|
|
import re
|
|
|
import warnings
|
|
|
|
|
|
import docx
|
|
|
|
|
|
import os
|
|
|
import shutil
|
|
|
import uuid
|
|
|
import zipfile
|
|
|
|
|
|
from docx import Document
|
|
|
from docx.oxml.ns import nsmap
|
|
|
|
|
|
# 抑制HTTPS相关警告
|
|
|
warnings.filterwarnings('ignore', message='Connecting to .* using TLS with verify_certs=False is insecure')
|
|
|
warnings.filterwarnings('ignore', message='Unverified HTTPS request is being made to host')
|
|
|
|
|
|
|
|
|
def extract_images_from_docx(docx_path, output_folder):
|
|
|
"""
|
|
|
从docx提取图片并记录位置
|
|
|
:param docx_path: Word文档路径
|
|
|
:param output_folder: 图片输出文件夹
|
|
|
:return: 包含图片路径和位置的列表
|
|
|
"""
|
|
|
# 创建一个List<String> 记录每个图片的名称和序号
|
|
|
image_data = []
|
|
|
# 创建临时解压目录
|
|
|
temp_dir = os.path.join(output_folder, "temp_docx")
|
|
|
os.makedirs(temp_dir, exist_ok=True)
|
|
|
|
|
|
# 解压docx文件
|
|
|
with zipfile.ZipFile(docx_path, 'r') as zip_ref:
|
|
|
zip_ref.extractall(temp_dir)
|
|
|
|
|
|
# 读取主文档关系
|
|
|
with open(os.path.join(temp_dir, 'word', '_rels', 'document.xml.rels'), 'r') as rels_file:
|
|
|
rels_content = rels_file.read()
|
|
|
|
|
|
# 加载主文档
|
|
|
doc = Document(docx_path)
|
|
|
img_counter = 1
|
|
|
|
|
|
# 遍历所有段落
|
|
|
for para_idx, paragraph in enumerate(doc.paragraphs):
|
|
|
for run_idx, run in enumerate(paragraph.runs):
|
|
|
# 检查运行中的图形
|
|
|
for element in run._element:
|
|
|
if element.tag.endswith('drawing'):
|
|
|
# 提取图片关系ID
|
|
|
blip = element.find('.//a:blip', namespaces=nsmap)
|
|
|
if blip is not None:
|
|
|
embed_id = blip.get('{%s}embed' % nsmap['r'])
|
|
|
|
|
|
# 从关系文件中获取图片文件名
|
|
|
rel_entry = f'<Relationship Id="{embed_id}"'
|
|
|
if rel_entry in rels_content:
|
|
|
start = rels_content.find(rel_entry)
|
|
|
target_start = rels_content.find('Target="', start) + 8
|
|
|
target_end = rels_content.find('"', target_start)
|
|
|
image_path = rels_content[target_start:target_end]
|
|
|
|
|
|
# 构建图片源路径
|
|
|
src_path = os.path.join(temp_dir, 'word', image_path.replace('..', '').lstrip('/'))
|
|
|
|
|
|
if os.path.exists(src_path):
|
|
|
# 创建输出文件名
|
|
|
ext = os.path.splitext(src_path)[1]
|
|
|
# 名称为uuid
|
|
|
fileName = uuid.uuid4().hex
|
|
|
img_name = f"{fileName}{ext}"
|
|
|
image_data.append(img_name)
|
|
|
dest_path = os.path.join(output_folder, img_name)
|
|
|
# 复制图片
|
|
|
shutil.copy(src_path, dest_path)
|
|
|
|
|
|
img_counter += 1
|
|
|
|
|
|
# 清理临时目录
|
|
|
shutil.rmtree(temp_dir)
|
|
|
return image_data
|
|
|
|
|
|
|
|
|
def read_word_content(docx_path):
|
|
|
res = ""
|
|
|
idx = 0
|
|
|
"""遍历Word文档的每个段落，输出文字或图片标识"""
|
|
|
try:
|
|
|
doc = docx.Document(docx_path)
|
|
|
|
|
|
for paragraph in doc.paragraphs:
|
|
|
has_image = False
|
|
|
# 检查段落中是否有图片
|
|
|
for run in paragraph.runs:
|
|
|
for element in run._element:
|
|
|
if element.tag.endswith('drawing'):
|
|
|
# 找到图片元素
|
|
|
has_image = True
|
|
|
break
|
|
|
if has_image:
|
|
|
break
|
|
|
|
|
|
if has_image:
|
|
|
idx = idx + 1
|
|
|
res = res + "\n" + "【图片" + str(idx) + "】"
|
|
|
elif paragraph.text.strip():
|
|
|
res = res + "\n" + paragraph.text.strip()
|
|
|
return res
|
|
|
except Exception as e:
|
|
|
print(f"处理Word文档时出错: {str(e)}")
|
|
|
|
|
|
|
|
|
def split_into_blocks(text):
|
|
|
"""按行遍历文本，发现'问题X'或'话题X'时开始分割，只移除前缀但保留整行内容"""
|
|
|
blocks = []
|
|
|
current_block = []
|
|
|
in_block = False
|
|
|
|
|
|
for line in text.splitlines():
|
|
|
if line.startswith(('问题', '话题')) and any(c.isdigit() for c in line[:5]):
|
|
|
if in_block:
|
|
|
blocks.append('\n'.join(current_block))
|
|
|
current_block = []
|
|
|
in_block = True
|
|
|
# 循环移除问题和话题前缀后的数字
|
|
|
while line and (line.startswith(('问题', '话题')) or (line and line and line[0].isdigit())):
|
|
|
if line.startswith(('问题', '话题')):
|
|
|
line = line[2:] if len(line) > 2 else line
|
|
|
elif line and line[0].isdigit():
|
|
|
line = line[1:] if len(line) > 1 else line
|
|
|
line = line.strip()
|
|
|
if in_block and line: # 只添加非空行
|
|
|
current_block.append(line)
|
|
|
|
|
|
if current_block:
|
|
|
blocks.append('\n'.join(current_block))
|
|
|
|
|
|
return [(i + 1, block) for i, block in enumerate(blocks)]
|
|
|
|
|
|
|
|
|
# 保留原有的save_to_txt函数
|
|
|
def save_to_txt(content, file_path, mode='w'):
|
|
|
"""将内容保存到文本文件"""
|
|
|
try:
|
|
|
with open(file_path, mode, encoding='utf-8') as f:
|
|
|
f.write(content)
|
|
|
return True
|
|
|
except Exception as e:
|
|
|
print(f"保存文件{file_path}时出错: {str(e)}")
|
|
|
return False
|
|
|
|
|
|
|
|
|
def process_document(word_document_path,txt_output_dir,img_output_dir):
|
|
|
# 提取图片
|
|
|
listImage = extract_images_from_docx(word_document_path, img_output_dir)
|
|
|
# 读取内容
|
|
|
res = read_word_content(word_document_path)
|
|
|
# 分块
|
|
|
chunks = split_into_blocks(res)
|
|
|
saved_count = 0
|
|
|
|
|
|
# 使用原来的正则表达式
|
|
|
pattern = re.compile(r'【图片\d+】')
|
|
|
# 初始化图片索引
|
|
|
img_idx = 0
|
|
|
|
|
|
for x in chunks:
|
|
|
firstLine = x[1].split("\n")[0].strip()
|
|
|
content = x[1][len(firstLine):].strip()
|
|
|
|
|
|
# 使用finditer查找所有匹配项
|
|
|
# 使用闭包函数替换所有匹配项
|
|
|
img_idx = [0] # 使用列表实现可变状态
|
|
|
|
|
|
def replacer(match):
|
|
|
if img_idx[0] < len(listImage):
|
|
|
result = f"<img src=\"./Images/{listImage[img_idx[0]]}\">"
|
|
|
img_idx[0] += 1
|
|
|
return result
|
|
|
return match.group()
|
|
|
|
|
|
content = pattern.sub(replacer, content)
|
|
|
# 保存文本文件
|
|
|
# 从docx文件名提取学科和编号
|
|
|
docx_name = os.path.basename(word_document_path).split('.')[0]
|
|
|
subject_part = '_'.join(docx_name.split('_')[-2:]) # 获取最后两部分如CHINESE_1
|
|
|
output_file = os.path.join(txt_output_dir, f"{subject_part}_{x[0]}.txt")
|
|
|
full_content = f"{firstLine}\n{content}"
|
|
|
if save_to_txt(full_content, output_file, mode='w'):
|
|
|
saved_count += 1
|
|
|
|
|
|
print(f"处理完成，共保存{saved_count}个文件到目录: {txt_output_dir}")
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
txt_output_dir = "../Txt/"
|
|
|
img_output_dir = "../static/Images/"
|
|
|
# 遍历static/Txt/下所有的docx
|
|
|
for filename in os.listdir("../static/Txt/"):
|
|
|
print("正在处理文件：" + filename)
|
|
|
# 这里需要文件的全称路径
|
|
|
filename = os.path.join("../static/Txt/", filename)
|
|
|
process_document(filename,txt_output_dir,img_output_dir)
|
