import os
from pdf2image import convert_from_path
import comtypes.client
# 1. doc/docx 转 pdf

current_directory = os.getcwd()
print(current_directory )
doc_file = current_directory  + "\\test.doc"
pdf_file = current_directory + "\\test.pdf"

def doc_to_pdf(doc_path, pdf_path):
    word = comtypes.client.CreateObject("Word.Application")
    doc = word.Documents.Open(doc_path)
    doc.SaveAs(pdf_path, FileFormat=17)  # 17 表示 PDF 格式
    doc.Close()
    word.Quit()


def process_directory(dir_path):
    print(f"开始处理目录：{dir_path}")
    for file in os.listdir(dir_path):
        if file.lower().endswith(".doc") and not file.lower().endswith(".docx"):
            doc_path = os.path.join(dir_path, file)
            pdf_path = os.path.splitext(doc_path)[0] + ".pdf"

            try:
                # 1. doc → pdf
                doc_to_pdf(doc_path, pdf_path)

                # 2. pdf → jpg
                images = convert_from_path(pdf_file, dpi=200)
                for i, page in enumerate(images, start=1):
                    if i < 8:
                        jpg_name =f"个人申请表{i}.jpg" 
                        
                    else:
                        jpg_name =f"背景审查结论.jpg" 

                    page.save(os.path.join(dir_path, jpg_name),"JPEG")
                # 3. 删除 doc 和 pdf
                os.remove(doc_path)
                os.remove(pdf_path)

                print(f"  ✔ 成功处理文件: {file}")

            except Exception as e:
                print(f"  ✘ 处理失败 {file}: {e}")

    print(f"完成目录处理：{dir_path}\n")

def main():
    base_dir = "target"
    for root, dirs, files in os.walk(base_dir):
        # 只处理子目录，不处理 base_dir 自己的文件
        for d in dirs:
            subdir = os.path.join(root, d)
            process_directory(os.getcwd() + "\\" + subdir)
            # print(subdir)

if __name__ == "__main__":
    main()