沃巴蒂
ff22ed3a8b
本次同步 09-12 至 09-28 的代码变更，主要内容： 新增功能 - 修改密码：后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口，前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构：file-preview 目录拆分出 VideoPreview（支持 blobUrl 直传）、 ImagePreview、AudioPreview，index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块：markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗：cleaning_task_service/scheduler/routes 重构， data_juicer_executor 与 wrapper 增强，OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注：annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入（useOperatorOperations、dj_ops_schema） 结构调整 - deepflow/ 更名为 deep-flow/（419 个文件重命名） - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/（备份目录） - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl（46MB 构建产物） - DataX/（内嵌独立仓库，远程亦未收录其源码）
86 lines
4.1 KiB
Python
86 lines
4.1 KiB
Python
from markitdown import MarkItDown
|
||
from openpyxl import load_workbook
|
||
from io import BytesIO
|
||
from PIL import Image
|
||
import base64
|
||
from zipfile import ZipFile
|
||
|
||
def extract_xlsx_all_images_base64(xlsx_path: str, max_width=1200):
|
||
img_list = []
|
||
wb = load_workbook(xlsx_path)
|
||
# 1.先读取单元格内嵌图片
|
||
for sheet_name in wb.sheetnames:
|
||
ws = wb[sheet_name]
|
||
for img in ws._images:
|
||
img_bytes = img.ref
|
||
pil_img = Image.open(BytesIO(img_bytes))
|
||
if pil_img.width > max_width:
|
||
ratio = max_width / pil_img.width
|
||
new_size = (max_width, int(pil_img.height * ratio))
|
||
pil_img = pil_img.resize(new_size, Image.Resampling.LANCZOS)
|
||
buf = BytesIO()
|
||
pil_img.save(buf, format="PNG", optimize=True)
|
||
b64_str = base64.b64encode(buf.getvalue()).decode("utf-8")
|
||
uri = f"data:image/png;base64,{b64_str}"
|
||
img_list.append({"sheet": sheet_name, "data_uri": uri})
|
||
wb.close()
|
||
|
||
# 2.解析xlsx压缩包内drawing.xml，提取浮动形状图片
|
||
with ZipFile(xlsx_path, "r") as zf:
|
||
file_list = zf.namelist()
|
||
# 遍历所有drawing，匹配media图片
|
||
drawing_files = [f for f in file_list if f.startswith("xl/drawings/drawing") and f.endswith(".xml")]
|
||
for drawing_path in drawing_files:
|
||
# 解析drawing.xml获取图片rId
|
||
import xml.etree.ElementTree as ET
|
||
ns_a = {"a": "http://schemas.openxmlformats.org/drawingml/2006/main"}
|
||
ns_xdr = {"xdr": "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing"}
|
||
xml_data = zf.read(drawing_path)
|
||
root = ET.fromstring(xml_data)
|
||
for blip in root.findall(".//a:blip", ns_a):
|
||
r_id = blip.get("{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed")
|
||
if not r_id:
|
||
continue
|
||
# 读取drawing的关系文件
|
||
rel_path = drawing_path.replace(".xml", ".rels")
|
||
if rel_path not in file_list:
|
||
continue
|
||
rel_xml = zf.read(rel_path)
|
||
rel_root = ET.fromstring(rel_xml)
|
||
ns_rel = {"r": "http://schemas.openxmlformats.org/package/2006/relationships"}
|
||
for rel in rel_root.findall(".//r:Relationship", ns_rel):
|
||
if rel.get("Id") == r_id:
|
||
target = rel.get("Target")
|
||
media_path = f"xl/drawings/{target}"
|
||
if media_path in file_list:
|
||
media_bytes = zf.read(media_path)
|
||
pil_img = Image.open(BytesIO(media_bytes))
|
||
if pil_img.width > max_width:
|
||
ratio = max_width / pil_img.width
|
||
new_size = (max_width, int(pil_img.height * ratio))
|
||
pil_img = pil_img.resize(new_size, Image.Resampling.LANCZOS)
|
||
buf = BytesIO()
|
||
pil_img.save(buf, format="PNG", optimize=True)
|
||
b64_str = base64.b64encode(buf.getvalue()).decode("utf-8")
|
||
uri = f"data:image/png;base64,{b64_str}"
|
||
# 缺陷：无法精确归属到sheet名称，统一标记为浮动图片
|
||
img_list.append({"sheet": "FloatingShape", "data_uri": uri})
|
||
return img_list
|
||
|
||
|
||
if __name__ == "__main__":
|
||
xlsx_file = "test_xlsx.xlsx"
|
||
out_md = "xlsx_out.md"
|
||
md = MarkItDown()
|
||
res = md.convert(source=xlsx_file)
|
||
md_text = res.text_content
|
||
images = extract_xlsx_all_images_base64(xlsx_file)
|
||
print(f"一共提取图片：{len(images)}")
|
||
if len(images) > 0:
|
||
md_text += "\n\n## 提取的内嵌图片\n"
|
||
for item in images:
|
||
md_text += f"\n【Sheet：{item['sheet']}】\n\n"
|
||
with open(out_md, "w", encoding="utf-8") as f:
|
||
f.write(md_text)
|
||
print(f"✅转换完成，输出文件：{out_md}")
|