Python文件解析之Excel/Word/PDF的解析、处理、预览与下载

# Backend
pip install fastapi uvicorn python-multipart openpyxl pandas python-docx pymupdf

# Frontend
npm install xlsx mammoth react-data-grid

# Optional OCR fallback
pip install pytesseract pillow
# or
pip install paddleocr

# Optional legacy-format support
pip install xlrd

from pathlib import Path
from fastapi import APIRouter, UploadFile, File

router = APIRouter()

@router.post("/api/files/upload")
async def upload(files: list[UploadFile] = File(...)):
    items = []
    for f in files:
        suffix = Path(f.filename).suffix.lower()
        raw_path = save_raw_file(f)  # 保存原件

        if suffix == ".xlsx":
            file_id = process_excel(raw_path)
            file_type = "excel"
        elif suffix == ".docx":
            file_id = process_word(raw_path)
            file_type = "word"
        elif suffix == ".pdf":
            file_id = process_pdf(raw_path)
            file_type = "pdf"
        else:
            items.append({"filename": f.filename, "error": "unsupported file type"})
            continue

        items.append({"file_id": file_id, "type": file_type, "filename": f.filename})

    return {"items": items}

from fastapi.responses import FileResponse

@router.get("/api/files/{file_id}/download/raw")
def download_raw(file_id: str):
    path = locate_raw_file(file_id)
    return FileResponse(path, filename=path.name)

from openpyxl import load_workbook


def parse_excel(path: str) -> dict:
    wb = load_workbook(path, data_only=True)
    sheets: dict[str, list[list[str]]] = {}

    for sheet_name in wb.sheetnames:
        ws = wb[sheet_name]
        rows: list[list[str]] = []
        for row in ws.iter_rows(values_only=True):
            rows.append(["" if c is None else str(c) for c in row])
        sheets[sheet_name] = rows

    return {
        "sheet_names": wb.sheetnames,
        "sheets": sheets,
    }

def normalize_excel_rows(rows: list[list[str]]) -> list[list[str]]:
    if not rows:
        return [[""]]
    width = max(len(r) for r in rows)
    normalized = []
    for r in rows:
        row = ["" if c is None else str(c) for c in r]
        if len(row) < width:
            row += [""] * (width - len(row))
        normalized.append(row[:width])
    return normalized

PUT /api/excel/{file_id}/edit

{
  "sheet_name": "Sheet1",
  "rows": [["A1", "B1"], ["A2", "B2"]]
}

@router.get("/api/excel/{file_id}/download/edited")
def download_excel_edited(file_id: str):
    edited_path = build_edited_excel(file_id)  # 根据保存的 rows 重建 xlsx
    return FileResponse(edited_path, filename=edited_path.name)

from docx import Document


def parse_word(path: str) -> dict:
    doc = Document(path)
    blocks: list[dict] = []

    # 段落块
    for p in doc.paragraphs:
        text = p.text.strip()
        if text:
            blocks.append({"type": "paragraph", "text": text})

    # 表格块
    for table_index, table in enumerate(doc.tables):
        rows = []
        for row in table.rows:
            rows.append([cell.text.strip() for cell in row.cells])
        blocks.append({"type": "table", "table_index": table_index, "rows": rows})

    return {"blocks": blocks}

PUT /api/word/{file_id}/edit

{
  "blocks": [
    {"type": "paragraph", "text": "Updated paragraph"},
    {"type": "table", "table_index": 0, "rows": [["Header1", "Header2"], ["V1", "V2"]]}
  ]
}

@router.get("/api/word/{file_id}/download/edited")
def download_word_edited(file_id: str):
    edited_docx = build_edited_word_docx(file_id)
    return FileResponse(edited_docx, filename=edited_docx.name)

import fitz


def parse_pdf(path: str) -> dict:
    pages = []
    with fitz.open(path) as doc:
        for i in range(doc.page_count):
            page = doc.load_page(i)
            text = page.get_text("text") or ""

            tables = []
            finder = page.find_tables()
            if finder and finder.tables:
                for t in finder.tables:
                    tables.append([[str(c or "").strip() for c in row] for row in t.extract()])

            pages.append({
                "page_no": i + 1,
                "text": text,
                "tables": tables,
                "width": float(page.rect.width),
                "height": float(page.rect.height),
            })

    return {"page_count": len(pages), "pages": pages}

PUT /api/pdf/{file_id}/edit

{
  "page_no": 1,
  "table_index": 0,
  "rows": [["Col1", "Col2"], ["A", "B"]],
  "notes": "manual correction"
}