如何获取目录树
当您想要获取文档目录树(即大纲结构)时，您可以参考以下教程和示例代码。这里为您提供了一份Textin官方pdf示例文件，您可点击下载或使用该链接：文档解析pdf示例.pdf
- 参考快速启动，在 options 中设置URL参数 catalog_details=1，API会在返回结果中包含目录相关信息。
- 在main函数中添加以下示例代码，获取API输出的目录信息，并保存为 json 文件。
# 解析JSON响应
json_response = json.loads(response)
if "result" in json_response and "catalog" in json_response["result"]:
catalog = json_response["result"]["catalog"]
# 保存为json文件
with open("catalog.json", "w", encoding="utf-8") as f:
json.dump(catalog, f, ensure_ascii=False, indent=2)
print("目录已保存为 catalog.json")
else:
print("未检测到目录字段，可能文档没有目录或参数设置有误。")
return
- 请注意：为了更加灵活的支持下游业务场景，文档解析API的目录返回结果中通过hierarchy字段表示目录的标题层级，但并没有目录之间直接的父子层级关系，您可以参考以下示例代码获取标题目录间的父子层级关系，以构建目录树状结构。
toc_list = catalog['toc']
result = []
parent_stack = [] # 用于跟踪当前路径上的父节点
for item in toc_list:
# 复制当前项目，避免修改原始数据
current_item = item.copy()
current_item['children'] = []
current_level = item.get('hierarchy', 1)
# 根据层级调整父节点栈
# 移除层级大于等于当前层级的节点
while parent_stack and parent_stack[-1]['hierarchy'] >= current_level:
parent_stack.pop()
# 如果有父节点，将当前项目添加到父节点的children中
if parent_stack:
parent_stack[-1]['children'].append(current_item)
else:
# 如果没有父节点，说明是根节点
result.append(current_item)
# 将当前项目添加到父节点栈中
parent_stack.append(current_item)
print(result)
# 保存处理后的目录结构为json文件
with open("processed_catalog.json", "w", encoding="utf-8") as f:
json.dump(result, f, ensure_ascii=False, indent=2)
print("处理后的目录结构已保存为 processed_catalog.json")
return result
- 处理后的目录结构如下，标题目录间有了父子层级关系，您可以据此构建标题目录的树状结构。
[
{
"title": "Textin",
"hierarchy": 1,
"page_id": 1,
"paragraph_id": 0,
"pos": [
276,
228,
467,
228,
467,
272,
276,
272
],
"pos_list": [
[
276,
228,
467,
228,
467,
272,
276,
272
]
],
"sub_type": "text_title",
"children": []
},
{
"pos": [
371,
382,
906,
382,
906,
450,
371,
450
],
"pos_list": [
[
371,
382,
906,
382,
906,
450,
371,
450
]
],
"sub_type": "text_title",
"title": "标准参考样例",
"hierarchy": 1,
"page_id": 1,
"paragraph_id": 2,
"children": []
},
{
"paragraph_id": 3,
"pos": [
214,
564,
974,
564,
974,
657,
214,
657
],
"pos_list": [
[
214,
564,
974,
564,
974,
657,
214,
657
]
],
"sub_type": "text_title",
"title": "本科毕业论文模板",
"hierarchy": 1,
"page_id": 1,
"children": []
},
{
"sub_type": "text_title",
"title": "目录",
"hierarchy": 1,
"page_id": 2,
"paragraph_id": 0,
"pos": [
571,
198,
685,
198,
685,
228,
571,
228
],
"pos_list": [
[
571,
198,
685,
198,
685,
228,
571,
228
]
],
"children": []
},
{
"title": "第一章 背景介绍",
"hierarchy": 1,
"page_id": 3,
"paragraph_id": 0,
"pos": [
456,
212,
733,
212,
733,
241,
456,
241
],
"pos_list": [
[
456,
212,
733,
212,
733,
241,
456,
241
]
],
"sub_type": "text_title",
"children": [
{
"page_id": 3,
"paragraph_id": 2,
"pos": [
342,
413,
657,
413,
657,
440,
342,
440
],
"pos_list": [
[
342,
413,
657,
413,
657,
440,
342,
440
]
],
"sub_type": "text_title",
"title": "第1节 模板使用说明",
"hierarchy": 2,
"children": [
{
"title": "1.1.如何使用样式？",
"hierarchy": 3,
"page_id": 3,
"paragraph_id": 5,
"pos": [
179,
798,
411,
798,
411,
820,
179,
820
],
"pos_list": [
[
179,
798,
411,
798,
411,
820,
179,
820
]
],
"sub_type": "text_title",
"children": []
}
]
},
{
"title": "第2节 如何刷新目录",
"hierarchy": 2,
"page_id": 3,
"paragraph_id": 7,
"pos": [
342,
1019,
657,
1019,
657,
1046,
342,
1046
],
"pos_list": [
[
342,
1019,
657,
1019,
657,
1046,
342,
1046
]
],
"sub_type": "text_title",
"children": [
{
"hierarchy": 3,
"page_id": 3,
"paragraph_id": 9,
"pos": [
177,
1286,
747,
1286,
747,
1308,
177,
1308
],
"pos_list": [
[
177,
1286,
747,
1286,
747,
1308,
177,
1308
]
],
"sub_type": "text_title",
"title": "2.1．为什么我写了新的章节后没有新的目录项出现？",
"children": []
},
{
"title": "2.2. 如何排版文章章节",
"hierarchy": 3,
"page_id": 4,
"paragraph_id": 1,
"pos": [
176,
221,
445,
221,
445,
243,
176,
243
],
"pos_list": [
[
176,
221,
445,
221,
445,
243,
176,
243
]
],
"sub_type": "text_title",
"children": []
},
{
"paragraph_id": 4,
"pos": [
176,
522,
423,
522,
423,
543,
176,
543
],
"pos_list": [
[
176,
522,
423,
522,
423,
543,
176,
543
]
],
"sub_type": "text_title",
"title": "2.3. 其他的一些样式",
"hierarchy": 3,
"page_id": 4,
"children": []
},
{
"sub_type": "text_title",
"title": "2.4.如何使用其他的高级功能？",
"hierarchy": 3,
"page_id": 4,
"paragraph_id": 6,
"pos": [
176,
684,
531,
684,
531,
704,
176,
704
],
"pos_list": [
[
176,
684,
531,
684,
531,
704,
176,
704
]
],
"children": []
}
]
}
]
},
{
"title": "第二章 正文要求说明",
"hierarchy": 1,
"page_id": 5,
"paragraph_id": 0,
"pos": [
422,
210,
766,
210,
766,
241,
422,
241
],
"pos_list": [
[
422,
210,
766,
210,
766,
241,
422,
241
]
],
"sub_type": "text_title",
"children": [
{
"hierarchy": 2,
"page_id": 5,
"paragraph_id": 2,
"pos": [
384,
412,
642,
412,
642,
439,
384,
439
],
"pos_list": [
[
384,
412,
642,
412,
642,
439,
384,
439
]
],
"sub_type": "text_title",
"title": "第1节 字体和大小",
"children": [
{
"hierarchy": 3,
"page_id": 5,
"paragraph_id": 3,
"pos": [
176,
496,
349,
496,
349,
518,
176,
518
],
"pos_list": [
[
176,
496,
349,
496,
349,
518,
176,
518
]
],
"sub_type": "text_title",
"title": "1.1．文章标题",
"children": []
},
{
"pos": [
176,
636,
324,
636,
324,
657,
176,
657
],
"pos_list": [
[
176,
636,
324,
636,
324,
657,
176,
657
]
],
"sub_type": "text_title",
"title": "1.2. 章标题",
"hierarchy": 3,
"page_id": 5,
"paragraph_id": 5,
"children": []
},
{
"hierarchy": 3,
"page_id": 5,
"paragraph_id": 7,
"pos": [
176,
775,
324,
775,
324,
795,
176,
795
],
"pos_list": [
[
176,
775,
324,
775,
324,
795,
176,
795
]
],
"sub_type": "text_title",
"title": "1.3. 节标题",
"children": []
},
{
"title": "1.4．子节标题",
"hierarchy": 3,
"page_id": 5,
"paragraph_id": 9,
"pos": [
176,
913,
349,
913,
349,
934,
176,
934
],
"pos_list": [
[
176,
913,
349,
913,
349,
934,
176,
934
]
],
"sub_type": "text_title",
"children": []
},
{
"title": "1.5.正文",
"hierarchy": 3,
"page_id": 5,
"paragraph_id": 11,
"pos": [
176,
1054,
300,
1054,
300,
1076,
176,
1076
],
"pos_list": [
[
176,
1054,
300,
1054,
300,
1076,
176,
1076
]
],
"sub_type": "text_title",
"children": []
}
]
}
]
},
{
"title": "第三章 公式排版",
"hierarchy": 1,
"page_id": 6,
"paragraph_id": 0,
"pos": [
457,
211,
733,
211,
733,
241,
457,
241
],
"pos_list": [
[
457,
211,
733,
211,
733,
241,
457,
241
]
],
"sub_type": "text_title",
"children": [
{
"hierarchy": 2,
"page_id": 6,
"paragraph_id": 2,
"pos": [
297,
412,
731,
412,
731,
441,
297,
441
],
"pos_list": [
[
297,
412,
731,
412,
731,
441,
297,
441
]
],
"sub_type": "text_title",
"title": "第1节 Microsoft Equation Editor",
"children": []
},
{
"page_id": 6,
"paragraph_id": 4,
"pos": [
366,
641,
637,
641,
637,
669,
366,
669
],
"pos_list": [
[
366,
641,
637,
641,
637,
669,
366,
669
]
],
"sub_type": "text_title",
"title": "第2节 MathType",
"hierarchy": 2,
"children": []
}
]
},
{
"pos_list": [
[
359,
163,
644,
163,
644,
189,
359,
189
]
],
"sub_type": "text_title",
"title": "第3节 TeX/LaTeX",
"hierarchy": 1,
"page_id": 7,
"paragraph_id": 0,
"pos": [
359,
163,
644,
163,
644,
189,
359,
189
],
"children": []
},
{
"pos": [
442,
210,
750,
210,
750,
241,
442,
241
],
"pos_list": [
[
442,
210,
750,
210,
750,
241,
442,
241
]
],
"sub_type": "text_title",
"title": "第四章 图形和表格",
"hierarchy": 1,
"page_id": 8,
"paragraph_id": 0,
"children": [
{
"pos": [
428,
350,
602,
350,
602,
376,
428,
376
],
"pos_list": [
[
428,
350,
602,
350,
602,
376,
428,
376
]
],
"sub_type": "text_title",
"title": "第1节 图形",
"hierarchy": 2,
"page_id": 8,
"paragraph_id": 1,
"children": [
{
"sub_type": "image_title",
"title": "图表1.1这是一幅牛的图片",
"hierarchy": 3,
"page_id": 8,
"paragraph_id": 4,
"pos": [
471,
847,
719,
847,
719,
865,
471,
865
],
"pos_list": [
[
471,
847,
719,
847,
719,
865,
471,
865
]
],
"children": []
}
]
},
{
"pos": [
401,
1087,
602,
1087,
602,
1114,
401,
1114
],
"pos_list": [
[
401,
1087,
602,
1087,
602,
1114,
401,
1114
]
],
"sub_type": "text_title",
"title": "第2节 表格",
"hierarchy": 2,
"page_id": 8,
"paragraph_id": 6,
"children": [
{
"sub_type": "table_title",
"title": "插入表格与图片类似。当然，可以使用Excel预先作一个表格，然后导入进来，但是word本身也可以胜任一部分简单表格的绘制，如：",
"hierarchy": 3,
"page_id": 8,
"paragraph_id": 8,
"pos": [
179,
1167,
1011,
1167,
1011,
1231,
179,
1231
],
"pos_list": [
[
179,
1167,
1011,
1167,
1011,
1231,
179,
1231
]
],
"children": []
},
{
"hierarchy": 3,
"page_id": 8,
"paragraph_id": 10,
"pos": [
479,
1372,
713,
1372,
713,
1391,
479,
1391
],
"pos_list": [
[
479,
1372,
713,
1372,
713,
1391,
479,
1391
]
],
"sub_type": "table_title",
"title": "表格2.1一个简单的表格",
"children": []
}
]
}
]
},
{
"sub_type": "text_title",
"title": "第五章 定理环境",
"hierarchy": 1,
"page_id": 9,
"paragraph_id": 0,
"pos": [
456,
208,
734,
208,
734,
242,
456,
242
],
"pos_list": [
[
456,
208,
734,
208,
734,
242,
456,
242
]
],
"children": [
{
"pos_list": [
[
357,
452,
673,
452,
673,
478,
357,
478
]
],
"sub_type": "text_title",
"title": "第1节 自定义定理环境",
"hierarchy": 2,
"page_id": 9,
"paragraph_id": 2,
"pos": [
357,
452,
673,
452,
673,
478,
357,
478
],
"children": [
{
"page_id": 9,
"paragraph_id": 4,
"pos": [
176,
581,
411,
581,
411,
603,
176,
603
],
"pos_list": [
[
176,
581,
411,
581,
411,
603,
176,
603
]
],
"sub_type": "text_title",
"title": "定理1.1．对顶角相等。",
"hierarchy": 3,
"children": []
},
{
"hierarchy": 3,
"page_id": 9,
"paragraph_id": 6,
"pos": [
176,
683,
581,
683,
581,
706,
176,
706
],
"pos_list": [
[
176,
683,
581,
683,
581,
706,
176,
706
]
],
"sub_type": "text_title",
"title": "定理1.2．三边对应相等的三角形全等。",
"children": []
}
]
},
{
"page_id": 9,
"paragraph_id": 9,
"pos": [
371,
925,
631,
925,
631,
951,
371,
951
],
"pos_list": [
[
371,
925,
631,
925,
631,
951,
371,
951
]
],
"sub_type": "text_title",
"title": "第2节 已有环境",
"hierarchy": 2,
"children": []
},
{
"pos_list": [
[
357,
1255,
645,
1255,
645,
1282,
357,
1282
]
],
"sub_type": "text_title",
"title": "第3节 自定义环境",
"hierarchy": 2,
"page_id": 9,
"paragraph_id": 14,
"pos": [
357,
1255,
645,
1255,
645,
1282,
357,
1282
],
"children": []
}
]
}
]