PDF2PPT（Images） and PPT2PDF

 1. pdf转图片及pptx

# -*- coding: utf-8 -*-
from pptx import Presentation
from pdf2image import convert_from_path, convert_from_bytes
from pdf2image.exceptions import (
    PDFInfoNotInstalledError,
    PDFPageCountError,
    PDFSyntaxError
)
from sys import argv
from PIL import Image
from pptx.enum.shapes import MSO_SHAPE
from pptx.util import Inches, Pt
from pptx.dml.color import RGBColor
from pathlib import Path

fff=argv[1]
pp=Path.cwd()
fn=fff+'.pdf'
filename=pp/fn
print(filename)
print("Creating %s" % fff)
prs = Presentation()
width,height=argv[3].split('*')
prs.slide_width = Inches(16)
prs.slide_height = Inches(9)
print(argv[2],width,height)
pages = convert_from_path(filename,dpi=int(argv[2]), size=(int(width)*100,int(height)*100))
jpgs=pp/'jpgs'
if not jpgs.exists():
    jpgs.mkdir()
for index, page in enumerate(pages):
    name=fff+"-(%d).png" % index
    jpg_file =jpgs/name
#    print(jpg_file)
    page.save(jpg_file, 'PNG')


    image = Image.open(jpg_file)
    height = image.height
    width = image.width
#
    if height > width:
        adjusted = image.rotate(270, expand=True)
        adjusted.save(jpg_file)
#
#
    title_slide_layout = prs.slide_layouts[6]
    slide = prs.slides.add_slide(title_slide_layout)
    left = top = 0
    jpg_file=str(jpg_file)
    print(jpg_file)
    slide.shapes.add_picture(jpg_file, left,top,height = prs.slide_height)



pptname='%s.pptx' % fff
prs.save(pp/pptname)
print("Saved")

#use

2. 批量ppt转pdf

import comtypes.client
import os

def init_powerpoint():
   powerpoint = comtypes.client.CreateObject("Powerpoint.Application")
   powerpoint.Visible = 1
   return powerpoint

def ppt_to_pdf(powerpoint, inputFileName, outputFileName, formatType = 32):
   if outputFileName[-3:] != 'pdf':
       outputFileName = outputFileName + ".pdf"
   deck = powerpoint.Presentations.Open(inputFileName)
   deck.SaveAs(outputFileName, formatType) # formatType = 32 for ppt to pdf
   deck.Close()

def convert_files_in_folder(powerpoint, folder):
   files = os.listdir(folder)
   pptfiles = [f for f in files if f.endswith((".ppt", ".pptx"))]
   for pptfile in pptfiles:
       fullpath = os.path.join(cwd, pptfile)
       ppt_to_pdf(powerpoint, fullpath, fullpath)

if __name__ == "__main__":
   powerpoint = init_powerpoint()
   cwd = os.getcwd()
   convert_files_in_folder(powerpoint, cwd)
   powerpoint.Quit()

其中可能会出现：Windows 安装pdf2image运行后遇到PDFInfoNotInstalledError解决办法

安装pdf2image，安装没有报错，运行之后报错：

pdf2image.exceptions.PDFInfoNotInstalledError: Unable to get page count. Is poppler installed and in PATH?

一开始是想直接安装PDFInfo，或者poppler，但是都安装失败。按照网友提示安装python-poppler也因为ndk版本不对失败。

最终解决办法：
1、首先通过poppler-windows下载地址下载压缩包

2、然后解压到自定义文件目录，随后添加到环境变量。

3、最后就是更改安装包内的pdf2image.py文件中的poppler路径
 

def convert_from_path(
    pdf_path,
    dpi=200,
    output_folder=None,
    first_page=None,
    last_page=None,
    fmt="ppm",
    jpegopt=None,
    thread_count=1,
    userpw=None,
    use_cropbox=False,
    strict=False,
    transparent=False,
    single_file=False,
    output_file=uuid_generator(),
    poppler_path=r'D:\poppler-0.68.0\bin',  #将这里改为你解压安装的poppler路径
    grayscale=False,
    size=None,
    paths_only=False,
    use_pdftocairo=False,
    timeout=None,

 保存即可。

==左手代码，右手写诗==