Huge News!Announcing our $40M Series B led by Abstract Ventures.Learn More
Socket
Sign inDemoInstall
Socket

github.com/dslipak/pdf

Package Overview
Dependencies
Alerts
File Explorer
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

github.com/dslipak/pdf

  • v0.0.2
  • Source
  • Go
  • Socket score

Version published
Created
Source

PDF Reader

A simple Go library which enables reading PDF files.

This repository contains merged code from https://github.com/rsc/pdf and https://github.com/ledongthuc/pdf

Features

  • Get plain text content (without formatting)
  • Get Content (including all font and formatting information)

Install:

go get -u github.com/dslipak/pdf

Read plain text

package main

import (
	"bytes"
	"fmt"

	"github.com/dslipak/pdf"
)

func main() {
	pdf.DebugOn = true
	content, err := readPdf("test.pdf") // Read local pdf file
	if err != nil {
		panic(err)
	}
	fmt.Println(content)
	return
}

func readPdf(path string) (string, error) {
	f, r, err := pdf.Open(path)
	// remember close file
    defer f.Close()
	if err != nil {
		return "", err
	}
	var buf bytes.Buffer
    b, err := r.GetPlainText()
    if err != nil {
        return "", err
    }
    buf.ReadFrom(b)
	return buf.String(), nil
}

Read all text with styles from PDF

func readPdf2(path string) (string, error) {
	f, r, err := pdf.Open(path)
	// remember close file
	defer f.Close()
	if err != nil {
		return "", err
	}
	totalPage := r.NumPage()

	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
		p := r.Page(pageIndex)
		if p.V.IsNull() {
			continue
		}
		var lastTextStyle pdf.Text
		texts := p.Content().Text
		for _, text := range texts {
			if isSameSentence(text, lastTextStyle) {
				lastTextStyle.S = lastTextStyle.S + text.S
			} else {
				fmt.Printf("Font: %s, Font-size: %f, x: %f, y: %f, content: %s \n", lastTextStyle.Font, lastTextStyle.FontSize, lastTextStyle.X, lastTextStyle.Y, lastTextStyle.S)
				lastTextStyle = text
			}
		}
	}
	return "", nil
}

Read text grouped by rows

package main

import (
	"fmt"
	"os"

	"github.com/dslipak/pdf"
)

func main() {
	content, err := readPdf(os.Args[1]) // Read local pdf file
	if err != nil {
		panic(err)
	}
	fmt.Println(content)
	return
}

func readPdf(path string) (string, error) {
	f, r, err := pdf.Open(path)
	defer func() {
		_ = f.Close()
	}()
	if err != nil {
		return "", err
	}
	totalPage := r.NumPage()

	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
		p := r.Page(pageIndex)
		if p.V.IsNull() {
			continue
		}

		rows, _ := p.GetTextByRow()
		for _, row := range rows {
		    println(">>>> row: ", row.Position)
		    for _, word := range row.Content {
		        fmt.Println(word.S)
		    }
		}
	}
	return "", nil
}

FAQs

Package last updated on 24 Jan 2024

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts

SocketSocket SOC 2 Logo

Product

  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap
  • Changelog

Packages

npm

Stay in touch

Get open source security insights delivered straight into your inbox.


  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc