小工具 - Python图片转PDF文件

前言

主要整理记载一些python实现的小脚本，网上基本转换要会员，懒得搞了，这个一键生成，可以打包成exe文件使用

单张图片转换成pdf、图片批量转换成pdf

python 复制代码

# coding = UTF-8
import os
from io import BytesIO
from PIL import Image


os.environ['NLS_LANG'] = 'SIMPLIFIED CHINESE_CHINA.UTF8'  # 防止中文乱码
SUPPORT_SUFFIX = ["jpg", "jpeg", "png"]  # 支持的图片文件格式


def pic_to_pdf(image_bytes: bytes) -> bytes:
    """将单个图片转换为单张PDF

    :param image_bytes: 图片的bytes对象
    :return: PDF的bytes对象
    """
    # 将bytes对象转换为BytesIO对象
    image_bytes_io = BytesIO(image_bytes)
    # 从内存中读取图片
    image_object = Image.open(image_bytes_io)
    # 打开内存中的文件用于保存PDF
    with BytesIO() as result_bytes_io:
        # 将图片保存为单张PDF
        image_object.save(result_bytes_io, "PDF", resolution=100.0)
        # 获取内存中的文件
        data = result_bytes_io.getvalue()
    # 返回PDF的bytes对象
    return data


def batch_convert(image_path: str, pdf_path: str) -> None:
    """批量将图片转换为单张PDF

    :param image_path: 图片的文件夹
    :param pdf_path: PDF文件保存的文件夹
    """
    # 遍历文件夹下所有文件
    for root, dirs, files in os.walk(image_path, topdown=False):
        for name in files:
            # 提取文件的后缀名
            file_suffix = os.path.splitext(name)[-1].lstrip(".").lower()
            # 检测该文件格式是否受到支持
            if file_suffix not in SUPPORT_SUFFIX:
                continue
            # 拼接出图片文件的绝对路径
            source_file_path = os.path.join(root, name)
            # 拼接出PDF文件的绝对路径
            target_file_path = os.path.join(pdf_path, f"{os.path.splitext(name)[0]}.pdf")
            # 将图片文件转换为PDF文件
            with open(source_file_path, "rb") as source:
                with open(target_file_path, "wb") as target:
                    target.write(pic_to_pdf(source.read()))


# pic_to_pdf('E:\银登中心pdf\\f1669413880707_0.jpg')
batch_convert('E:\pdf\\f1669413880707', 'E:\pdf\\f1669413880707')

多张图片合并为1个pdf文件

python 复制代码

import os
import re
import time

import PIL.ExifTags
import PIL.Image
from reportlab.lib.pagesizes import A4
from reportlab.lib.utils import ImageReader
from reportlab.pdfgen import canvas
from reportlab.platypus import Image


def img_search(mypath, filenames):
    for lists in os.listdir(mypath):
        path = os.path.join(mypath, lists)
        if os.path.isfile(path):
            expression = r'[\w]+\.(jpg|png|jpeg)$'
            if re.search(expression, path, re.IGNORECASE):
                filenames.append(path)
        elif os.path.isdir(path):
            img_search(path, filenames)


def img_search1(mypath, filenames):
    for lists in os.listdir(mypath):
        path = os.path.join(mypath, lists)
        if os.path.isfile(path):
            a = path.split('.')
            if a[-1] in ['jpg', 'png', 'JPEG']:
                filenames.append(path)
        elif os.path.isdir(path):
            img_search1(path, filenames)


def rotate_img_to_proper(image):
    try:
        # image = Image.open(filename)
        if hasattr(image, '_getexif'):  # only present in JPEGs
            for orientation in PIL.ExifTags.TAGS.keys():
                if PIL.ExifTags.TAGS[orientation] == 'Orientation':
                    break
            e = image._getexif()  # returns None if no EXIF data
            if e is not None:
                # log.info('EXIF data found: %r', e)
                exif = dict(e.items())
                orientation = exif[orientation]
                # print('found, ',orientation)

                if orientation == 3:
                    image = image.transpose(Image.ROTATE_180)
                elif orientation == 6:
                    image = image.transpose(Image.ROTATE_270)
                elif orientation == 8:
                    image = image.rotate(90, expand=True)
    except:
        pass
    return image


def main(src_folder=None):
    output_file_name = 'E:\pdf\\f1671228232790.pdf'
    # save_file_name = 'ex.pdf'
    # doc = SimpleDocTemplate(save_file_name, pagesize=A1,
    #                     rightMargin=72, leftMargin=72,
    #                     topMargin=72, bottomMargin=18)
    imgDoc = canvas.Canvas(output_file_name)  # pagesize=letter
    imgDoc.setPageSize(A4)
    document_width, document_height = A4
    if src_folder is None:
        mypath = input('Input the image folder please:')
    else:
        mypath = src_folder
    filenames = []
    start = time.perf_counter()
    img_search(mypath, filenames)
    end = time.perf_counter()
    print('find file cost time: ', end - start, 'find files: ', len(filenames))
    # for f in filenames:
    #     print(f)
    for image in filenames:
        try:
            image_file = PIL.Image.open(image)
            image_file = rotate_img_to_proper(image_file)

            image_width, image_height = image_file.size
            print('img size:', image_file.size)
            if not (image_width > 0 and image_height > 0):
                raise Exception
            image_aspect = image_height / float(image_width)
            # Determins the demensions of the image in the overview
            print_width = document_width
            print_height = document_width * image_aspect
            imgDoc.drawImage(ImageReader(image_file), document_width - print_width,
                             document_height - print_height, width=print_width,
                             height=print_height, preserveAspectRatio=True)
            # inform the reportlab we want a new page
            imgDoc.showPage()
        except Exception as e:
            print('error:', e, image)
    imgDoc.save()
    print('Done')


if __name__ == '__main__':
    main(src_folder='E:\pdf\\f1671228232790')