Skip to content
Office Oxide

提取表格

Office Oxide 将表格视为 IR 的一等元素：DOCX 中的每个 <w:tbl>、XLSX 中的每个区间、PPTX 中的每个 <a:tbl> 都会以带类型的 Table { rows: [[cell, ...]] } 形式返回。一个循环即可处理这三种格式。

遍历文档中的所有表格

Rust

use office_oxide::Document;
use office_oxide::ir::Element;

let doc = Document::open("report.docx")?;
let ir = doc.to_ir();

for section in &ir.sections {
    for el in &section.elements {
        if let Element::Table(t) = el {
            for row in &t.rows {
                println!("{row:?}");
            }
        }
    }
}

Python

from office_oxide import Document

with Document.open("report.docx") as doc:
    ir = doc.to_ir()

for section in ir["sections"]:
    for el in section["elements"]:
        if el["kind"] == "Table":
            for row in el["rows"]:
                print(row)

JavaScript

using doc = Document.open('report.docx');
const ir = doc.toIr();

for (const section of ir.sections) {
  for (const el of section.elements) {
    if (el.kind === 'Table') {
      for (const row of el.rows) {
        console.log(row);
      }
    }
  }
}

Go

doc, err := officeoxide.Open("report.docx")
if err != nil { log.Fatal(err) }
defer doc.Close()

irJSON, _ := doc.ToIRJSON()
var ir struct {
    Sections []struct {
        Elements []struct {
            Kind string     `json:"kind"`
            Rows [][]string `json:"rows"`
        } `json:"elements"`
    } `json:"sections"`
}
json.Unmarshal([]byte(irJSON), &ir)

for _, section := range ir.Sections {
    for _, el := range section.Elements {
        if el.Kind == "Table" {
            for _, row := range el.Rows {
                fmt.Println(row)
            }
        }
    }
}

C#

using OfficeOxide;
using System.Text.Json;

using var doc = Document.Open("report.docx");
using var ir = JsonDocument.Parse(doc.ToIrJson());

foreach (var section in ir.RootElement.GetProperty("sections").EnumerateArray())
{
    foreach (var el in section.GetProperty("elements").EnumerateArray())
    {
        if (el.GetProperty("kind").GetString() != "Table") continue;
        foreach (var row in el.GetProperty("rows").EnumerateArray())
        {
            Console.WriteLine(string.Join(" | ", row.EnumerateArray().Select(c => c.GetString())));
        }
    }
}

C

int err = 0;
OfficeDocumentHandle *doc = office_document_open("report.docx", &err);
char *ir_json = office_document_to_ir_json(doc, &err);   /* DocumentIR as JSON */
if (ir_json) {
    /* parse ir_json with your JSON lib, then walk sections -> elements,
       keeping every element whose "kind" == "Table" and iterating its "rows" */
    office_oxide_free_string(ir_json);
}
office_document_free(doc);

WASM

import { WasmDocument } from 'office-oxide-wasm';

const data = new Uint8Array(await (await fetch('/report.docx')).arrayBuffer());
const doc = new WasmDocument(data, 'docx');
try {
  const ir = doc.toIr();   // JS object, schema == Rust DocumentIR
  for (const section of ir.sections) {
    for (const el of section.elements) {
      if (el.kind === 'Table') {
        for (const row of el.rows) {
          console.log(row);
        }
      }
    }
  }
} finally {
  doc.free();
}

XLSX：每个工作表区间对应一张表

对于电子表格，每个 section 对应一个 worksheet，表格映射到检测到的已用区间。空单元格输出为空字符串；合并单元格展开为左上角的值，其余位置留空。

Python

import csv
from office_oxide import Document

with Document.open("budget.xlsx") as doc:
    ir = doc.to_ir()

for section in ir["sections"]:
    sheet_name = section.get("title", "Sheet")
    out_path = f"{sheet_name}.csv"
    with open(out_path, "w", newline="") as f:
        w = csv.writer(f)
        for el in section["elements"]:
            if el["kind"] == "Table":
                for row in el["rows"]:
                    w.writerow(row)

若需要更细粒度的单元格访问（公式、合并单元格、命名区域），可使用格式专属 API：

Python

with Document.open("budget.xlsx") as doc:
    xlsx = doc.as_xlsx()
    for sheet in xlsx.sheets():
        print(sheet.name(), sheet.dimensions())

DOCX：表格与段落交错排列

IR 保留了段落和表格的原始顺序，因此可以还原文档的阅读流程：

Python

from office_oxide import Document

with Document.open("report.docx") as doc:
    ir = doc.to_ir()

for section in ir["sections"]:
    for el in section["elements"]:
        if el["kind"] == "Heading":
            print(f"\n## {el['text']}")
        elif el["kind"] == "Paragraph":
            print(" ".join(r["text"] for r in el["runs"]))
        elif el["kind"] == "Table":
            for row in el["rows"]:
                print("|", " | ".join(row), "|")

PPTX：表格位于幻灯片 section 内

每张幻灯片都是独立的 section。遍历 section 即可逐张幻灯片恢复上下文：

Python

with Document.open("deck.pptx") as doc:
    ir = doc.to_ir()

for i, section in enumerate(ir["sections"], 1):
    for el in section["elements"]:
        if el["kind"] == "Table":
            print(f"slide {i}: {len(el['rows'])}×{len(el['rows'][0])} table")

需要单元格类型而非字符串时

IR 中的表格表示会将单元格扁平化为字符串。若要在 XLSX 中区分数字、文本和布尔值，请使用格式专属访问器：

Python

with Document.open("budget.xlsx") as doc:
    xlsx = doc.as_xlsx()
    for sheet in xlsx.sheets():
        for cell in sheet.cells():
            print(cell.address(), cell.value(), cell.value_type())

相关链接