langchain-hs-0.0.2.0: Haskell implementation of Langchain
Copyright(c) 2025 Tushar Adhatrao
LicenseMIT
MaintainerTushar Adhatrao <tusharadhatrao@gmail.com>
Stabilityexperimental
Safe HaskellNone
LanguageHaskell2010

Langchain.Tool.WebScraper

Description

WebScraper is a tool that scrapes text content from a given URL. It fetches the HTML content of the page, extracts the body text, removes scripts, and strips classidstyle attributes from the HTML tags. It is designed to be used with the Langchain framework for building language models and applications.

Synopsis

Documentation

data WebScraper Source #

Represents a web scraper tool that extracts content from web pages

Constructors

WebScraper 

Instances

Instances details
Show WebScraper Source # 
Instance details

Defined in Langchain.Tool.WebScraper

Tool WebScraper Source #

Implement the Tool typeclass for WebScraper

Instance details

Defined in Langchain.Tool.WebScraper

Associated Types

type Input WebScraper 
Instance details

Defined in Langchain.Tool.WebScraper

type Output WebScraper 
Instance details

Defined in Langchain.Tool.WebScraper

type Input WebScraper Source # 
Instance details

Defined in Langchain.Tool.WebScraper

type Output WebScraper Source # 
Instance details

Defined in Langchain.Tool.WebScraper

data WebPageInfo Source #

Stores the extracted webpage information

Constructors

WebPageInfo 

Instances

Instances details
ToJSON WebPageInfo Source # 
Instance details

Defined in Langchain.Tool.WebScraper

Generic WebPageInfo Source # 
Instance details

Defined in Langchain.Tool.WebScraper

Associated Types

type Rep WebPageInfo 
Instance details

Defined in Langchain.Tool.WebScraper

type Rep WebPageInfo = D1 ('MetaData "WebPageInfo" "Langchain.Tool.WebScraper" "langchain-hs-0.0.2.0-inplace" 'False) (C1 ('MetaCons "WebPageInfo" 'PrefixI 'True) (S1 ('MetaSel ('Just "pageTitle") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "pageContent") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 Text)))
Show WebPageInfo Source # 
Instance details

Defined in Langchain.Tool.WebScraper

type Rep WebPageInfo Source # 
Instance details

Defined in Langchain.Tool.WebScraper

type Rep WebPageInfo = D1 ('MetaData "WebPageInfo" "Langchain.Tool.WebScraper" "langchain-hs-0.0.2.0-inplace" 'False) (C1 ('MetaCons "WebPageInfo" 'PrefixI 'True) (S1 ('MetaSel ('Just "pageTitle") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "pageContent") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 Text)))

fetchAndScrape :: Text -> IO (Either String WebPageInfo) Source #

Fetch HTML content from a URL and extract webpage information