Go处理PDF的实现代码

## 将一个静态html页面打印成pdf
$ wkhtmltopdf input.html output.pdf

## 将一个网页打印成pdf
$ wkhtmltopdf https://www.google.com output.pdf

$ wkhtmltopdf --help
...
--post <name> <value>      Add an additional post field (repeatable)
...

$ wkhtmltopdf --run-script "javascript:(function(){document.getElementsByClassName('dom_class_name')[0].style.display = 'none'}())" page input.html output.pdf

package main

import (
  "context"
  "io/ioutil"

  "github.com/chromedp/cdproto/page"
  "github.com/chromedp/chromedp"
  "errors"
)

func main(){
  err := ChromedpPrintPdf("https://www.google.com", "/path/to/file.pdf")
  if err != nil {
    fmt.Println(err)
    return
  }
}

func ChromedpPrintPdf(url string, to string) error {
  ctx, cancel := chromedp.NewContext(context.Background())
  defer cancel()

  var buf []byte
  err := chromedp.Run(ctx, chromedp.Tasks{
    chromedp.Navigate(url),
    chromedp.WaitReady("body"),
    chromedp.ActionFunc(func(ctx context.Context) error {
      var err error
      buf, _, err = page.PrintToPDF().
        Do(ctx)
      return err
    }),
  })
  if err != nil {
    return fmt.Errorf("chromedp Run failed,err:%+v", err)
  }

  if err := ioutil.WriteFile(to, buf, 0644); err != nil {
    return fmt.Errorf("write to file failed,err:%+v", err)
  }

  return nil
}

$ unipdf -h
...
Available Commands:
 decrypt   Decrypt PDF files
 encrypt   Encrypt PDF files
 explode   Explodes the input file into separate single page PDF files
 extract   Extract PDF resources
 form    PDF form operations
 grayscale  Convert PDF to grayscale
 help    Help about any command
 info    Output PDF information
 merge    Merge PDF files
 optimize  Optimize PDF files
 passwd   Change PDF passwords
 rotate   Rotate PDF file pages
 search   Search text in PDF files
 split    Split PDF files
 version   Output version information and exit
 watermark  Add watermark to PDF files
...

$ unipdf watermark in.pdf watermark.png -o out.pdf

Watermark successfully applied to in.pdf
Output file saved to out.pdf

$ pdfcpu help
...
The commands are:

  attachments list, add, remove, extract embedded file attachments
  changeopw  change owner password
  changeupw  change user password
  decrypt   remove password protection
  encrypt   set password protection
  extract   extract images, fonts, content, pages, metadata
  fonts    install, list supported fonts
  grid    rearrange pages or images for enhanced browsing experience
  import   import/convert images to PDF
  info    print file info
  merge    concatenate 2 or more PDFs
  nup     rearrange pages or images for reduced number of pages
  optimize  optimize PDF by getting rid of redundant page resources
  pages    insert, remove selected pages
  paper    print list of supported paper sizes
  permissions list, set user access permissions
  rotate   rotate pages
  split    split multi-page PDF into several PDFs according to split span
  stamp    add, remove, update text, image or PDF stamps for selected pages
  trim    create trimmed version of selected pages
  validate  validate PDF against PDF 32000-1:2008 (PDF 1.7)
  version   print version
  watermark  add, remove, update text, image or PDF watermarks for selected pages
...

$ pdfcpu watermark add -mode image 'voucher_watermark.png' 's:1 abs, rot:0' in.pdf out.pdf

package main

import (
  "github.com/pdfcpu/pdfcpu/pkg/api"
  "github.com/pdfcpu/pdfcpu/pkg/pdfcpu"
)

func main() {
  onTop := false
  wm, _ := pdfcpu.ParseImageWatermarkDetails("watermark.png", "s:1 abs, rot:0", onTop)
  api.AddWatermarksFile("in.pdf", "out.pdf", nil, wm, nil)
}

$ cpdf -merge input1.pdf input2.pdf -o output.pdf

$ unipdf merge output.pdf input1.pdf input2.pdf

$ pdfcpu merge output.pdf input1.pdf input2.pdf

## 逐页拆分成单个pdf
$ cpdf -split in.pdf 1 even -chunk 1 -o ./out%%%.pdf

## 将第一页拆分出来
$ unipdf split input.pdf out.pdf 1-1

$ pdfcpu split in.pdf .

$ pdfdraw -o out%d.png in.pdf

## 使用pdftopng将pdf转换成png
$ pdftopng in.pdf out-prefix

$ qpdf --decrypt in.pdf out.pdf

$ pdfcpu decrypt encrypted.pdf output.pdf

$ unipdf decrypt -p pass -o output.pdf input.pdf

$ pdftotext input.pdf output.txt

$ unipdf extract text input.pdf

## 输入一组坐标，即可按照坐标解析pdf中的数据
$ tet --pageopt "includebox={{38 707.93 243.91 716.93}}" input.pdf

$ tet --tetml input.pdf

import (
  "fmt"
  "github.com/rsc.io/pdf"
)

func main() {
  filePath := "path/to/your/broken.pdf"
  _, err := pdf.Open(filePath)
  if err != nil {
    fmt.Println("open pdf failed,err:", err.Error())
    return
  }
}

$ pdfclean broken.pdf repaired.pdf

+ pdf/pdf_xref.c:160: pdf_read_trailer(): cannot recognize xref format: '%'
| pdf/pdf_xref.c:481: pdf_load_xref(): cannot read trailer
\ pdf/pdf_xref.c:537: pdf_open_xref_with_stream(): trying to repair

$ pdffonts input.pdf
name                 type       encoding     emb sub uni object ID
------------------------------------ ----------------- ---------------- --- --- --- ---------
NimbusSanL-Regu           CID TrueType   Identity-H    yes no yes   10 0
NimbusSanL-Bold           CID TrueType   Identity-H    yes no yes   20 0