visio 파일(.vsdx 확장자)은 다이어그램 생성 소프트웨어인 Microsoft Visio와 연결됩니다. 다이어그램의 구조, 레이아웃 및 그래픽 요소에 대한 정보를 저장합니다. 이 형식은 비즈니스, 엔지니어링, 컴퓨터 과학과 같은 분야에서 시각화를 생성하고 공유하는 것을 용이하게 합니다.Visio 파일에는 여러 페이지가 포함될 수 있습니다. 일부는 다른 페이지의 배경으로 사용될 수 있으며 이는 여러 레이어에 걸쳐 발생할 수 있습니다. 이 로더는 각 페이지와 관련 페이지에서 텍스트 콘텐츠를 추출하여 OCR 알고리즘이 수행하는 것과 유사하게 각 페이지에서 모든 표시 텍스트를 추출할 수 있습니다. 경고 : .vsdx 확장자를 가진 Visio 파일만 이 로더와 호환됩니다. .vsd 등과 같은 확장자를 가진 파일은 압축된 XML로 변환할 수 없기 때문에 호환되지 않습니다.
Copy
from langchain_community.document_loaders import VsdxLoader
Copy
loader = VsdxLoader(file_path="./example_data/fake.vsdx")
documents = loader.load()
Copy
for i, doc in enumerate(documents):
print(f"\n------ 페이지 {doc.metadata['page']} ------")
print(f"제목 페이지 : {doc.metadata['page_name']}")
print(f"소스 : {doc.metadata['source']}")
print("\n==> 콘텐츠 <== ")
print(doc.page_content)
Copy
------ 페이지 0 ------
제목 페이지 : Summary
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Best Caption of the worl
This is an arrow
This is Earth
This is a bounded arrow
------ 페이지 1 ------
제목 페이지 : Glossary
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
------ 페이지 2 ------
제목 페이지 : blanket page
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
This file is a vsdx file
First text
Second text
Third text
------ 페이지 3 ------
제목 페이지 : BLABLABLA
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Another RED arrow wow
Arrow with point but red
Green line
User
Captions
Red arrow magic !
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
This is a page with something...
WAW I have learned something !
This is a page with something...
WAW I have learned something !
X2
------ 페이지 4 ------
제목 페이지 : What a page !!
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
Another RED arrow wow
Arrow with point but red
Green line
User
Captions
Red arrow magic !
------ 페이지 5 ------
제목 페이지 : next page after previous one
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Another RED arrow wow
Arrow with point but red
Green line
User
Captions
Red arrow magic !
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor
- incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in
voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa
*
qui officia deserunt mollit anim id est laborum.
------ 페이지 6 ------
제목 페이지 : Connector Page
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
------ 페이지 7 ------
제목 페이지 : Useful ↔ Useless page
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
Title of this document : BLABLABLA
------ 페이지 8 ------
제목 페이지 : Alone page
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Black cloud
Unidirectional traffic primary path
Unidirectional traffic backup path
Encapsulation
User
Captions
Bidirectional traffic
Alone, sad
Test of another page
This is a "bannier"
Tests of some exotics characters : ãäåāă ü╔ ¼ Ç ◘○♂♫♀î♥
This is ethernet
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
This is an empty case
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor
- incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in
voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa
*
qui officia deserunt mollit anim id est laborum.
------ 페이지 9 ------
제목 페이지 : BG
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Best Caption of the worl
This is an arrow
This is Earth
This is a bounded arrow
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
------ 페이지 10 ------
제목 페이지 : BG + caption1
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Another RED arrow wow
Arrow with point but red
Green line
User
Captions
Red arrow magic !
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
Useful↔ Useless page
Tests of some exotics characters : ãäåāă ü╔ ¼ Ç ◘○♂♫♀î♥
------ 페이지 11 ------
제목 페이지 : BG+
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
------ 페이지 12 ------
제목 페이지 : BG WITH CONTENT
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. - Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
This is a page with a lot of text
------ 페이지 13 ------
제목 페이지 : 2nd caption with ____________________________________________________________________ content
소스 : ./example_data/fake.vsdx
==> 콘텐츠 <==
Created by
Created the
Modified by
Modified the
Version
Title
Florian MOREL
2024-01-14
FLORIAN Morel
Today
0.0.0.0.0.1
This is a title
Another RED arrow wow
Arrow with point but red
Green line
User
Captions
Red arrow magic !
Something white
Something Red
This a completely useless diagram, cool !!
But this is for example !
This diagram is a base of many pages in this file. But it is editable in file "BG WITH CONTENT"
Only connectors on this page. This is the CoNNeCtor page
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.