https://embedded-workflow-builder.netlify.app/assets/js/0494f2c4.3c9f1295.js

1"use strict";(self.webpackChunkembedded_workflow_builder_docs=self.webpackChunkembedded_workflow_builder_docs||[]).push([["1274"],{67976(e,n,t){t.r(n),t.d(n,{metadata:()=>r,default:()=>x,frontMatter:()=>i,contentTitle:()=>a,toc:()=>h,assets:()=>c});var r=JSON.parse('{"id":"connectors/pdf","title":"PDF Connector","description":"Search and extract data from PDF documents","source":"@site/docs/connectors/pdf.md","sourceDirName":"connectors","slug":"/connectors/pdf","permalink":"/connectors/pdf","draft":false,"unlisted":false,"tags":[],"version":"current","frontMatter":{"title":"PDF Connector","sidebar_label":"PDF","description":"Search and extract data from PDF documents"},"sidebar":"docs","previous":{"title":"Paylocity","permalink":"/connectors/paylocity"},"next":{"title":"PDQ","permalink":"/connectors/pdq"}}'),s=t(74848),d=t(28453);let i={title:"PDF Connector",sidebar_label:"PDF",description:"Search and extract data from PDF documents"},a,c={},h=[{value:"Actions",id:"actions",level:2},{value:"Extract All Text",id:"extractalltext",level:3},{value:"Extract Page",id:"extractpage",level:3},{value:"Extract Page Text",id:"extractpagetext",level:3},{value:"Extract Structured Text",id:"extractstructuredtext",level:3},{value:"Extract Table Data",id:"extracttabledata",level:3},{value:"Extract Text by Pattern",id:"extracttextbypattern",level:3},{value:"Extract Text with Layout",id:"extracttextwithlayout",level:3},{value:"Find Pattern",id:"findpattern",level:3},{value:"Find Text Position",id:"findtextposition",level:3}

1,{value:"Page Numbers",id:"pagenumbers",level:3}];function l(e){let n={h2:"h2",h3:"h3",img:"img",p:"p",strong:"strong",table:"table",tbody:"tbody",td:"td",th:"th",thead:"thead",tr:"tr",...(0,d.R)(),...e.components};return(0,s.jsxs)(s.Fragment,{children:[(0,s.jsxs)(n.p,{children:[(0,s.jsx)(n.img,{alt:"PDF",src:t(10379).A+"#connector-icon",width:"32",height:"32"}),"\nPDF (Portable Document Format) is a file format developed by Adobe for presenting documents independently of software, hardware, or operating systems.\nThe ",(0,s.jsx)(n.strong,{children:"pdf"})," component allows finding text in PDF documents, listing page numbers, and extracting specific pages from a document."]}),"\n",(0,s.jsx)(n.h2,{id:"actions",children:"Actions"}),"\n",(0,s.jsx)(n.h3,{id:"extractalltext",children:"Extract All Text"}),"\n",(0,s.jsx)(n.p,{children:"Extracts all text from the specified PDF document and returns it as an array of text strings."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsx)(n.tbody,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]})})]}),"\n",(0,s.jsx)(n.h3,{id:"extractpage",children:"Extract Page"}),"\n",(0,s.jsx)(n.p,{children:"Extracts the specified page from the PDF document and returns it as a new separate PDF document."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page Number"}),(0,s.jsx)(n.td,{children:"The page number to extract from the PDF."}),(0,s.jsx)(n.td,{})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"extractpagetext",children:"Extract Page Text"}),"\n",(0,s.jsx)(n.p,{children:"Extracts text from the specified page range in the PDF document."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page Start"}),(0,s.jsx)(n.td,{children:"The starting page number for extraction."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page End"}),(0,s.jsx)(n.td,{children:"The ending page number for extraction. If not provided, only the start page is extracted."}),(0,s.jsx)(n.td,{})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"extractstructuredtext",children:"Extract Structured Text"}),"\n",(0,s.jsx)(n.p,{children:"Extracts all text items from the PDF with their position coordinates, dimensions, font metadata, and layout flags for custom parsing."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page Start"}),(0,s.jsx)(n.td,{children:"The starting page number for extraction. If not provided, extraction starts from the first page."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page End"}),(0,s.jsx)(n.td,{children:"The ending page number for extraction. If not provided, extraction continues to the last page."}),(0,s.jsx)(n.td,{})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"extracttabledata",children:"Extract Table Data"}),"\n",(0,s.jsx)(n.p,{children:"Detects and extracts tabular structures from the PDF using coordinate-based row and column clustering, returning two-dimensional string arrays."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Row Tolerance"}),(0,s.jsx)(n.td,{children:"Y-coordinate tolerance in PDF points for grouping text items into table rows. Default is 3 points."}),(0,s.jsx)(n.td,{children:"3"})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Column Tolerance"}),(0,s.jsx)(n.td,{children:"X-coordinate tolerance in PDF points for detecting table column boundaries. Default is 10 points. Decrease for dense tables, increase for tables with wider spacing."}),(0,s.jsx)(n.td,{children:"10"})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page Start"}),(0,s.jsx)(n.td,{children:"The starting page number for extraction. If not provided, extraction starts from the first page."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page End"}),(0,s.jsx)(n.td,{children:"The ending page number for extraction. If not provided, extraction continues to the last page."}),(0,s.jsx)(n.td,{})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"extracttextbypattern",children:"Extract Text by Pattern"}),"\n",(0,s.jsx)(n.p,{children:"Extracts text from the specified PDF document that matches the search text."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Search Pattern"}),(0,s.jsx)(n.td,{children:"This is the text to search for in the PDF document."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Characters After"}),(0,s.jsx)(n.td,{children:"The number of characters to extract after the search pattern. If not provided, the entire page is returned."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Case Sensitive"}),(0,s.jsx)(n.td,{children:"When true, the search is case-sensitive."}),(0,s.jsx)(n.td,{children:"false"})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"extracttextwithlayout",children:"Extract Text with Layout"}),"\n",(0,s.jsx)(n.p,{children:"Extracts text from the PDF with line breaks and paragraph spacing preserved from the original document layout."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Line Tolerance"}),(0,s.jsx)(n.td,{children:"Y-coordinate tolerance in PDF points for grouping text items into lines. Items within this vertical distance are considered same-line. Default is 2 points. Increase for PDFs with inconsistent text positioning."}),(0,s.jsx)(n.td,{children:"2"})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page Start"}),(0,s.jsx)(n.td,{children:"The starting page number for extraction. If not provided, extraction starts from the first page."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page End"}),(0,s.jsx)(n.td,{children:"The ending page number for extraction. If not provided, extraction continues to the last page."}),(0,s.jsx)(n.td,{})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"findpattern",children:"Find Pattern"}),"\n",(0,s.jsx)(n.p,{children:"Searches the PDF document and returns page numbers containing text that matches the search criteria."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Search Pattern"}

1),(0,s.jsx)(n.td,{children:"The text pattern to search for in the PDF document."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Case Sensitive"}),(0,s.jsx)(n.td,{children:"When true, the search is case-sensitive."}),(0,s.jsx)(n.td,{children:"false"})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Use Regex"}),(0,s.jsx)(n.td,{children:"When true, treats the search pattern as a regular expression."}),(0,s.jsx)(n.td,{children:"false"})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Contains"}),(0,s.jsx)(n.td,{children:"When true, returns pages containing the pattern; when false, returns pages without the pattern."}),(0,s.jsx)(n.td,{children:"true"})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"findtextposition",children:"Find Text Position"}),"\n",(0,s.jsx)(n.p,{children:"Searches the PDF document and returns the position coordinates of all occurrences of the specified text."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsxs)(n.tbody,{children:[(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Search Text"}),(0,s.jsx)(n.td,{children:"The text to search for in the PDF document."}),(0,s.jsx)(n.td,{})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Case Sensitive"}),(0,s.jsx)(n.td,{children:"When true, the search is case-sensitive."}),(0,s.jsx)(n.td,{children:"false"})]}),(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"Page Number"}),(0,s.jsx)(n.td,{children:"Limit the search to a specific page number. If not provided, all pages are searched."}),(0,s.jsx)(n.td,{})]})]})]}),"\n",(0,s.jsx)(n.h3,{id:"pagenumbers",children:"Page Numbers"}),"\n",(0,s.jsx)(n.p,{children:"Returns a sequence of page numbers for the PDF document, from 1 to the last page."}),"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",(0,s.jsxs)(n.table,{children:[(0,s.jsx)(n.thead,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.th,{children:"Input"}),(0,s.jsx)(n.th,{children:"Comments"}),(0,s.jsx)(n.th,{children:"Default"})]})}),(0,s.jsx)(n.tbody,{children:(0,s.jsxs)(n.tr,{children:[(0,s.jsx)(n.td,{children:"PDF Data"}),(0,s.jsx)(n.td,{children:"The PDF file data to process. This can be a file reference from a previous step."}),(0,s.jsx)(n.td,{})]})})]})]})}function x(e={}){let{wrapper:n}={...(0,d.R)(),...e.components};return n?(0,s.jsx)(n,{...e,children:(0,s.jsx)(l,{...e})}):l(e)}},10379(e,n,t){t.d(n,{A:()=>r});let r="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAACXBIWXMAABcRAAAXEQHKJvM/AAAFEUlEQVRYhbVXWXMbRRDexE+JHV+KLXln1tOzNvEtX4GiIFVOuP4BL1D4FSqG8CcoH

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"},28453(e,n,t){t.d(n,{R:()=>i,x:()=>a});var r=t(96540);let s={},d=r.createContext(s);function i(e){let n=r.useContext(d);return r.useMemo(function(){return"function"==typeof e?e(n):{...n,...e}},[n,e])}function a(e){let n;return n=e.disableParentContext?"function"==typeof e.components?e.components(s):e.components||s:i(e.components),r.createElement(d.Provider,{value:n},e.children)}}}]);