Background:
I am try to fill in a pdf file that:
a) has form fields.
b) that is stored on Google Drive.
with data that is stored in Google spreadsheet.
I am using:
Google Apps Script.
HtmlService
PDF-lib.js in a htmlOutput object generated from a htmlTemplate.
The work flow is:
The showModalDialog_downloadFilledPDFform_NAMOFFORM() function is called from a menu.
The function is:
function showModalDialog_downloadFilledPDFform_NAMOFFORM() {
var pdf_template_file_url = getPDFfileURL("form1.pdf");
var htmlTemplate = HtmlService.createTemplateFromFile('downloadFilledPDFformHTML');
htmlTemplate.dataFromServerTemplate = { pdf_template_file: "form1.pdf", pdf_template_file_url: pdf_template_file_url };
var htmlOutput = htmlTemplate.evaluate();
htmlOutput.setWidth(648.1);
htmlOutput.setHeight(286.300)
SpreadsheetApp.getUi().showModalDialog(htmlOutput, 'Download filled PDF');
}
The url that is passed to the htmlTemplate is generated by: "fillPDFForm.gs"
function: fillPDFForm.gs:
var pdfFileNamesAndIDs = [ ]
pdfFileNamesAndIDs.push(["form1.pdf", "1y8F5NgnK50mdtWSR6v1b8pELsbbBJert"])
pdfFileNamesAndIDs.push(["form2.pdf", "1B4BOaI-BqFmhmnFx7FaT-yys-U0vkYKz"])
pdfFileNamesAndIDs.push(["form3.pdf", "17LrJpRA5oBZBqw-2du1H74KxWIX55qYC"])
function getPDFfileURL(fileName) {
var documentID = "";
for (var i in pdfFileNamesAndIDs) {
//console.log(pdfFileNamesAndIDs[i][0]);
if (pdfFileNamesAndIDs[i][0] == fileName) {
documentID = pdfFileNamesAndIDs[i][1];
console.log("documentID: " + documentID);
}
}
var documentFile = DriveApp.getFileById(documentID);
var documentURL = documentFile.getDownloadUrl();
Logger.log("documentURL = "+documentURL);
return documentURL;
}
The Problem:
The URL generated by getPDFfileURL() doesn't work in the html file generated in showModalDialog_downloadFilledPDFform_NAMOFFORM().
The error in Chrome dev console is:
pdf-lib#1.11.0:15 Uncaught (in promise) Error: Failed to parse PDF document (line:0 col:0 offset=0): No PDF header found
at e [as constructor] (pdf-lib#1.11.0:15:189222)
at new e (pdf-lib#1.11.0:15:190065)
at e.parseHeader (pdf-lib#1.11.0:15:401731)
at e.<anonymous> (pdf-lib#1.11.0:15:400782)
at pdf-lib#1.11.0:15:1845
at Object.next (pdf-lib#1.11.0:15:1950)
at pdf-lib#1.11.0:15:887
at new Promise (<anonymous>)
at i (pdf-lib#1.11.0:15:632)
at e.parseDocument (pdf-lib#1.11.0:15:400580)
The basic concept for the html page (shown as a modal dialog box), came from: https://jsfiddle.net/Hopding/0mwfqkv6/3/
The contents of the htmlTemplate are:
<!DOCTYPE html>
<html>
<head>
<base target="_top">
<!-- Add Stylesheet -->
<?!= HtmlService.createHtmlOutputFromFile('downloadFilledPDFformCSS').getContent(); ?>
<!-- Add pdf-lib and downloadjs libraries -->
<!-- https://pdf-lib.js.org/ and https://github.com/rndme/download -->
<!-- https://jsfiddle.net/Hopding/0mwfqkv6/3/ -->
<script src="https://unpkg.com/pdf-lib#1.11.0"></script>
<script src="https://unpkg.com/downloadjs#1.4.7"></script>
</head>
<body>
<h2 id="myTitle"></h2>
<p>Click the button to fill form fields in an the following PDF document: <code id="pdf_template_file">pdf-lib</code></p>
<button onclick="fillForm()">Fill PDF</button>
<p class="small">(Your browser will download the resulting file)</p>
</body>
<script>
const data = <?!= JSON.stringify(dataFromServerTemplate) ?>; //Stores the data directly in the javascript code
function removeExtension(filename) {
return filename.substring(0, filename.lastIndexOf('.')) || filename;
}
const pdf_template_file = data.pdf_template_file;
const pdf_template_file_basename = removeExtension(pdf_template_file);
// sample usage
function initialize() {
document.getElementById("myTitle").innerText = pdf_template_file;
//or use jquery: $("#myTitle").text(data.first + " - " + data.last);
document.getElementById("pdf_template_file").innerText = pdf_template_file;
}
// use onload or use jquery to call your initialization after the document loads
window.onload = initialize;
</script>
<script>
const { PDFDocument } = PDFLib;
async function fillForm() {
// Fetch the PDF with form fields
const formUrl = data.pdf_template_file_url
//const formPdfBytes = await fetch(formUrl).then(res => res.arrayBuffer())
const formPdfBytes = await fetch(formUrl, {
redirect: "follow",
mode: 'no-cors',
method: 'GET',
headers: {
'Content-Type': 'application/pdf',
}
}).then(res => res.arrayBuffer());
// Load a PDF with form fields
const pdfDoc = await PDFDocument.load(formPdfBytes);
// Get the form containing all the fields
const form = pdfDoc.getForm()
// Get all fields in the PDF by their names
const invIDField = form.getTextField('invID')
const makeAndModelField = form.getTextField('makeAndModel')
const nameField = form.getTextField('name')
const addressField = form.getTextField('address')
const phoneNumberField = form.getTextField('phoneNumber')
const emailAddressField = form.getTextField('emailAddress')
const dateField = form.getTextField('date')
// Output file name
const INPUT_FNAME = "AN"
const INPUT_LNAME = "Other"
// Fill in the basic info fields
invIDField.setText()
makeAndModelField.setText()
nameField.setText(INPUT_FNAME + " " + INPUT_LNAME)
addressField.setText()
phoneNumberField.setText()
emailAddressField.setText()
dateField.setText()
// Serialize the PDFDocument to bytes (a Uint8Array)
const pdfBytes = await pdfDoc.save({updateFieldAppearances: false})
const outputPDFfilename = pdf_template_file_basename + "." + INPUT_FNAME + "_" + INPUT_LNAME + ".pdf"
// Trigger the browser to download the PDF document
download(pdfBytes, outputPDFfilename, "application/pdf");
}
</script>
</html>
I have replicated the contents of the html file on my testing webserver. The server has 3 files: index.html, stykesheet.css and form1.pdf
The pdf (on the web server) is the same pdf file that is stored on Google drive.
On my server the following works:
if I use the pdf file that is in the same folder as the html and css files, a filled pdf is offered for download.
...but the following doesn't work:
if I use the same URL that is generated by getPDFfileURL(), nothing happens and no filled pdf is offered for download.
So the question is:
How do I generate the correct URL (for the pdf file stored in Google Drive), so it can then be used by PDF-lib.js (in the htmlTemplate)?
The answer is:
fetch the pdf file from Google drive as raw bytes.
encode the bytes as base64.
pass the base64 string from the GAS function to the htmlTemplate.
This is the function that gets the pdf file and returns it as a base64 encoded string:
function getPDFfileAsBase64() {
var fileId = "";
var url = "https://drive.google.com/uc?id=" + fileId + "&alt=media";
console.log("url: " + url);
var params = {
method: "get",
headers: {
Authorization: "Bearer " + ScriptApp.getOAuthToken(),
},
};
var bytes = UrlFetchApp.fetch(url, params).getContent();
var encoded = Utilities.base64Encode(bytes);
//console.log("encoded: " + encoded);
return encoded;
}
the function to create a modal dialog is:
function showModalDialog_downloadFilledPDFform_form1() {
// Display a modal dialog box with custom HtmlService content.
var pdf_template_file = "form1.pdf";
var pdf_template_file_AsBase64 = getPDFfileAsBase64(pdf_template_file);
var htmlTemplate = HtmlService.createTemplateFromFile('downloadFilledPDFformHTML');
htmlTemplate.dataFromServerTemplate = { pdf_template_file: pdf_template_file, pdf_template_file_AsBase64: pdf_template_file_AsBase64};
var htmlOutput = htmlTemplate.evaluate();
htmlOutput.setWidth(648.1);
htmlOutput.setHeight(286.300)
SpreadsheetApp.getUi().showModalDialog(htmlOutput, 'Download filled PDF');
}
Related
I'm using Flask with one of my wtforms TextAreaFields mapped to Trix-Editor. All works well except for images using the built toolbar attach button.
I'd like to save the images to a directory on the backend and have a link to it in the trix-editor text. I'm saving this to a database.
I can make this work by adding an <input type='file'/>in my template like so:
{{ form.description }}
<trix-editor input="description"></trix-editor>
<input type="file"/>
and the following javascript which I found somewhere as an example.
document.addEventListener('DOMContentLoaded', ()=> {
let contentEl = document.querySelector('[name="description"]');
let editorEl = document.querySelector('trix-editor');
document.querySelector('input[type=file]').addEventListener('change', ({ target })=> {
let reader = new FileReader();
reader.addEventListener('load', ()=> {
let image = document.createElement('img');
image.src = reader.result;
let tmp = document.createElement('div');
tmp.appendChild(image);
editorEl.editor.insertHTML(tmp.innerHTML);
target.value = '';
}, false);
reader.readAsDataURL(target.files[0]);
});
// document.querySelector('[role="dump"]').addEventListener('click', ()=> {
// document.querySelector('textarea').value = contentEl.value;
// });
});
This saves the image embedded in the text. I don't want that because large images will take up a lot of space in the database and slow down loading of the editor when I load this data back into it from the database.
It is also ugly having the extra button when Trix has an attachment button in it's toolbar. So, I'd like to be able to click the toolbar button and have it upload or if that is too hard, have the built in toolbar button save the image embedded.
To save the images to a folder instead of embedded, the Trix-editor website says to use this javascript https://trix-editor.org/js/attachments.js
In this javascript I have to provide a HOST so I use
var HOST = "http://localhost:5000/upload/"
and I set up a route in my flask file:
#tickets.post('/_upload/')
def upload():
path = current_app.config['UPLOAD_DIRECTORY']
if request.method == 'POST':
if 'file' not in request.files:
flash('No file part')
return redirect(request.url)
file = request.files['file']
if file.filename == '':
flash('No selected file')
return redirect(request.url)
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
session["id"] = filename
file.save(os.path.join(path, filename))
return send_from_directory(path, filename)
I can select an image and it shows in the editor and it uploads to the directory on my backend as expected. But when I save the form the location of the image is not in in the document text (should be in there as something like <img src="uploads/image.png>
On the python console I see
"POST /_upload/ HTTP/1.1" 404 -
I can make this go away if I change the return on my route to something like return "200" But all the examples I have seen about uploading files have this or a render_template. I don't want to render a template so I'm using this although I don't really understand what it does.
I'm assuming I need to return something the javasript can use to embed the image link in the document. But I'm a total newbie (like you didn't figure that out already) so I don't know what to do for the return statement (assuming this is where the problem lies).
If anyone else is trying to figure this out this is what I ended up doing.
Still needs a but of tweaking but works.
First I modified the example javascript for uploading to use Fetch instead of XMLHttpRequest
const editor = document.querySelector('trix-editor');
(function() {
HOST = '/_upload/'
addEventListener("trix-attachment-add", function(event) {
if (event.attachment.file) {
uploadFileAttachment(event.attachment)
}
// get rid of the progress bar as Fetch does not support progress yet
// this code originally used XMLHttpRequest instead of Fetch
event.attachment.setUploadProgress(100)
})
function uploadFileAttachment(attachment) {
uploadFile(attachment.file, setAttributes)
function setAttributes(attributes) {
attachment.setAttributes(attributes)
alert(attributes)
}
}
function uploadFile(file, successCallback) {
var key = createStorageKey(file)
var formData = createFormData(key, file)
fetch(HOST, {method: 'POST', body: formData}).then(function(response){
response.json().then(function(data){
alert(data.file, data.status)
if (data.status == 204) {
var attributes = {
url: HOST + key,
href: HOST + key + "?content-disposition=attachment"
}
console.log(attributes)
successCallback(attributes)
}
})
})
}
function createStorageKey(file) {
var date = new Date()
var day = date.toISOString().slice(0,10)
var name = date.getTime() + "-" + file.name
return [day, name ].join("/")
}
function createFormData(key, file) {
var data = new FormData()
data.append("key", key)
data.append("Content-Type", file.type)
data.append("file", file)
return data
}
})();
Then modified my Flask route (which I'll refactor, this was just slapped together to make it work):
def upload():
path = current_app.config['UPLOAD_DIRECTORY']
new_path = request.form["key"].split('/')[0]
file_upload_name = os.path.join(path, request.form["key"])
print(file_upload_name)
upload_path = os.path.join(path, new_path)
if request.method == 'POST':
if 'file' not in request.files:
flash('No file part')
return redirect(request.url)
file = request.files['file']
if file.filename == '':
flash('No selected file')
return redirect(request.url)
if file and allowed_file(file.filename):
if not os.path.exists(upload_path):
os.mkdir(upload_path)
filename = secure_filename(file.filename)
session["id"] = filename
attachment = os.path.join(upload_path, filename)
file.save(attachment)
file.close()
os.rename(attachment, file_upload_name)
print(os.listdir(upload_path))
return jsonify({'file': attachment, 'status': 204})
return f'Nothing to see here'
Anyway, I hope that helps as it took me ages to figure out.
I’m seeking how to output SharePoint Document Library Files to csv file. I found script that get me almost there, but I can’t figure out how to update the code to export the information to a csv file instead to the console.log() or to an alert(). Everything I tried breaks the code. I review other JavaScript concept that shows the how to add out to CSV but I again the script concept breaks the code I’m trying to modify. The script I am using. In addition, the script output the file names. I like to get help on how I can not only output the file name, but I like to output, modified date, created date, and the link to the file. I hope this is possible and I appreciate any help in achieving this concept. Script I'm using follows below.
jQuery(document).ready(function() {
var scriptbase = _spPageContextInfo.webServerRelativeUrl + "/_layouts/15/";
$.getScript(scriptbase + "SP.Runtime.js", function() {
$.getScript(scriptbase + "SP.js", function() {
$.getScript(scriptbase + "SP.DocumentManagement.js", createDocumentSet);
});
});
});
var docSetFiles;
function createDocumentSet() {
//Get the client context,web and library object.
clientContext = new SP.ClientContext.get_current();
oWeb = clientContext.get_web();
var oList = oWeb.get_lists().getByTitle("Fact Sheets & Agreements");
clientContext.load(oList);
//Get the root folder of the library
oLibraryFolder = oList.get_rootFolder();
var documentSetFolder = "sites/nbib/ep/Fact%20Sheets/";
//Get the document set files using CAML query
var camlQuery = SP.CamlQuery.createAllItemsQuery();
camlQuery.set_folderServerRelativeUrl(documentSetFolder);
docSetFiles = oList.getItems(camlQuery);
//Load the client context and execute the batch
clientContext.load(docSetFiles, 'Include(File)');
clientContext.executeQueryAsync(QuerySuccess, QueryFailure);
}
function QuerySuccess() {
//Loop through the document set files and get the display name
var docSetFilesEnumerator = docSetFiles.getEnumerator();
while (docSetFilesEnumerator.moveNext()) {
var oDoc = docSetFilesEnumerator.get_current().get_file();
alert("Document Name : " + oDoc.get_name());
console.log("Document Name : " + oDoc.get_name());
}
}
function QueryFailure() {
console.log('Request failed - ' + args.get_message());
}
Sample test script in chrome.
function QuerySuccess() {
//Loop through the document set files and get the display name
var csv = 'Document Name\n';
var docSetFilesEnumerator = docSetFiles.getEnumerator();
while (docSetFilesEnumerator.moveNext()) {
var oDoc = docSetFilesEnumerator.get_current().get_file();
//alert("Document Name : " + oDoc.get_name());
//console.log("Document Name : " + oDoc.get_name());
csv += oDoc.get_name();//+',' if more cloumns
csv += "\n";
}
var hiddenElement = document.createElement('a');
hiddenElement.href = 'data:text/csv;charset=utf-8,' + encodeURI(csv);
hiddenElement.target = '_blank';
hiddenElement.download = 'DocumentList.csv';
hiddenElement.click();
}
I need to convert HTML to PDF. I have tried with jsPDF and read a lot of questions here on stackoverflow about this. I have tried all the methods that exist, html(), fromHtml, html2pdf and html2canvas. But all of them have various problems. Either missing content, fuzzy content or margins are completely off.
So I am trying a different route. I found following code snippet to convert to word document. And this works.
function exportHTML(){
var header = "<html xmlns:o='urn:schemas-microsoft-com:office:office' "+
"xmlns:w='urn:schemas-microsoft-com:office:word' "+
"xmlns='http://www.w3.org/TR/REC-html40'>"+
"<head><meta charset='utf-8'><title>Export HTML to Word Document with JavaScript</title></head><body>";
var footer = "</body></html>";
var sourceHTML = header+document.getElementById("source-html").innerHTML+footer;
var source = 'data:application/vnd.ms-word;charset=utf-8,' + encodeURIComponent(sourceHTML);
var fileDownload = document.createElement("a");
document.body.appendChild(fileDownload);
fileDownload.href = source;
fileDownload.download = 'document.doc';
fileDownload.click();
document.body.removeChild(fileDownload);
}
However I do not want the word file to be downloaded. I need to capture it and convert it to a base64 string because then I can send it to a rest api that can convert the word document to pdf. That rest api does not support html directly otherwise I would just send the html. Hence the workaround to word then to pdf. ps I cannot use an online pdf solution due to sensitive information, the rest api is an internal service.
However I do not want the word file to be downloaded. I need to capture it and convert it to a base64 string because then I can send it to a rest api that can convert the word document to pdf.
Then no need to insert it into a download link. Just base64 encode the string with btoa:
function exportHTML(){
var header = "<html xmlns:o='urn:schemas-microsoft-com:office:office' "+
"xmlns:w='urn:schemas-microsoft-com:office:word' "+
"xmlns='http://www.w3.org/TR/REC-html40'>"+
"<head><meta charset='utf-8'><title>Export HTML to Word Document with JavaScript</title></head><body>";
var footer = "</body></html>";
var sourceHTML = header+document.getElementById("source-html").innerHTML+footer;
var source = 'data:application/vnd.ms-word;charset=utf-8,' + encodeURIComponent(sourceHTML);
// encode here instead of creating a link
var encoded = window.btoa(source);
return encoded;
}
Then you'll be free to use XMLHttpRequest to send the encoded string to your API endpoint. E.g.:
var encodedString = exportHTML();
var xhr = new XMLHttpRequest();
xhr.open('POST', '/my-conversion-endpoint', true);
xhr.setRequestHeader('Content-type', 'application/x-www-form-urlencoded');
xhr.onreadystatechange = function() {
if(xhr.readyState == 4 && xhr.status == 200) {
// request finished
alert(xhr.responseText);
}
}
xhr.send('encodedString=' + encodedString);
Use "new Blob" by file's construct:
function exportHTML(){
var header = "<html xmlns:o='urn:schemas-microsoft-com:office:office' "+
"xmlns:w='urn:schemas-microsoft-com:office:word' "+
"xmlns='http://www.w3.org/TR/REC-html40'>"+
"<head><meta charset='utf-8'><title>Export HTML to Word Document with JavaScript</title></head><body>";
var footer = "</body></html>";
var sourceHTML = header+document.getElementById("source-html").innerHTML+footer;
var source = 'data:application/vnd.ms-word;charset=utf-8,' + encodeURIComponent(sourceHTML);
//var fileDownload = document.createElement("a");
//document.body.appendChild(fileDownload);
//fileDownload.href = source;
//fileDownload.download = 'document.doc';
//fileDownload.click();
//document.body.removeChild(fileDownload);
var my_file=new Blob([source]);
getBase64(my_file);
}
function getBase64(file) {
var reader = new FileReader();
reader.readAsDataURL(file);
reader.onload = function () {
console.log(reader.result);
};
reader.onerror = function (error) {
console.log('Error: ', error);
};
}
exportHTML();
<div id="source-html">Hi <b>World</b>!</div>
I want to make a form with React and upload pdf files. I've to implement until here but now my app needs to read data from pdf without saving in backend database etc. The whole functionality works as pre-checker.
Any suggestion?
You can use PDF.js to read the content of PDF file using javascript/jQuery. Here is my working example.
$("#file").on("change", function(evt){
var file = evt.target.files[0];
//Read the file using file reader
var fileReader = new FileReader();
fileReader.onload = function () {
//Turn array buffer into typed array
var typedarray = new Uint8Array(this.result);
//calling function to read from pdf file
getText(typedarray).then(function (text) {
/*Selected pdf file content is in the variable text. */
$("#content").html(text);
}, function (reason) //Execute only when there is some error while reading pdf file
{
alert('Seems this file is broken, please upload another file');
console.error(reason);
});
//getText() function definition. This is the pdf reader function.
function getText(typedarray) {
//PDFJS should be able to read this typedarray content
var pdf = PDFJS.getDocument(typedarray);
return pdf.then(function (pdf) {
// get all pages text
var maxPages = pdf.pdfInfo.numPages;
var countPromises = [];
// collecting all page promises
for (var j = 1; j <= maxPages; j++) {
var page = pdf.getPage(j);
var txt = "";
countPromises.push(page.then(function (page) {
// add page promise
var textContent = page.getTextContent();
return textContent.then(function (text) {
// return content promise
return text.items.map(function (s) {
return s.str;
}).join(''); // value page text
});
}));
}
// Wait for all pages and join text
return Promise.all(countPromises).then(function (texts) {
return texts.join('');
});
});
}
};
//Read the file as ArrayBuffer
fileReader.readAsArrayBuffer(file);
});
<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.0.87/pdf.js"></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<body>
<input type="file" id="file" name="file" accept="application/pdf">
<br>
<p id="content"></p>
</body>
I'm using a script to extract data from google search console in a sheet.
I built a sidebar to chose on which website the user want to analyse his data.
For that i have a function that can list all sites link to the google account, but i have an error when i try to execute this function in my html file.
I use withSuccessHandler(function) method which sets a callback function to run if the server-side function returns successfully. (i have a OAuth2.0.gs file where is my getService function.
The error is "service.hasAccess is not a function at listAccountSites" where listAccountSites is my function. Here's an extract of my html file:
<script src="OAuth2.0.gs"></script>
<script src="//ajax.googleapis.com/ajax/libs/jquery/1.9.1/jquery.min.js">
</script>
<script>
$(function() {
var liste = google.script.run.withSuccessHandler(listAccountSites)
.getService();
console.log(liste);
});
function listAccountSites(service){
if (service.hasAccess()) {
var apiURL = "https://www.googleapis.com/webmasters/v3/sites";
var headers = {
"Authorization": "Bearer " + getService().getAccessToken()
};
var options = {
"headers": headers,
"method" : "GET",
"muteHttpExceptions": true
};
var response = UrlFetchApp.fetch(apiURL, options);
var json = JSON.parse(response.getContentText());
Logger.log(json)
console.log('if')
var URLs = []
for (var i in json.siteEntry) {
URLs.push([json.siteEntry[i].siteUrl, json.siteEntry[i].permissionLevel]);
}
/*
newdoc.getRange(1,1).setValue('Sites');
newdoc.getRange(1,3).setValue('URL du site à analyser');
newdoc.getRange(2,1,URLs.length,1).setValues(URLs);
*/
console.log(URLs);
} else {
console.log('else')
var authorizationUrl = service.getAuthorizationUrl();
Logger.log('Open the following URL and re-run the script: %s', authorizationUrl);
Browser.msgBox('Open the following URL and re-run the script: ' + authorizationUrl);
}
return URLs;
}
</script>
i found the solution.
Jquery is useless here, you just have to use google.script.run.yourfunction() to run your gs. function on your html sidebar.