354 lines
12 KiB
Python
354 lines
12 KiB
Python
import PySimpleGUI as sg
|
||
import json
|
||
|
||
import os
|
||
import random
|
||
import re
|
||
from docx.shared import Pt, RGBColor
|
||
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT, WD_UNDERLINE
|
||
from docx.enum.text import WD_ALIGN_PARAGRAPH
|
||
from docx.oxml import OxmlElement
|
||
from docx.oxml.ns import qn
|
||
from docx.enum.style import WD_STYLE_TYPE
|
||
from docx import Document
|
||
from docx.shared import Inches
|
||
from PIL import Image
|
||
|
||
# 保存文件路径的 JSON 文件
|
||
SETTINGS_FILE = 'settings.json'
|
||
|
||
|
||
def set_picture_wrapping(paragraph):
|
||
"""
|
||
设置图片环绕方式
|
||
:param paragraph:
|
||
:return:
|
||
"""
|
||
# 设置图片环绕方式为上下环绕
|
||
pPr = paragraph._element.get_or_add_pPr()
|
||
framePr = OxmlElement('w:framePr')
|
||
framePr.set(qn('w:wrap'), 'around')
|
||
framePr.set(qn('w:vAnchor'), 'text')
|
||
framePr.set(qn('w:hAnchor'), 'text')
|
||
pPr.append(framePr)
|
||
|
||
|
||
def format_word_document(input_filename, output_filename):
|
||
# 打开文档
|
||
doc = Document(input_filename)
|
||
|
||
# 创建或更新标题样式
|
||
style = doc.styles.add_style('CustomHeading', WD_STYLE_TYPE.PARAGRAPH)
|
||
style.font.name = '黑体'
|
||
style.font.size = Pt(22) # 二号字
|
||
style.font.color.rgb = RGBColor(0, 0, 255) # 蓝色
|
||
style.paragraph_format.space_after = Pt(12) # 标题后间距
|
||
# 创建或更新正文样式
|
||
style = doc.styles.add_style('CustomBody', WD_STYLE_TYPE.PARAGRAPH)
|
||
style.font.name = '仿宋'
|
||
style.font.size = Pt(14) # 四号字
|
||
style.paragraph_format.first_line_indent = Pt(20) # 首行缩进两字符
|
||
style.paragraph_format.alignment = WD_PARAGRAPH_ALIGNMENT.LEFT
|
||
style.paragraph_format.line_spacing = 1.5 # 行间距
|
||
style.paragraph_format.space_before = Pt(6) # 段前间距
|
||
style.paragraph_format.space_after = Pt(6) # 段后间距
|
||
|
||
# 遍历所有段落
|
||
for paragraph in doc.paragraphs:
|
||
# 设置标题格式
|
||
if paragraph.style.name.startswith('Heading'):
|
||
paragraph.style = doc.styles['CustomHeading']
|
||
|
||
# 设置段落格式
|
||
else:
|
||
paragraph.style = doc.styles['CustomBody']
|
||
|
||
# 遍历所有图片
|
||
for rel in doc.part.rels.values():
|
||
if "image" in rel.target_ref:
|
||
# 获取图片所在的段落
|
||
for paragraph in doc.paragraphs:
|
||
for run in paragraph.runs:
|
||
if run._element.tag.endswith('}pict'):
|
||
# 设置图片居中
|
||
paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||
# 设置图片环绕方式为上下环绕
|
||
set_picture_wrapping(paragraph)
|
||
paragraph.paragraph_format.space_before = Pt(12)
|
||
paragraph.paragraph_format.space_after = Pt(12)
|
||
|
||
# output_filename = remove_book_titles(output_filename)
|
||
|
||
# 保存文档
|
||
doc.save(output_filename)
|
||
|
||
|
||
def crop_and_replace_images(folder_path):
|
||
"""
|
||
修改图片尺寸
|
||
:param folder_path:
|
||
:return:
|
||
"""
|
||
folder_path = folder_path.strip()
|
||
# 遍历文件夹中的所有文件
|
||
if not os.path.exists(folder_path):
|
||
os.mkdir(folder_path)
|
||
else:
|
||
for filename in os.listdir(folder_path):
|
||
if os.path.exists(filename):
|
||
# 检查文件扩展名是否为图片格式
|
||
if filename.lower().endswith(('.jpg','.png')):
|
||
# 拼接完整的文件路径
|
||
file_path = os.path.join(folder_path, filename)
|
||
print("文件夹路径：" + folder_path)
|
||
print("文件路径：" + file_path)
|
||
# 打开图片
|
||
with Image.open(file_path) as img:
|
||
# 获取图片的尺寸
|
||
width, height = img.size
|
||
# 裁剪图片，裁剪下方10px
|
||
cropped_img = img.crop((0, 0, width, height - (height * 0.2)))
|
||
# 保存裁剪后的图片，覆盖原文件
|
||
output_path = file_path[0:file_path.find('.')] + '.png'
|
||
cropped_img.save(output_path, 'PNG')
|
||
|
||
|
||
def split_text_into_paragraphs(text):
|
||
"""
|
||
将文本分割成段落，并在每个段落之间加一个空行
|
||
:param text: 输入的文本
|
||
:return: 段落列表
|
||
"""
|
||
paragraphs = text.split('\n\n')
|
||
# 过滤掉空行和只包含空白字符的段落
|
||
paragraphs = list(filter(lambda p: p.strip(), paragraphs))
|
||
|
||
# 在每个段落之间加一个空行
|
||
paragraphs_with_blank_lines = []
|
||
for paragraph in paragraphs:
|
||
paragraphs_with_blank_lines.append(paragraph)
|
||
paragraphs_with_blank_lines.append('')
|
||
|
||
# 移除最后一个多余的空行
|
||
if paragraphs_with_blank_lines:
|
||
paragraphs_with_blank_lines.pop()
|
||
|
||
return paragraphs_with_blank_lines
|
||
|
||
|
||
def insert_images_into_paragraphs(paragraphs, image_folder, doc, title):
|
||
"""
|
||
将图片插入到段落中
|
||
:param paragraphs:
|
||
:param image_folder:
|
||
:param doc:
|
||
:return:
|
||
"""
|
||
|
||
if os.path.exists(image_folder):
|
||
images = sorted([os.path.join(image_folder, img) for img in os.listdir(image_folder) if
|
||
img.lower().endswith(('jpg'))])
|
||
else:
|
||
images = []
|
||
|
||
# 获取图片列表并排序
|
||
# images = sorted([os.path.join(image_folder, img) for img in os.listdir(image_folder) if
|
||
# img.lower().endswith(('jpg'))])
|
||
# images = sorted([os.path.join(image_folder, img) for img in os.listdir(image_folder) if
|
||
# # img.lower().endswith(('png', 'jpg', 'jpeg'))])
|
||
|
||
total_images = len(images)
|
||
|
||
image_index = 0
|
||
for i, paragraph in enumerate(paragraphs):
|
||
|
||
if "正文：" in paragraph:
|
||
paragraph = paragraph.replace("正文：", '')
|
||
p = doc.add_paragraph(paragraph)
|
||
if os.path.exists(image_folder):
|
||
# 插入图片
|
||
if image_index < total_images:
|
||
img_path = images[image_index]
|
||
|
||
# 确保图片路径正确且图片文件存在
|
||
if os.path.exists(img_path):
|
||
try:
|
||
with Image.open(img_path) as img:
|
||
width, height = img.size
|
||
doc.add_picture(img_path, width=Inches(width / height * 1.5))
|
||
image_index += 1
|
||
except Exception as e:
|
||
print(f"无法识别图像: {img_path}, 错误: {e}")
|
||
continue
|
||
else:
|
||
print(f"图片路径无效: {img_path}")
|
||
|
||
|
||
def create_word_document(text, image_folder, output_path, title):
|
||
"""
|
||
创建Word文档
|
||
:param text:
|
||
:param image_folder:
|
||
:param output_path:
|
||
:return:
|
||
"""
|
||
doc = Document()
|
||
paragraphs = split_text_into_paragraphs(text)
|
||
insert_images_into_paragraphs(paragraphs, image_folder, doc, title)
|
||
# modify_document(doc)
|
||
doc.save(output_path)
|
||
format_word_document(output_path, output_path)
|
||
print(f'文档已保存到: {output_path}')
|
||
|
||
|
||
# 读取指定路径下txt文本的内容
|
||
def read_text_file(file_path):
|
||
"""
|
||
读取指定路径下txt文本的内容
|
||
:param file_path:
|
||
:return:
|
||
"""
|
||
with open(file_path, 'r', encoding='utf-8') as file:
|
||
return file.read()
|
||
|
||
|
||
def get_file_name(file_path):
|
||
"""
|
||
获取文件名
|
||
:param file_path:
|
||
:return:
|
||
"""
|
||
return os.path.basename(file_path)
|
||
|
||
|
||
def apply_random_style(paragraph):
|
||
# 预定义字体颜色列表
|
||
predefined_font_colors = [
|
||
RGBColor(255, 0, 0), # 红色
|
||
RGBColor(255, 165, 0), # 橙色
|
||
RGBColor(128, 0, 128), # 紫色
|
||
]
|
||
|
||
# 预定义背景颜色列表（手动定义RGB颜色，避免太亮或太深）
|
||
predefined_bg_colors = [
|
||
RGBColor(240, 240, 240), # 浅灰色
|
||
RGBColor(255, 255, 224), # 浅黄色
|
||
RGBColor(224, 255, 224), # 浅绿色
|
||
RGBColor(224, 255, 255), # 浅青色
|
||
RGBColor(255, 228, 225), # 浅粉色
|
||
RGBColor(240, 248, 255), # 浅蓝色
|
||
]
|
||
|
||
# 获取段落中的每一个run对象（代表一段连续的文字）
|
||
for run in paragraph.runs:
|
||
# 随机选择样式
|
||
style_choice = random.choice(['bold', 'italic', 'underline', 'color', 'background'])
|
||
|
||
if style_choice == 'bold':
|
||
run.bold = True
|
||
elif style_choice == 'italic':
|
||
run.italic = True
|
||
elif style_choice == 'underline':
|
||
run.underline = WD_UNDERLINE.SINGLE
|
||
elif style_choice == 'color':
|
||
# 从预定义颜色中随机选择一个颜色
|
||
run.font.color.rgb = random.choice(predefined_font_colors)
|
||
elif style_choice == 'background':
|
||
# 从预定义背景颜色中随机选择一个颜色
|
||
run.font.color.highlight_color = random.choice(predefined_bg_colors)
|
||
|
||
|
||
def txt2docx(txt_path, image_path, keep_txt=True):
|
||
file_path = txt_path
|
||
txts = sorted([os.path.join(file_path, txt) for txt in os.listdir(file_path) if
|
||
txt.lower().endswith(('txt'))])
|
||
img_path = image_path
|
||
|
||
for txt in txts:
|
||
print("正在修改：" + txt)
|
||
text = read_text_file(txt)
|
||
# print(text)
|
||
txt_name = get_file_name(txt)
|
||
title_name = txt_name.replace(".txt", "")
|
||
title = title_name
|
||
print(title)
|
||
if "正文：" in text:
|
||
new_text = text.split('正文：')[1].replace("```markdown", "").replace("```", "")
|
||
else:
|
||
new_text = text.replace("```markdown", "").replace("```", "")
|
||
content = new_text
|
||
# image_folder = img_path + r'\\' + txt_name.replace(".txt", "").rstrip(".")
|
||
# image_folder = os.path.join(img_path, txt_name.replace(".txt", "").rstrip("."))
|
||
from pathlib import Path
|
||
from pathlib import Path
|
||
|
||
img_path = Path(img_path)
|
||
image_folder = img_path / txt_name.replace(".txt", "").rstrip(".")
|
||
|
||
# crop_and_replace_images(image_folder)
|
||
|
||
create_word_document(content, image_folder, txt.replace(".txt", ".docx"), title_name)
|
||
|
||
# 根据用户选择决定是否删除原始txt文件
|
||
if not keep_txt:
|
||
os.remove(txt)
|
||
print(f"已删除原始文件: {txt}")
|
||
else:
|
||
print(f"保留原始文件: {txt}")
|
||
|
||
|
||
# 加载设置
|
||
def load_settings():
|
||
if os.path.exists(SETTINGS_FILE):
|
||
with open(SETTINGS_FILE, 'r') as f:
|
||
return json.load(f)
|
||
return {'folder1': '', 'folder2': ''}
|
||
|
||
|
||
# 保存设置
|
||
def save_settings(settings):
|
||
with open(SETTINGS_FILE, 'w') as f:
|
||
json.dump(settings, f)
|
||
|
||
|
||
# 自定义函数，用于处理用户选择的文件夹
|
||
def process_folders(folder1, folder2, keep_txt=True):
|
||
# 在这里添加处理文件夹的代码
|
||
txt2docx(folder1, folder2, keep_txt)
|
||
|
||
|
||
# 加载之前的设置
|
||
settings = load_settings()
|
||
if 'keep_txt' not in settings:
|
||
settings['keep_txt'] = True
|
||
|
||
# 定义窗口的布局
|
||
layout = [
|
||
[sg.Text('文章文件夹：'), sg.Input(default_text=settings['folder1']), sg.FolderBrowse()],
|
||
[sg.Text('图片文件夹：'), sg.Input(default_text=settings['folder2']), sg.FolderBrowse()],
|
||
[sg.Checkbox('保留原始txt文件', default=settings['keep_txt'], key='keep_txt')],
|
||
[sg.Button('确认'), sg.Button('取消')]
|
||
]
|
||
|
||
# 创建窗口
|
||
window = sg.Window('文件夹选择窗口', layout)
|
||
|
||
# 事件循环
|
||
while True:
|
||
event, values = window.read()
|
||
if event == sg.WIN_CLOSED or event == '取消': # 如果用户关闭窗口或点击取消按钮
|
||
break
|
||
elif event == '确认': # 如果用户点击确认按钮
|
||
folder1 = values[0]
|
||
folder2 = values[1]
|
||
keep_txt = values['keep_txt']
|
||
process_folders(folder1, folder2, keep_txt)
|
||
# 保存用户选择的文件夹路径和保留txt文件的选项
|
||
settings['folder1'] = folder1
|
||
settings['folder2'] = folder2
|
||
settings['keep_txt'] = keep_txt
|
||
save_settings(settings)
|
||
|
||
# 关闭窗口
|
||
window.close()
|