###### tags: `python`

# python讀取/修改PDF

## 安裝

pip3 install pikepdf

## 複製pdf檔

from pikepdf import Pdf

sample_pdf = Pdf.open('Python連結Arduino.pdf')
sample_pdf.save('sample2.pdf')

## 取得pdf檔總頁數

from pikepdf import Pdf

pdf = Pdf.open('Python連結Arduino.pdf')
print(len(pdf.pages))

## 倒轉pdf內容（以頁為單位）

from pikepdf import Pdf

pdf = Pdf.open('Python連結Arduino.pdf')

pdf.pages.reverse()
pdf.save('sample3.pdf')

## 刪除pdf某幾頁的內容

from pikepdf import Pdf

pdf = Pdf.open('Python連結Arduino.pdf')
del pdf.pages[1:3]
pdf.save('sample3.pdf')

## 合併其他pdf檔的內容(所有檔案內容合併到最後面）

from pikepdf import Pdf

pdf1 = Pdf.open('Python連結Arduino.pdf')
pdf2 = Pdf.open('頭頸癌食譜.pdf')

pdf1.pages.extend(pdf2.pages) # 插入所有內容
pdf1.save('sample3.pdf')

pdf1.pages.extend(pdf2.pages[1:2]) # 只插入第2頁的內容
pdf1.save('sample4.pdf')

## 合併指定頁數到指定位置之後

from pikepdf import Pdf

pdf1 = Pdf.open('Python連結Arduino.pdf')
pdf2 = Pdf.open('頭頸癌食譜.pdf')

pdf1.pages.insert(1, pdf2.pages[0])

pdf1.save('sample3.pdf')

## 以檔案2指定的頁碼內容取代檔案1指定的頁碼內容

from pikepdf import Pdf

pdf1 = Pdf.open('Python連結Arduino.pdf')
pdf2 = Pdf.open('頭頸癌食譜.pdf')


pdf1.pages[2] = pdf2.pages[1]
pdf1.save('sample3.pdf')

## 拆解pdf檔成多個pdf檔

from pikepdf import Pdf

pdf = Pdf.open('Python連結Arduino.pdf')

for n, page in enumerate(pdf.pages):
    dst = Pdf.new()
    dst.pages.append(page)
    dst.save('{:02d}.pdf'.format(n))

---------
## 顯示pdf檔內某一頁的內容

from pikepdf import Pdf

pdf = Pdf.open('Python連結Arduino.pdf')

page = pdf.pages[0]
print(page.__str__)

## word to pdf

import sys
import os
import comtypes.client

wdFormatPDF = 17
 
in_file = "test.docx"
out_file = "test.pdf"
 
def docx2pdf(in_file, out_file):
    word = comtypes.client.CreateObject('Word.Application')
    doc = word.Documents.Open(in_file)
    doc.SaveAs(out_file, FileFormat=wdFormatPDF)
    doc.Close()
    word.Quit()
    
docx2pdf(in_file, out_file)