Document Loader Python Packages

langchain-urlpipe

LangChain integration for URLpipe: agent tools that read any web page (JavaScript included), metadata, console errors, Lighthouse, and a document loader.

dompruner

Token-efficient web content extraction for Python. DOM AST pruning + BM25 section filtering cuts LLM context by 90%+ — LangChain-compatible, no API key required.

capslane

Python SDK for Capslane YouTube transcripts, with an optional LangChain document loader and timestamp citations.

langchain-google-classroom

A LangChain community document loader for Google Classroom. Extract coursework, materials, and Drive attachments for RAG pipelines.

langchain-proxyhat

Route LangChain web access through ProxyHat residential proxies — ProxyHatLoader + fetch tool with geo-targeting and sticky sessions.

tooltrace-langchain

LangChain integration for ToolTrace: a document loader for RAG pipelines plus agent tools for extraction, metadata, SEO audits and tech stack detection

langchain-quanticdata

LangChain integration for QuanticData — document loaders, a live-web retriever and a 9-tool agent toolkit: scraping to Markdown, SERP search, crawl/map, SEO audits and 74 ready-made collectors.

langchain-synapsoft

LangChain integration package for Synap DocuAnalyzer

ocrcontext

Intelligent document OCR and structured extraction. Turn PDFs and images into typed JSON with zero vendor lock-in.