> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Dropbox 集成

> 使用 LangChain Python 集成 Dropbox 文档加载器。

[Dropbox](https://en.wikipedia.org/wiki/Dropbox) is a file hosting service that brings everything-traditional files, cloud content, and web shortcuts together in one place.

本 notebook 介绍如何load documents from *Dropbox*. In addition to common files such as text and PDF files, it also supports *Dropbox Paper* files.

## 前提条件

1. Create a Dropbox app.
2. Give the app these scope permissions: `files.metadata.read` and `files.content.read`.
3. Generate access token: [www.dropbox.com/developers/apps/create](https://www.dropbox.com/developers/apps/create).
4. `pip install dropbox` (requires `pip install "unstructured[pdf]"` for PDF filetype).

## Instructions

\`DropboxLoader\`\` requires you to create a Dropbox App and generate an access token. This can be done from [www.dropbox.com/developers/apps/create](https://www.dropbox.com/developers/apps/create). You also need to have the Dropbox Python SDK installed (pip install dropbox).

DropboxLoader can load data from a list of Dropbox file paths or a single Dropbox folder path. Both paths should be relative to the root directory of the Dropbox account linked to the access token.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install dropbox
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_community.document_loaders import DropboxLoader
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Generate access token: https://www.dropbox.com/developers/apps/create.
dropbox_access_token = "<DROPBOX_ACCESS_TOKEN>"
# Dropbox root folder
dropbox_folder_path = ""
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
loader = DropboxLoader(
    dropbox_access_token=dropbox_access_token,
    dropbox_folder_path=dropbox_folder_path,
    recursive=False,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
documents = loader.load()
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
File /JHSfLKn0.jpeg could not be decoded as text. Skipping.
File /A REPORT ON WILES’ CAMBRIDGE LECTURES.pdf could not be decoded as text. Skipping.
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
for document in documents:
    print(document)
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [通过 MCP 将这些文档连接到](/use-these-docs) Claude、VSCode 等工具以获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/document_loaders/dropbox.mdx) 或 [提交 issue](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>