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

# Document loader 集成

> 使用 LangChain Python 与文档加载器集成

文档加载器提供了一种**标准接口**，用于从不同来源（如Slack、Notion或Google Drive）将数据转换为LangChain的@\[Document]格式。
这确保了数据无论来源如何，都能被一致处理。

所有文档加载器均实现@\[`BaseLoader`]接口。

Integration components
Arrows show a typical retrieval flow. The highlighted component is the one this page covers.

### Typical retrieval flow

### Agent capabilities

### Execution and state

> [!WARNING]
>
> 社区文档加载器由用户贡献且未经验证。LangChain不审查或推荐这些集成，请自行评估风险。

## 接口

每个文档加载器可能定义其 own参数，但共享统一API：

* `load()`：一次性加载所有文档。
* `lazy_load()`：惰性流式加载，适用于大数据集。

```python theme={null}
from langchain_docling.loader import DoclingLoader

FILE_PATH = "https://arxiv.org/pdf/2408.09869"

loader = DoclingLoader(file_path=FILE_PATH)

# Load all documents
documents = loader.load()

# For large datasets, lazily load documents
for document in loader.lazy_load():
    print(document)
```

## 按类别

### 办公工具

以下文档加载器支持从常用办公工具加载数据。

| 文档加载器 | API参考 |
| - | - |
| [AgentMail](https://github.com/agentmail-to/langchain-agentmail) | [`AgentMailLoader`](https://github.com/agentmail-to/langchain-agentmail) |
| [Google Classroom](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_classroom.md) | [`GoogleClassroomLoader`](https://pypi.org/project/langchain-google-classroom/) |

### 网页

以下文档加载器支持网页加载。

| 文档加载器 | 描述 | 包装/API |
| - | - | - |
| [Unstructured](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/unstructured_file.md) | 使用Unstructured加载数据并解析网页 | 包装 |
| [Apify Dataset](https://docs.apify.com/integrations/langchain) | 从Apify数据集加载数据 | API |
| [Apify Crawl](https://docs.apify.com/integrations/langchain) | 按需爬取网站并将每页作为Document加载 | API |
| [Diffbot Crawl Loader](https://github.com/diffbot/langchain-diffbot) | 使用Diffbot爬取API将网站每页解析为结构化JSON | API |
| [Diffbot Extract Loader](https://github.com/diffbot/langchain-diffbot) | 使用Diffbot提取API将网页解析为结构化JSON | API |
| [Docling](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/docling.md) | 使用Docling加载数据并解析网页 | 包装 |
| [DomPruner](https://github.com/dong7812/dompruner-py) | DOM AST剪枝：加载为97%+ Token减少的紧凑Markdown，无需API密钥 | 包装 |
| [Firecrawl](https://docs.firecrawl.dev) | 通过爬取/爬取/映射/提取/搜索将网站转换为清洁的LLM数据 | API |
| [Hyperbrowser](https://docs.hyperbrowser.ai) | 头less浏览器平台，支持爬取/爬取任意网站 | API |
| [OpeddFeedLoader](https://opedd.com/for-ai-agents) | 加载带版权溯源的Opedd内容目录作为Document | API |
| [ProxyHatLoader](https://docs.proxyhat.com) | 通过ProxyHat住宅代理加载数据 | API |
| [AgentQL](https://docs.agentql.com/) | 使用AgentQL查询或自然语言提示进行网页交互及结构化数据提取 | API |
| [CRW](https://fastcrw.com) | 兼容Firecrawl的开源爬虫，支持本地二进制或fastcrw\.com云服务 | 包装 |
| [Plasmate](https://docs.plasmate.app/integration-langchain) | Agent原生头less浏览器，支持Set of Mark（SOM）结构化UI提取 | 包装 |
| [Spidra](https://docs.spidra.io) | 带实时浏览器、CAPTCHA破解和结构化数据提取的AI爬虫 | API |

### PDFs

合作伙伴及社区PDF加载器。托管合作伙伴指南列于前。经典加载器来自[`langchain-community`](https://pypi.org/project/langchain-community/)及其他社区包。完整按下载量排序的目录见[所有文档加载器](#所有文档加载器)。

| 文档加载器 | 描述 | 包装/API |
| - | - | - |
| [Unstructured](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/unstructured_file.md) | 使用Unstructured开源库加载数据 | 包装 |
| [Upstage Document Parse Loader](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/upstage.md) | 使用UpstageDocumentParseLoader | 包装 |
| [Docling](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/docling.md) | 使用Docling | 包装 |
| `PyPDFLoader` | 使用`pypdf`（`langchain-community`） | 社区 |
| `PyMuPDFLoader` | 使用PyMuPDF（`langchain-community`） | 社区 |
| `PDFMinerLoader` | 使用PDFMiner（`langchain-community`） | 社区 |
| `PDFPlumberLoader` | 使用pdfplumber（`langchain-community`） | 社区 |
| [MinerU](https://mineru.net) | 使用MinerU加载数据 | 包装 |
| [UnDatasIO](https://undatas.io) | 使用UnDatasIO | 包装 |
| [OpenDataLoader PDF](https://github.com/opendataloader-project/langchain-opendataloader-pdf) | 使用OpenDataLoader PDF | 包装 |
| [CVFileLoader](https://cvfile.org) | 加载CV PDF/A-3u文件，包含嵌入Markdown/HTML/JSON简历 | 包装 |
| [pdfmuse](https://github.com/casperkwok/pdfmuse) | 确定性加载PDF/DOCX，保留坐标、表格及块级元数据 | 包装 |
| [oxidize-pdf](https://github.com/bzsanti/oxidize-pdf-integrations/tree/main/langchain) | 使用Rust引擎进行元素不重叠的RAG分块 | 包装 |
| [pdf-inspector](https://github.com/undacmic/langchain-pdf-inspector) | 使用pdf-inspector | 包装 |

### 云服务提供商

以下文档加载器支持从云服务加载数据。

| 文档加载器 | 描述 | 合作伙伴包装 | API参考/来源 |
| - | - | - | - |
| [Azure Blob Storage](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/azure_blob_storage.md) | 加载Azure Blob Storage容器或单个数据块 | ✅ | [`langchain-ai/langchain-azure`](https://github.com/langchain-ai/langchain-azure/tree/main/libs/azure-storage) |
| [Google Cloud Storage Directory](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_cloud_storage_directory.md) | 加载数据存储桶 | ✅ | [`GCSDirectoryLoader`](https://reference.langchain.com/python/langchain-google-community/gcs_directory/GCSDirectoryLoader) |
| [Google Cloud Storage File](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_cloud_storage_file.md) | 加载数据存储文件对象 | ✅ | [`GCSFileLoader`](https://reference.langchain.com/python/langchain-google-community/gcs_file/GCSFileLoader) |
| [Google Drive](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_drive.md) | 加载Google Drive（仅Google Docs） | ✅ | [`GoogleDriveLoader`](https://reference.langchain.com/python/langchain-google-community/drive/GoogleDriveLoader) |

### 常见文件类型

以下文档加载器支持常见数据格式。

| 文档加载器 | 数据类型 |
| - | - |
| [`Unstructured`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/unstructured_file) | 多种文件类型（见[https://docs.unstructured.io/platform/supported-file-types）](https://docs.unstructured.io/platform/supported-file-types）) |
| [`HwpHwpxLoader`](https://github.com/jaypakdevkr/HWP-Loader) | HWP/HWPX文件 |
| [`DoclingLoader`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/docling) | 多种文件类型（见[https://docling-project.github.io/docling/](https://docling-project.github.io/docling/)) |
| [`PolarisAIDataInsightLoader`](https://datainsight.polarisoffice.com/playground) | 多种文件类型（见[https://datainsight.polarisoffice.com/documentation?docType=doc\_extract）](https://datainsight.polarisoffice.com/documentation?docType=doc_extract）) |

## 所有文档加载器

| 集成 | 下载 |
| :- | :- |
| [`Google bigquery`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_bigquery) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-community/month)](https://pypi.org/project/langchain-google-community/) |
| [`Google cloud storage directory`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_cloud_storage_directory) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-community/month)](https://pypi.org/project/langchain-google-community/) |
| [`Google cloud storage file`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_cloud_storage_file) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-community/month)](https://pypi.org/project/langchain-google-community/) |
| [`Google drive`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_drive) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-community/month)](https://pypi.org/project/langchain-google-community/) |
| [`Google speech-to-text audio transcripts`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_speech_to_text) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-community/month)](https://pypi.org/project/langchain-google-community/) |
| [`Oracle AI vector search document processing`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/oracleai) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-oracledb/month)](https://pypi.org/project/langchain-oracledb/) |
| [`Oracle autonomous database`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/oracleadb_loader) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-oracledb/month)](https://pypi.org/project/langchain-oracledb/) |
| [`UnstructuredLoader`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/unstructured_file) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-unstructured/month)](https://pypi.org/project/langchain-unstructured/) |
| [`AstraDB`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/astradb) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-astradb/month)](https://pypi.org/project/langchain-astradb/) |
| [`Docling`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/docling) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-docling/month)](https://pypi.org/project/langchain-docling/) |
| [`Google alloydb for postgresql`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_alloydb) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-alloydb-pg/month)](https://pypi.org/project/langchain-google-alloydb-pg/) |
| [`PyMuPDF4LLMLoader`](https://github.com/pymupdf/langchain-pymupdf4llm) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-pymupdf4llm/month)](https://pypi.org/project/langchain-pymupdf4llm/) |
| [`ApifyCrawlLoader`](https://docs.apify.com/integrations/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-apify/month)](https://pypi.org/project/langchain-apify/) |
| [`ApifyDatasetLoader`](https://docs.apify.com/integrations/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-apify/month)](https://pypi.org/project/langchain-apify/) |
| [`Upstage`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/upstage) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-upstage/month)](https://pypi.org/project/langchain-upstage/) |
| [`Google cloud SQL for postgresql`](https://docs.cloud.google.com/sql/docs/postgres) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-cloud-sql-pg/month)](https://pypi.org/project/langchain-google-cloud-sql-pg/) |
| [`Google firestore (native mode)`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_firestore) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-firestore/month)](https://pypi.org/project/langchain-google-firestore/) |
| [`Google spanner`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_spanner) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-spanner/month)](https://pypi.org/project/langchain-google-spanner/) |
| [`DoclingLoader`](https://github.com/docling-project/docling.rs/blob/master/crates/docling-py/README.md#langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-docling-rs/month)](https://pypi.org/project/langchain-docling-rs/) |
| [`Azure blob storage loader`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/azure_blob_storage) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-azure-storage/month)](https://pypi.org/project/langchain-azure-storage/) |
| [`FlatmarkLoader`](https://github.com/flatmark-dev/flatmark-integrations/blob/main/langchain/README.md) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-flatmark/month)](https://pypi.org/project/langchain-flatmark/) |
| [`FirecrawlLoader`](https://docs.firecrawl.dev) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-firecrawl/month)](https://pypi.org/project/langchain-firecrawl/) |
| [`OpenDataLoader PDF`](https://github.com/opendataloader-project/langchain-opendataloader-pdf) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-opendataloader-pdf/month)](https://pypi.org/project/langchain-opendataloader-pdf/) |
| [`AnakinLoader`](https://anakin.io/docs/documentation) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-anakin/month)](https://pypi.org/project/langchain-anakin/) |
| [`Docugami`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/docugami) | [  ![Downloads per month](https://static.pepy.tech/badge/docugami-langchain/month)](https://pypi.org/project/docugami-langchain/) |
| [`HwpHwpxLoader`](https://github.com/jaypakdevkr/HWP-Loader) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-hwp-hwpx-loader/month)](https://pypi.org/project/langchain-hwp-hwpx-loader/) |
| [`PDFParser`](https://dev.writer.com/api-reference/tool-api/pdf-parser#parse-pdf) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-writer/month)](https://pypi.org/project/langchain-writer/) |
| [`SingleStoreLoader`](https://github.com/singlestore-labs/langchain-singlestore/) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-singlestore/month)](https://pypi.org/project/langchain-singlestore/) |
| [`YoutubeLoaderDL`](https://github.com/aqib0770/langchain-yt-dlp) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-yt-dlp/month)](https://pypi.org/project/langchain-yt-dlp/) |
| [`SuperPDFLoader`](https://superpdf.ai/docs/python/langchain-llamaindex#langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-superpdf/month)](https://pypi.org/project/langchain-superpdf/) |
| [`MeshArcLoader`](https://mesharc.dev/docs/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-mesharc/month)](https://pypi.org/project/langchain-mesharc/) |
| [`HyperbrowserLoader`](https://www.hyperbrowser.ai/docs/home) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-hyperbrowser/month)](https://pypi.org/project/langchain-hyperbrowser/) |
| [`FastOCRLoader`](https://github.com/fastocr-org/langchain-fastocr#readme) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-fastocr/month)](https://pypi.org/project/langchain-fastocr/) |
| [`ReplyLayerLoader`](https://replylayer.ai/docs/guides/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-replylayer/month)](https://pypi.org/project/langchain-replylayer/) |
| [`HydrafetchLoader`](https://docs.hydrafetch.com) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-hydrafetch/month)](https://pypi.org/project/langchain-hydrafetch/) |
| [`SecureLangChainLoader`](https://github.com/arsbr/Veritensor) | [  ![Downloads per month](https://static.pepy.tech/badge/veritensor/month)](https://pypi.org/project/veritensor/) |
| [`SpidraLoader`](https://docs.spidra.io) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-spidra/month)](https://pypi.org/project/langchain-spidra/) |
| [`PdfInspectorLoader`](https://github.com/undacmic/langchain-pdf-inspector) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-pdf-inspector/month)](https://pypi.org/project/langchain-pdf-inspector/) |
| [`WebCrawlerAPILoader`](https://webcrawlerapi.com/docs/sdk/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/webcrawlerapi-langchain/month)](https://pypi.org/project/webcrawlerapi-langchain/) |
| [`CrwLoader`](https://fastcrw.com) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-crw/month)](https://pypi.org/project/langchain-crw/) |
| [`Google bigtable`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_bigtable) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-bigtable/month)](https://pypi.org/project/langchain-google-bigtable/) |
| [`Outline`](https://github.com/10Pines/langchain-outline) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-outline/month)](https://pypi.org/project/langchain-outline/) |
| [`MinerULoader`](https://mineru.net) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-mineru/month)](https://pypi.org/project/langchain-mineru/) |
| [`DiffbotCrawlLoader`](https://github.com/diffbot/langchain-diffbot) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-diffbot/month)](https://pypi.org/project/langchain-diffbot/) |
| [`DiffbotExtractLoader`](https://github.com/diffbot/langchain-diffbot) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-diffbot/month)](https://pypi.org/project/langchain-diffbot/) |
| [`DomPrunerLoader`](https://github.com/dong7812/dompruner-py) | [  ![Downloads per month](https://static.pepy.tech/badge/dompruner/month)](https://pypi.org/project/dompruner/) |
| [`PolarisAIDataInsightLoader`](https://datainsight.polarisoffice.com/playground) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-polaris-ai-datainsight/month)](https://pypi.org/project/langchain-polaris-ai-datainsight/) |
| [`ProxmintLoader`](https://proxmint.com/docs/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-proxmint/month)](https://pypi.org/project/langchain-proxmint/) |
| [`Google memorystore for Redis`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_memorystore_redis) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-memorystore-redis/month)](https://pypi.org/project/langchain-google-memorystore-redis/) |
| [`OpeddFeedLoader`](https://opedd.com/for-ai-agents) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-opedd/month)](https://pypi.org/project/langchain-opedd/) |
| [`langchain_box`](https://developer.box.com/) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-box/month)](https://pypi.org/project/langchain-box/) |
| [`AnyToMarkdownLoader`](https://pypi.org/project/langchain-anytomarkdown/) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-anytomarkdown/month)](https://pypi.org/project/langchain-anytomarkdown/) |
| [`Web2MDLoader`](https://github.com/kanavsingla28/web2md-clients/tree/main/python#readme) | [  ![Downloads per month](https://static.pepy.tech/badge/web2md-client/month)](https://pypi.org/project/web2md-client/) |
| [`PaddleOCR-VL`](https://www.paddleocr.com) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-paddleocr/month)](https://pypi.org/project/langchain-paddleocr/) |
| [`AlfrescoLoader`](https://github.com/OpenDMA/langchain-opendma/blob/main/docs/Loader.md#alfrescoloader) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-opendma/month)](https://pypi.org/project/langchain-opendma/) |
| [`OpenDMALoader`](https://github.com/OpenDMA/langchain-opendma/blob/main/docs/Loader.md) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-opendma/month)](https://pypi.org/project/langchain-opendma/) |
| [`CommentScraperLoader`](https://comment-scraper.com/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-comment-scraper/month)](https://pypi.org/project/langchain-comment-scraper/) |
| [`Google Classroom`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_classroom) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-classroom/month)](https://pypi.org/project/langchain-google-classroom/) |
| [`Google cloud SQL for mysql`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_cloud_sql_mysql) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-cloud-sql-mysql/month)](https://pypi.org/project/langchain-google-cloud-sql-mysql/) |
| [`Kinetica document loader`](https://github.com/kineticadb/langchain-kinetica) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-kinetica/month)](https://pypi.org/project/langchain-kinetica/) |
| [`Google firestore in datastore mode`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_datastore) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-datastore/month)](https://pypi.org/project/langchain-google-datastore/) |
| [`AgentQLLoader`](https://docs.agentql.com/home) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-agentql/month)](https://pypi.org/project/langchain-agentql/) |
| [`CVFileLoader`](https://cvfile.org) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-cvfile/month)](https://pypi.org/project/langchain-cvfile/) |
| [`ProxyHatLoader`](https://docs.proxyhat.com) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-proxyhat/month)](https://pypi.org/project/langchain-proxyhat/) |
| [`AirbyteLoader`](https://docs.airbyte.com/integrations/) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-airbyte/month)](https://pypi.org/project/langchain-airbyte/) |
| [`CapslaneLoader`](https://capslane.com/integrations/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/capslane/month)](https://pypi.org/project/capslane/) |
| [`PdfmuseLoader`](https://github.com/casperkwok/pdfmuse) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-pdfmuse/month)](https://pypi.org/project/langchain-pdfmuse/) |
| [`LyrenthLoader`](https://lyrenth.com/docs/integrations) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-lyrenth/month)](https://pypi.org/project/langchain-lyrenth/) |
| [`PlasmateSOMLLoader`](https://docs.plasmate.app/integration-langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-plasmate/month)](https://pypi.org/project/langchain-plasmate/) |
| [`Undatasio`](https://undatas.io) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-undatasio/month)](https://pypi.org/project/langchain-undatasio/) |
| [`EnconvertLoader`](https://github.com/enconvert/langchain-enconvert) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-enconvert/month)](https://pypi.org/project/langchain-enconvert/) |
| [`Soniox`](https://soniox.com/docs/stt/concepts/supported-languages) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-soniox/month)](https://pypi.org/project/langchain-soniox/) |
| [`AgentMail`](https://github.com/agentmail-to/langchain-agentmail) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-agentmail/month)](https://pypi.org/project/langchain-agentmail/) |
| [`QuanticDataLoader`](https://quanticdata.io/docs/) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-quanticdata/month)](https://pypi.org/project/langchain-quanticdata/) |
| [`Google cloud SQL for SQL server`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/google_cloud_sql_mssql) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-cloud-sql-mssql/month)](https://pypi.org/project/langchain-google-cloud-sql-mssql/) |
| [`OxidizePdfLoader`](https://github.com/bzsanti/oxidize-pdf-integrations/tree/main/langchain) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-oxidize-pdf/month)](https://pypi.org/project/langchain-oxidize-pdf/) |
| [`XNSBlobLoader`](https://docs.xns.tech) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-xns/month)](https://pypi.org/project/langchain-xns/) |
| [`XNSLoader`](https://docs.xns.tech) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-xns/month)](https://pypi.org/project/langchain-xns/) |
| [`Google el carro for Oracle workloads`](https://github.com/googleapis/langchain-google-el-carro-python/) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-google-el-carro/month)](https://pypi.org/project/langchain-google-el-carro/) |
| [`PowerScaleDocumentLoader`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/powerscale) | [  ![Downloads per month](https://static.pepy.tech/badge/powerscale-rag-connector/month)](https://pypi.org/project/powerscale-rag-connector/) |
| [`SectionAnythingLoader`](https://github.com/Omniwot/section-anything/tree/main/packages/langchain-section-anything) | [  ![Downloads per month](https://static.pepy.tech/badge/langchain-section-anything/month)](https://pypi.org/project/langchain-section-anything/) |
| [`LangSmithLoader`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/document_loaders/langsmith) | N/A |
| [`TranscriptFetchLoader`](https://transcriptfetch.com/docs/langchain) | N/A |

***

> 官方原文：[src/oss/python/integrations/document\_loaders/index.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/document_loaders/index.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.