腾讯会议截图自动去除黑边转PDF

python 复制代码

import cv2
import numpy as np
from PIL import Image
import os
from reportlab.lib.pagesizes import A4, landscape
from reportlab.pdfgen import canvas

def crop_by_white_contour(img_path, save_path):
    # 用PIL读取，解决中文路乱码问题
    pil_img = Image.open(img_path).convert("RGB")
    img = np.array(pil_img)
    # PIL是RGB，OpenCV需要BGR
    img_bgr = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
    gray = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY)

    # 二值化：白色区域255，深色背景0
    _, binary = cv2.threshold(gray, 60, 255, cv2.THRESH_BINARY)
    contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # 取面积最大轮廓=PPT主体白色区域
    max_contour = max(contours, key=cv2.contourArea)
    x_min, y_min, w, h = cv2.boundingRect(max_contour)
    x_max = x_min + w
    y_max = y_min + h

    # 裁剪
    crop_array = img[y_min:y_max, x_min:x_max]
    crop_pil = Image.fromarray(crop_array)
    crop_pil.save(save_path)

def batch_screenshot_to_pdf(folder, pdf_name="PPT无黑边汇总.pdf"):
    ext = (".jpg", ".jpeg", ".png", ".bmp")
    file_list = sorted([f for f in os.listdir(folder) if f.lower().endswith(ext)])
    if not file_list:
        print("❌ 文件夹内未找到图片文件")
        return

    temp_dir = os.path.join(folder, "crop_temp_clean")
    os.makedirs(temp_dir, exist_ok=True)
    crop_paths = []

    print("===== 轮廓识别裁剪，清除全部四周黑边 =====")
    for idx, fname in enumerate(file_list):
        src = os.path.join(folder, fname)
        dst = os.path.join(temp_dir, f"fixed_{idx:03d}_{fname}")
        try:
            crop_by_white_contour(src, dst)
            crop_paths.append(dst)
            print(f"✅ 处理完成：{fname}")
        except Exception as e:
            print(f"⚠️ {fname} 处理异常，跳过：{str(e)}")

    # 生成自适应横竖PDF
    pdf = canvas.Canvas(pdf_name)
    page_margin = 15
    print("\n===== 生成横版自适应PDF =====")
    for pic_p in crop_paths:
        pic = Image.open(pic_p)
        pw, ph = pic.size
        # 宽图自动A4横向
        if pw > ph:
            page_w, page_h = landscape(A4)
        else:
            page_w, page_h = A4
        pdf.setPageSize((page_w, page_h))

        max_w = page_w - page_margin * 2
        max_h = page_h - page_margin * 2
        scale = min(max_w / pw, max_h / ph)
        draw_w = pw * scale
        draw_h = ph * scale

        x = (page_w - draw_w) / 2
        y = (page_h - draw_h) / 2
        pdf.drawImage(pic_p, x, y, width=draw_w, height=draw_h)
        pdf.showPage()

    pdf.save()
    print(f"\n🎉 PDF生成完毕，路径：{os.path.abspath(pdf_name)}")

if __name__ == "__main__":
    WORK_FOLDER = r"./"
    batch_screenshot_to_pdf(WORK_FOLDER)

该代码实现了一个批量处理PPT截图并生成PDF的工具。主要功能包括：1) 通过轮廓识别自动裁剪图片四周的黑边，保留PPT主体白色区域；2) 批量处理文件夹中的图片文件（支持JPG/PNG等格式）；3) 智能判断图片方向，自适应生成横版或竖版A4尺寸的PDF文档，并保持图片居中显示。处理过程会先创建临时文件夹存储裁剪后的图片，最后将所有图片整合到一个PDF文件中输出。程序具有错误处理机制，对异常图片会跳过并提示。