更新pdf_tools.py, pdf_tools.exe

pdf_tools.py

+import math
+import os
+import re
+import subprocess as sub
+import sys
+import warnings
+from glob import glob
+
+import PySimpleGUI as sg
+from PyPDF2 import PdfFileReader, PdfFileWriter
+
+from pikepdf import Pdf, Rectangle
+from reportlab.lib import units
+from reportlab.pdfbase import pdfmetrics
+from reportlab.pdfbase.ttfonts import TTFont
+from reportlab.pdfgen import canvas
+
+warnings.filterwarnings("ignore")
+
+def pdf_add_water_mark(pdf_file, text, overwrite=False, col=2, row=3, font_file="C:\Windows\Fonts\msyh.ttc",
+                       font_szie=35, rotate=45, alpha=0.3):
+    pdfmetrics.registerFont(TTFont('msyh', font_file))  # 加载中文字体
+    c = canvas.Canvas("watermark.pdf", pagesize=(
+        200 * units.mm, 200 * units.mm))
+    c.translate(20 * units.mm, 20 * units.mm)
+    c.rotate(rotate)  # 把水印文字旋转45°
+    c.setFont('msyh', font_szie)  # 字体大小
+    c.setStrokeColorRGB(0, 0, 0)  # 设置字体颜色
+    c.setFillColorRGB(0, 0, 0)  # 设置填充颜色
+    c.setFillAlpha(alpha)  # 设置透明度，越小越透明
+    c.drawString(0, 0, text)
+    c.save()
+    water_mark_pdf = Pdf.open("watermark.pdf")
+    water_mark = water_mark_pdf.pages[0]
+
+    target = Pdf.open(pdf_file, allow_overwriting_input=True)
+    for page in target.pages:
+        _, _, w, h = page.trimbox
+        for x in range(col):  # 每一行显示多少列水印
+            for y in range(row):  # 每一页显示多少行PDF
+                page.add_overlay(water_mark,
+                                 Rectangle(w * x / col,
+                                           h * y / row,
+                                           w * (x + 1) / col,
+                                           h * (y + 1) / row))
+    if overwrite:
+        file = None
+    else:
+        file = pdf_file.replace(".pdf", "_带水印.pdf")
+    target.save(file)
+    return file or pdf_file
+
+
+sg.change_look_and_feel("Python")
+
+
+def write_pdf(save_filepath, pdf_writer):
+    with open(save_filepath, "wb") as out:
+        pdf_writer.write(out)
+
+
+def split_pdf(filename, output, n=3):
+    basename = os.path.basename(filename)
+    name, ext = os.path.splitext(basename)
+    pdf_reader = PdfFileReader(filename)
+    pdf_writer = PdfFileWriter()
+    os.makedirs(output, exist_ok=True)
+    page_num = len(pdf_reader.pages)
+    print(f"pdf共{page_num}页，要写出{math.ceil(page_num / n)}页")
+    for i, page in enumerate(pdf_reader.pages, 1):
+        page.compressContentStreams()
+        pdf_writer.addPage(page)
+        if i % n == 0:
+            output_name = f"{output}/{name}_{i // n}.pdf"
+            write_pdf(output_name, pdf_writer)
+            print(output_name, "写出完成")
+            pdf_writer = PdfFileWriter()
+    if i % n != 0:
+        output_name = f"{output}/{name}_{i // n}.pdf"
+        write_pdf(output_name, pdf_writer)
+        print(output_name, "写出完成")
+    print("拆分完成！")
+
+
+def get_files(dir_path):
+    files = glob(f"{dir_path}/*.pdf")
+    files.sort(key=lambda s: [(s, int(n)) for s, n in re.findall('(\D+)(\d+)', f'a{s}0')])
+    return files
+
+
+def merge_pdf(dir_path, out_name, add_bookmark=True):
+    dir_path = dir_path.strip("\\/")
+    files = get_files(dir_path)
+    pdf_writer = PdfFileWriter()
+    output_pages = 0
+    for pdf_file in files:
+        pdf_reader = PdfFileReader(pdf_file)
+        pdf_file = os.path.basename(pdf_file)
+        pageCount = pdf_reader.getNumPages()
+        output_pages += pageCount
+        print(pdf_file, "页数：", pageCount)
+        for page in pdf_reader.pages:
+            page.compressContentStreams()
+            pdf_writer.addPage(page)
+        if add_bookmark:
+            pdf_writer.addBookmark(pdf_file[:pdf_file.rfind(".")], output_pages - pageCount, parent=None)
+    print("总页数：", output_pages)
+    print("开始写出到文件")
+    with open(out_name, "wb") as outputfile:
+        pdf_writer.write(outputfile)
+    print("PDF文件合并完成")
+
+
+def get_pdf_Bookmark(filename):
+    "作者CSDN：https://blog.csdn.net/as604049322"
+    if isinstance(filename, str):
+        pdf_reader = PdfFileReader(filename)
+    else:
+        pdf_reader = filename
+    pagecount = pdf_reader.getNumPages()
+    # 用保存每个标题id所对应的页码
+    idnum2pagenum = {}
+    for i in range(pagecount):
+        page = pdf_reader.getPage(i)
+        idnum2pagenum[page.indirectRef.idnum] = i
+    # 保存每个标题对应的标签数据，包括层级，标题和页码索引（页码-1）
+    bookmark = []
+
+    def get_pdf_Bookmark_inter(outlines, tab=0):
+        for outline in outlines:
+            if isinstance(outline, list):
+                get_pdf_Bookmark_inter(outline, tab + 1)
+            else:
+                bookmark.append(
+                    (tab, outline['/Title'], idnum2pagenum[outline.page.idnum]))
+
+    outlines = pdf_reader.getOutlines()
+    get_pdf_Bookmark_inter(outlines)
+    return bookmark
+
+
+def read_bookmark_from_file(filename="bookmark.txt", diff=0):
+    bookmark = []
+    with open(filename, "rb") as f:
+        import cchardet
+        bytes = f.read()
+        content = bytes.decode(cchardet.detect(bytes)['encoding'])
+        for line in content.splitlines():
+            l2 = line.rfind("\t")
+            l1 = line.rfind("\t", 0, l2)
+            bookmark.append((l1 + 1, line[l1 + 1:l2], int(line[l2 + 1:]) - 1 + diff))
+    return bookmark
+
+
+def write_bookmark2file(bookmark, filename="bookmark.txt"):
+    with open(filename, "w", encoding="gbk") as f:
+        for tab, title, pagenum in bookmark:
+            prefix = "\t" * tab
+            f.write(f"{prefix}{title}\t{pagenum + 1}\n")
+    print("书签已经写出到文件", filename)
+
+
+def pdf_write_bookmark(bookmark, pdf_file, compress):
+    pdf_reader = PdfFileReader(pdf_file)
+    num_pages = pdf_reader.getNumPages()
+    pdf_writer = PdfFileWriter()
+    for page in pdf_reader.pages:
+        if compress:
+            page.compressContentStreams()
+        pdf_writer.addPage(page)
+    # pdf_reader.
+    last_cache = [None] * (max(bookmark, key=lambda x: x[0])[0] + 1)
+    for tab, title, pagenum in bookmark:
+        if pagenum >= num_pages:
+            continue
+        parent = last_cache[tab - 1] if tab > 0 else None
+        indirect_id = pdf_writer.addBookmark(title, pagenum, parent=parent)
+        last_cache[tab] = indirect_id
+    pdf_writer.setPageMode("/UseOutlines")
+    with open(pdf_file, "wb") as out:
+        pdf_writer.write(out)
+    print("已成功将书签写入到", pdf_file)
+
+
+sg.change_look_and_feel("Python")
+# 布局设置
+layout = [
+    [sg.TabGroup([[
+        sg.Tab('拆分', [
+            [sg.Text('pdf文件地址：', font=("楷体", 12)),
+             sg.In(size=(32, 1), key="filename"),
+             sg.FileBrowse('...', target='filename', file_types=(("PDF Files", "*.pdf"),), initial_folder=".")],
+            [sg.Text('拆分页数：', font=("楷体", 12)),
+             sg.In(size=(3, 1), key="n", default_text="5"),
+             sg.Button('开始拆分'),
+             sg.Button('打开输出目录'),
+             ],
+            [sg.Text('输出目录：', font=("楷体", 12)),
+             sg.In(size=(35, 1), default_text="./output", key="save_dir"),
+             sg.FolderBrowse('...', target='save_dir', initial_folder="."),
+             ],
+        ]),
+        sg.Tab('合并', [
+            [sg.Text('pdf文件目录：', font=("楷体", 12)),
+             sg.In(size=(32, 1), key="pdf_dir"),
+             sg.FolderBrowse('...', target='pdf_dir', initial_folder=".")],
+            [sg.Checkbox('添加文件名作为书签', key="add_bookmark", default=True),
+             sg.Button('开始合并'),
+             sg.Button('定位输出位置'),
+             ],
+            [sg.Text('输出位置：', font=("楷体", 12)),
+             sg.In(size=(35, 1), default_text="./合并.pdf", key="out_name"),
+             sg.FileSaveAs('...', target='out_name', file_types=(("PDF Files", "*.pdf"),), initial_folder="."),
+             ],
+        ]),
+        sg.Tab('书签', [
+            [sg.Text('pdf文件地址：', font=("楷体", 12)), sg.In(size=(32, 1), key="pdf_file"),
+             sg.FileBrowse('...', target='pdf_file', file_types=(("PDF Files", "*.pdf"),), initial_folder=".")],
+            [sg.Button('提取书签'),
+             sg.Button('定位书签位置'),
+             ],
+            [sg.Text('书签位置：', font=("楷体", 12)),
+             sg.In(size=(35, 1), default_text="./bookmark.txt", key="bookmark_name"),
+             sg.FileSaveAs('...', target='bookmark_name', file_types=(("书签文件", "*.txt"),), initial_folder="."),
+             ],
+            [sg.Checkbox('压缩', key="compress", default=False),
+             sg.Text('偏移:'), sg.In(size=(3, 1), default_text="0", key="diff"),
+             sg.Button('写入书签'), ]
+        ]),
+        sg.Tab('水印', [
+            [sg.Text('pdf文件地址：', font=("楷体", 12)),
+             sg.In(size=(32, 1), key="pdf_file2"),
+             sg.FileBrowse('...', target='pdf_file2', file_types=(("PDF Files", "*.pdf"),), initial_folder=".")],
+            [
+                sg.Text('行:'), sg.In(size=(2, 1), default_text="3", key="row"),
+                sg.Text('列:'), sg.In(size=(2, 1), default_text="2", key="col"),
+                sg.Text('旋转:'), sg.In(size=(2, 1), default_text="45", key="rotate"),
+                sg.Text('透明度:'), sg.In(size=(3, 1), default_text="0.3", key="alpha"),
+                sg.Checkbox('覆盖', key="overwrite", default=False),
+            ],
+            [
+                sg.Text('字体:', font=("楷体", 12)),
+                sg.In(size=(26, 1), key="font_file", default_text="C:\Windows\Fonts\msyh.ttc"),
+                sg.FileBrowse('...', target='font_file', initial_folder="."),
+                sg.Text('大小:'), sg.In(size=(3, 1), default_text="35", key="font_szie"),
+            ],
+            [sg.Text('水印内容:', font=("楷体", 12)), sg.In(size=(24, 1), key="text"),
+             sg.Button('添加水印'),
+             ],
+        ]),
+    ]])],
+
+    [sg.Output(size=(53, 7), key="out", text_color="#15d36a")],
+    [
+        sg.Checkbox('处理完毕后定位输出目录', key="open_folder", default=True),
+        sg.Button('清空输出'),
+    ],
+    [sg.Text("@小小明：https://blog.csdn.net/as604049322"), ],
+]
+
+
+def resource_path(relative_path):
+    base_path = getattr(sys, '_MEIPASS', os.path.dirname(os.path.abspath(__file__)))
+    return os.path.join(base_path, relative_path)
+
+
+title = 'PDF常用工具箱 v0.2'
+window = sg.Window(title, layout, icon=resource_path("./pdf.ico"))
+window.finalize()
+
+if __name__ == '__main__':
+    while True:
+        event, values = window.read()
+        if event in (None,):
+            break  # 相当于关闭界面
+        elif event == "开始拆分":
+            save_dir = os.path.abspath(values['save_dir'])
+            os.makedirs(values['save_dir'], exist_ok=True)
+            split_pdf(values["filename"], save_dir, int(values["n"]))
+            window["save_dir"].Update(save_dir)
+            if values["open_folder"]:
+                sub.Popen(f"explorer {save_dir}", shell=False)
+        elif event == "打开输出目录":
+            save_dir = os.path.abspath(values['save_dir'])
+            if os.path.exists(save_dir):
+                sub.Popen(f"explorer {save_dir}", shell=False)
+            else:
+                sg.popup("输出目录不存在！")
+                window["save_dir"].Update(os.path.abspath("./output"))
+        elif event == "开始合并":
+            pdf_dir = os.path.abspath(values['pdf_dir'])
+            out_name = os.path.abspath(values['out_name'])
+            merge_pdf(pdf_dir, out_name, values["add_bookmark"])
+            window["out_name"].Update(out_name)
+            if values["open_folder"]:
+                sub.Popen(f"explorer {os.path.dirname(out_name)}", shell=False)
+        elif event == "定位输出位置":
+            out_name = os.path.abspath(values['out_name'])
+            sub.Popen(f"explorer {os.path.dirname(out_name)}", shell=False)
+        elif event == "提取书签":
+            pdf_file = os.path.abspath(values['pdf_file'])
+            bookmark_name = os.path.abspath(values['bookmark_name'])
+            bookmark = get_pdf_Bookmark(pdf_file)
+            window["bookmark_name"].Update(bookmark_name)
+            write_bookmark2file(bookmark, filename=bookmark_name)
+            if values["open_folder"]:
+                sub.Popen(f"explorer {os.path.dirname(bookmark_name)}", shell=False)
+        elif event == "写入书签":
+            pdf_file = os.path.abspath(values['pdf_file'])
+            bookmark_name = os.path.abspath(values['bookmark_name'])
+            bookmark = read_bookmark_from_file(bookmark_name, int(values["diff"]))
+            window["bookmark_name"].Update(bookmark_name)
+            pdf_write_bookmark(bookmark, pdf_file, values["compress"])
+            if values["open_folder"]:
+                sub.Popen(f"explorer {os.path.dirname(pdf_file)}", shell=False)
+        elif event == "定位书签位置":
+            bookmark_name = os.path.abspath(values['bookmark_name'])
+            sub.Popen(f"explorer {os.path.dirname(bookmark_name)}", shell=False)
+        # elif event == "添加水印":
+        #     pdf_file = os.path.abspath(values['pdf_file2'])
+        #     result_file = pdf_add_water_mark(pdf_file, values["text"], values["overwrite"],
+        #                                      int(values["col"]), int(values["row"]),
+        #                                      values["font_file"], int(values["font_szie"]),
+        #                                      int(values["rotate"]), float(values["alpha"]))
+        #     print("水印保存到", result_file)
+        #     if values["open_folder"]:
+        #         sub.Popen(f"explorer {os.path.dirname(result_file)}", shell=False)
+        elif event == "清空输出":
+            window["out"].Update("")
+    window.close()