Question

我一直在使用puppeteer尝试获取pdfs - 或者它的缓冲区响应 - 来自一个网站，该网站在点击文档链接后执行两个请求（在新标签中打开）：

第一个请求（http://epicdocs.planningni.gov.uk/ViewDocument.pa?uri=4157826&ext=PDF）检索会话guid以访问文档
第二个请求（http://epicdocs.planningni.gov.uk/ViewDocument.aspx?guid=4ecd1fe5-43c6-4202-96e3-66b393fb819c）使用该guid访问文档并在浏览器上呈现pdf。

我尝试的结果是生成了一个空白的pdf，即使它是在页面加载后创建的（使用Fiddler检查）。

我试过

拦截targetcreated事件以获取页面
获取第二个请求网址并使用page.goto获取pdf
等待页面响应以获取缓冲区
将Page.setDownloadBehaviour设置为允许下载而不是在浏览器中呈现

感谢任何指导和帮助。尝试的代码如下：

const puppeteer = require("puppeteer");

let browser;

async function getDocument(index, title, page) {
  if (index != 19) return "";
  console.log("getDocument START");
  console.log("#repDocuments__ctl" + index + "_lnkViewDoc\ntitle: " + title);
  let docPagePromise = new Promise((resolve, reject) =>
    browser.once("targetcreated", async target => {
      let targetUrl = await target.url();
      if (targetUrl.indexOf("ViewDocument.aspx?") !== -1) {
        console.log(targetUrl);
        return resolve(target.page());
      } else {
        console.log("Failed to detect the ViewDocument page");
      }
    })
  );

  /* Tried to set the download behaviour to download automatically the pdf but it didn't work */
  // await page._client.send("Page.setDownloadBehaviour", {
  //   behaviour: "allow",
  //   downloadPath: "./"
  // });
  await page.click(`#repDocuments__ctl${index}_lnkViewDoc`);
  let pdfResults = "";
  let pdfPage = await docPagePromise;

  /* If I get the target from the page returned from the promise I get the correct ur, however the page url is blank */
  // let target = await pdfPage.target();
  // let url = await target.url();
  // let response = await pdfPage.goto(url);
  // console.log(response);
  pdfPage.on("console.log", msg => console.log(msg));

  /* This is never called */
  await pdfPage.on("response", async response => {
    console.log("PDF PAGE Response");
    let responseBuffer = await response.buffer();
    let responseHeaders = response.headers();
    console.log("PDF PAGE Response Header: " + responseHeaders);
    console.log("PDF PAGE Response Buffer: " + responseBuffer);
    return {
      responseHeaders,
      responseBuffer
    };
  });
  console.log(pdfResults);

  let pdfTitle = await pdfPage.title();
  console.log("PDFPage URL: " + pdfPage.url());
  console.log("PDFPage Title: " + pdfTitle);

  let pdfTarget = await pdfPage.target();
  console.log("PDFTarget URL: " + (await pdfTarget.url()));
  console.log("PDFTarget Type: " + pdfTarget.type());
  pdfPage = await pdfTarget.page();
  console.log("PDFPage URL: " + pdfPage.url());

  await pdfPage.waitFor(3000);
  let pdf = await pdfPage.pdf({ path: title + ".pdf" });
  console.log(pdf);
  return pdf;
}

async function getAdditionalDocumentation(page) {
  console.log("getAdditionalDocumentation START");

  await page.waitForSelector("#repGroupSummary__ctl1_lnkGroupName");
  await page.click("#repGroupSummary__ctl1_lnkGroupName");
  await page.waitForSelector("#pnlDocumentList > table > tbody > tr");

  await page.waitFor(2000);

  const documents = await page.$$eval(
    "#pnlDocumentList > table > tbody > tr",
    docs =>
      docs.map((doc, i) => ({
        type: doc.querySelector(".tdl-subgroup > span").innerText,
        datePublished: doc.querySelector(
          ".tdl-date > span[id*='DatePublished']"
        ).innerText,
        dateReceived: doc.querySelector(".tdl-date > span[id*='DateReceived']")
          .innerText,
        docType: doc.querySelector(".tdl-doctype > span").innerText,
        description: doc.querySelector(".tdl-description > span").innerText
        // 'docBuffer': window.getDocument(i + 1, doc.querySelector('.tdl-description > span').innerText)
      }))
  );

  for (let i = 0; i < documents.length; i++) {
    documents[i].docBuffer = await getDocument(i + 1, documents[i].description, page);
  }

  await page.click("#btnSummary");
  console.log("getAdditionalDocumentation FINISH");

  return documents;
}

async function getDocuments(page, browser) {
  console.log("getDocuments");
  let newPagePromise = new Promise((resolve, reject) =>
    browser.once("targetcreated", async target => {
      let targetUrl = await target.url();
      if (targetUrl.indexOf("ShowCaseFile.aspx?") !== -1) {
        console.log(targetUrl);
        return resolve(target.page());
      } else {
        console.log("Failed to detect the ShowCaseFile page");
      }
    })
  );
  await page.click("#tab_externalDocuments > span");
  await page.waitForSelector("#hp-doc-link");

  await page.click("#hp-doc-link");
  const newPage = await newPagePromise;

  const additionalDocumentation = await getAdditionalDocumentation(newPage);

  return {
    additionalDocumentation
  };
}




async function run() {
  try {
    browser = await puppeteer.launch();
    const page = await browser.newPage();

    page.on("console", msg => console.log("PAGE LOG:", ...msg.args));

    const planningReference = "LA04/2017/1388/F";
    await page.goto(
      "http://epicpublic.planningni.gov.uk/publicaccess/search.do?action=simple&searchType=Application"
    );
    await page.waitForSelector("#simpleSearchString");
    await page.type("#simpleSearchString", planningReference);
    await page.click("#simpleSearchForm > div.row3 > input.button.primary");

    await page.waitForSelector("#simpleDetailsTable");

    console.log("getDocuments START");
    const documents = await getDocuments(page, browser);
    console.log("getDocuments FINISH");

    console.log(documents);
    console.log(documents.additionalDocumentation.length);
  } finally {
    browser.close();
  }
}

run();

Answer 1

使用exposefunction将缓冲区数据写入磁盘：

page.exposeFunction("writeABString", async (strbuf, targetFile) => {
    var str2ab = function _str2ab(str) { // Convert a UTF-8 String to an ArrayBuffer

        var buf = new ArrayBuffer(str.length); // 1 byte for each char
        var bufView = new Uint8Array(buf);

        for (var i=0, strLen=str.length; i < strLen; i++) {
          bufView[i] = str.charCodeAt(i);
        }
        return buf;
    }

    console.log("In 'writeABString' function...");

    return new Promise((resolve, reject) => {

        // Convert the ArrayBuffer string back to an ArrayBufffer, which in turn is converted to a Buffer
        let buf = Buffer.from(str2ab(strbuf));

        // Try saving the file.        
        fs.writeFile(targetFile, buf, (err, text) => {
            if(err) reject(err);
            else resolve(targetFile);
        });
    });
});

使用下载链接，您可以将其与fetch api配合使用，将其作为blob进行转换，并将其转换为：

page.evaluate( async () => {

function arrayBufferToString(buffer){ // Convert an ArrayBuffer to an UTF-8 String

    var bufView = new Uint8Array(buffer);
    var length = bufView.length;
    var result = '';
    var addition = Math.pow(2,8)-1;

    for(var i = 0;i<length;i+=addition){
        if(i + addition > length){
            addition = length - i;
        }
        result += String.fromCharCode.apply(null, bufView.subarray(i,i+addition));
    }
    return result;
}

   let geturl = "https://whateverurl.example.com";

   return fetch(geturl, {
        credentials: 'same-origin', // usefull when we are logged into a website and want to send cookies
        responseType: 'arraybuffer', // get response as an ArrayBuffer
   })
   .then(response => response.arrayBuffer())
   .then( arrayBuffer => {
        var bufstring = arrayBufferToString(arrayBuffer);
        return window.writeABString(bufstring, '/tmp/downloadtest.pdf');
   })
   .catch(function (error) {
        console.log('Request failed: ', error);
   });
 });

有关更多信息，请在github puppeteer页面上查看此问题。该问题还提出了上述解决方案。 Source

使用会话生成的url获取pdpe缓冲区和puppeteer

1 个答案: