diff --git a/main.py b/main.py index 14a564d..daa0c64 100644 --- a/main.py +++ b/main.py @@ -26,7 +26,7 @@ def convert_all(path = os.path.abspath('.')): items = os.listdir(path) for item in items: if os.path.isdir(item): - result = convert_img(item, path + '\\' + item) + result = convert_img(item, path + os.sep + item) if result == 1: print("PDF 转换失败！") done(1) @@ -47,31 +47,46 @@ def convert_img(dir_name, path = os.path.abspath('.')): return 1 pdf_list.append(file) elif file.endswith('.jpg') or file.endswith('.jpeg'): - img = Image.open(path + '\\' + file) + img = Image.open(path + os.sep + file) dot_index = file.rfind('.') - img_path = path + '\\' + file[:dot_index] + ".png" + img_path = path + os.sep + file[:dot_index] + ".png" img.save(img_path, "PNG") gened_list.append(img_path) if len(pdf_list) > 1: - print(f"注意到文件夹 {dir_name} 中有多个 .pdf 文件：") - for i in range(len(pdf_list)): # 打印 pdf 文件和选项 - print(f"{i + 1} - {pdf_list[i]}") # 索引从 0 改为 1 - while True: - invoice_index = input("请选择发票文件（输入选项前的阿拉伯数字）：") - if not invoice_index.isdigit(): - print("请输入数字！") - continue - else: - invoice_int = int(invoice_index) - 1 # 索引从 1 改为 0 - if invoice_int < len(pdf_list) and invoice_int >= 0: - invoice_path = path + '\\' + "pdf" + pdf_list[invoice_int][:-4] + ".png" - invoice_renamed = path + '\\' + 'Pdf' + pdf_list[invoice_int][:-4] + ".png" + fp_name = ["发票","dzfp"] + finish = False + for i in fp_name: + for j in range(len(pdf_list)): + if i in pdf_list[j]: + invoice_path = path + os.sep + "pdf" + pdf_list[j][:-4] + ".png" + invoice_renamed = path + os.sep + 'Pdf' + pdf_list[j][:-4] + ".png" os.rename(invoice_path, invoice_renamed) # 将 "pdf" 标签变为 "Pdf" gened_list.remove(invoice_path) gened_list.append(invoice_renamed) + finish = True break + if finish == True: + break + if finish == False: + print(f"注意到文件夹 {dir_name} 中有多个 .pdf 文件：") + for i in range(len(pdf_list)): # 打印 pdf 文件和选项 + print(f"{i + 1} - {pdf_list[i]}") # 索引从 0 改为 1 + while True: + invoice_index = input("请选择发票文件（输入选项前的阿拉伯数字）：") + if not invoice_index.isdigit(): + print("请输入数字！") + continue else: - print("请选择正确的序号!") + invoice_int = int(invoice_index) - 1 # 索引从 1 改为 0 + if invoice_int < len(pdf_list) and invoice_int >= 0: + invoice_path = path + os.sep + "pdf" + pdf_list[invoice_int][:-4] + ".png" + invoice_renamed = path + os.sep + 'Pdf' + pdf_list[invoice_int][:-4] + ".png" + os.rename(invoice_path, invoice_renamed) # 将 "pdf" 标签变为 "Pdf" + gened_list.remove(invoice_path) + gened_list.append(invoice_renamed) + break + else: + print("请选择正确的序号!") def gen_filelist(path = os.path.abspath('.')): print("创建文件夹列表中...") @@ -82,20 +97,16 @@ def gen_filelist(path = os.path.abspath('.')): dir_list.append(item) file_list = {} for dir in dir_list: - file_list[dir] = os.listdir(path + '\\' + dir) + file_list[dir] = os.listdir(path + os.sep + dir) for dir, dir_file in file_list.items(): dir_file_copy = copy(dir_file) for file in dir_file_copy: if ".png" not in file.lower(): dir_file.remove(file) - if len(dir_file) != 3: + if len(dir_file) != 3 or len(dir_file) != 2: print(f"在{dir}文件夹发现错误：png文件个数不符") for file in dir_file: print('- ' + file) - if len(dir_file) == 2: # 说明有两个文件 - option = input("文件夹仅有两个文件，仍继续生成？（y/N）").lower() - if option != 'y': - done(1) print("创建完毕！将要加入文档的文件如下：") for dir, dir_file in file_list.items(): print('- ' + dir) @@ -113,18 +124,25 @@ def gen_docx(path = os.path.abspath('.')): print("生成 .docx 文档中...") if len(file_list) != 0: for dir, dir_file in file_list.items(): - parent_path = path + '\\' + dir + '\\' + parent_path = path + os.sep + dir + os.sep + for file in dir_file: + if file[0:3] == "pdf": + dir_file.remove(file) + dir_file.insert(0, file) for file in dir_file: if file[0:3] == "Pdf": dir_file.remove(file) dir_file.insert(0, file) # 将发票文件放在第一个位置 - doc.add_picture(parent_path + dir_file[0], height = Inches(2.5)) + doc.add_picture(parent_path + dir_file[0], height = Inches(4.2)) table = doc.add_table(rows = 1, cols = 2) cell1 = table.cell(0, 0) - cell1.paragraphs[0].add_run().add_picture(parent_path + dir_file[1], height = Inches(5.0)) + if "行程单" in dir_file[1]: + cell1.paragraphs[0].add_run().add_picture(parent_path + dir_file[1], height = Inches(4.0)) + else: + cell1.paragraphs[0].add_run().add_picture(parent_path + dir_file[1], height = Inches(4.0)) cell2 = table.cell(0, 1) if len(dir_file) == 3: - cell2.paragraphs[0].add_run().add_picture(parent_path + dir_file[2], height = Inches(5.0)) + cell2.paragraphs[0].add_run().add_picture(parent_path + dir_file[2], height = Inches(4.0)) if (dir, dir_file) != list(file_list.items())[-1]: # dict.items() 返回值需先转换为列表，才能索引 doc.add_page_break() else: @@ -133,17 +151,22 @@ def gen_docx(path = os.path.abspath('.')): doc.save("output.docx") print("生成完毕！") -def pdf2img(pdf_path, pdf_name, zoom_x = 3, zoom_y = 3): - doc = fitz.open(pdf_path + "\\" + pdf_name) # 打开文档 +def pdf2img(pdf_path, pdf_name, zoom_x = 7, zoom_y = 7): + doc = fitz.open(pdf_path + os.sep + pdf_name) # 打开文档 if len(doc) != 1: print("PDF 文件只能包含一页！") return 1 for page in doc: # 遍历页面 pix = page.get_pixmap(matrix=fitz.Matrix(zoom_x, zoom_y)) # 将页面渲染为图片 - png_path = pdf_path + '\\' + "pdf" + pdf_name[:-4] + ".png" + png_path = pdf_path + os.sep + "pdf" + pdf_name[:-4] + ".png" gened_list.append(png_path) pix.save(png_path) # 将图像存储为PNG格式 doc.close() # 关闭文档 + if "行程" in pdf_name: + img = Image.open(pdf_path + os.sep + "pdf" + pdf_name[:-4] + ".png") + if img.height > img.width: + img = img.rotate(270,expand=True) + img.save(pdf_path + os.sep + "pdf" + pdf_name[:-4] + ".png") if __name__ == "__main__": gened_list = [] # 新创建的文件列表，在出错时或者生成完毕时进行删除