADER>117.hdr.sgml : 20180824
<VALUE00>20180824153107
VALUE01:        117
VALUE02:    ABC

COMPANY:

    COMPANY DATA:   
        VALUE03:            Some Company
        VALUE04:            777

    BUSINESS ADDRESS:   
        VALUE05:        Some street
        VALUE06:            Some city

</XYZ-HEADER>
<DOCUMENT>
<VALUE07>ABC
<SEQUENCE>1
<FILENAME>primary_doc.xml
<TEXT>
<XML>
<?xml version="1.0" encoding="UTF-8"?>
<Submission xmlns="http://www.xyz.it/abc/" xmlns:com="http://www.xyz.it/abc/common">
  <headerData>
    <VALUE08>ABC</VALUE08>
    <xxxInfo>
      <xxx>
        <credentials>
          <VALUE09>777</VALUE09>
          <VALUE10>XXXXXXXX</VALUE10>
        </credentials>
      </xxx>
      <VALUE11>06-30-2018</VALUE11>
    </xxxInfo>
  </headerData>
  <bodyData>
    <coverPage>
      <VALUE12>06-30-2018</VALUE12>
      <VALUE13>1</VALUE13>
      <amendmentInfo>
        <VALUE14>STRAWBERRIES</VALUE14>
      </amendmentInfo>
      <xxxManager>
        <VALUE15>Corp</VALUE15>
        <address>
          <VALUE16:street1>MOUNTAIN STREET</VALUE16:street1>
          <VALUE17:city>NEW YORK</VALUE17:city>
        </address>
      </xxxManager>
      <provideInfoForInstruction5>N</provideInfoForInstruction5>
    </coverPage>
  </bodyData>
</Submission>
</XML>
</TEXT>
</DOCUMENT>
<DOCUMENT>
<TYPE>INFORMATION TABLE
<SEQUENCE>2
<FILENAME>xml_xyz.xml
<TEXT>
<XML>
<?xml version="1.0" encoding="UTF-8"?>
<informationTable xmlns="http://www.xyz.it/abc/informationtable" xmlns:xsi=" http://www.w3.org/2001/XMLSchema-instance">
<infoTable>
<VALUEA>Company A</VALUEA>
<VALUEB>INC</VALUEB>
<shParent>
<VALUEC>123</VALUEC>
<VALUED>AB</VALUED>
</shParent>
</infoTable>
<infoTable>
<VALUEA>Company B</VALUEA>
<VALUEB>LTD</VALUEB>
<shParent>
<VALUEC>567</VALUEC>
<VALUED>ST</VALUED>
</shParent>
</infoTable>

...

</informationTable>
</XML>
</TEXT>
</DOCUMENT>
</XYZ-DOCUMENT>

最后,我要获取所有VALUE(主要是VALUEA,VALUEB,VALUEC,VALUEC)!怎么做?


阅读 315

收藏
2020-07-07

共1个答案

一尘不染

您可以采用如下方案来从文本内容VALUEAVALUEBVALUEC,和VALUED

const example = await page.evaluate( () =>
{
    const page = document.createElement( 'html' );
    const page_content = document.body.textContent;

    page.innerHTML = page_content;

    return {
        'VALUEA' : Array.from( page.getElementsByTagName( 'VALUEA' ), e => e.textContent ),
        'VALUEB' : Array.from( page.getElementsByTagName( 'VALUEB' ), e => e.textContent ),
        'VALUEC' : Array.from( page.getElementsByTagName( 'VALUEC' ), e => e.textContent ),
        'VALUED' : Array.from( page.getElementsByTagName( 'VALUED' ), e => e.textContent )
    };
});

console.log( example.VALUEA[0] ); // Company A
console.log( example.VALUEA[1] ); // Company B

console.log( example.VALUEB[0] ); // INC
console.log( example.VALUEB[1] ); // LTD

console.log( example.VALUEC[0] ); // 123
console.log( example.VALUEC[1] ); // 567

console.log( example.VALUED[0] ); // AB
console.log( example.VALUED[1] ); // ST
2020-07-07