Wikipedia structured data with chunks

Wikipedia Scraper [$0.7💰/1k] | RAG & AI Training

ahmed_jasarevic/wikipedia-scraper

Extract structured data from Wikipedia articles — infoboxes, sections, tables and full text. Build knowledge graphs, RAG pipelines and AI training datasets from the world's largest encyclopedia.

Article/News Extractor

tropical_prune/article-news-extractor

CAPABILITIES: extract_article, extract_metadata, detect_language, clean_text, batch_urls. INPUT: URLs (single or array) of articles/news pages. OUTPUT: structured JSON with title, author, date, content, language, word_count. FORMATS: json, markdown, text. PRICING: PPE $0.001/article.

Extract Wikipedia articles via MediaWiki API. Get full text, summaries, sections, categories, images, links. Multi-language. Perfect for AI/ML training data and RAG.

Wikipedia Scraper - Articles, Summaries & Full Text for AI/RAG

flash_scraper/wikipedia-scraper

Wikipedia full text scraper: search by keyword or fetch exact titles in 300+ languages and get the intro summary or the full article plaintext plus word count, categories, thumbnail and URL. Free, keyless MediaWiki API. Built for RAG, LLM training and research. CSV/JSON/Excel.

RagChunk: Semantic RAG Splitter & Markdown Cleaner

flaretool/rag-semantic-chunker

Extract, clean, and semantically split documentation URLs into token-safe chunks for Vector DBs. Built-in HTML boilerplate stripping saves up to 40% on LLM token costs.

Scrape Wikipedia across 300+ languages. Modes: full articles, summaries, search, random, recent changes, category browse. Extracts text, sections, references, images, links, infobox. Official MediaWiki API — stable, no auth. Great for research, knowledge graphs, content enrichment.

Google Search MCP Server

datascoutapi/google-search-mcp-server

🚀 Google Search MCP Server scrapes real-time Google SERPs by processing search queries. Extract organic results, ads, People Also Ask, related queries, prices, and reviews. Supports 21+ countries, 25+ languages. Export data in JSON, Excel, or CSV. Ideal for SEO, research, and automation.

Google Search Results Scraper

datascoutapi/google-search-results-scraper

🚀 Google Search Engine Scraper API – Extract real-time Google search results easily. Get organic results, paid ads, People Also Ask, Related Queries, reviews, and prices. Supports 25+ languages & 21+ countries. Export structured results in JSON, Excel, or CSV for SEO & market research.

Turn any public web page or shallow site crawl into clean, LLM-ready Markdown + metadata + optional RAG chunks. Boilerplate/nav/ads removed. Honors robots.txt.

Webpage Text Extractor

automation-lab/webpage-text-extractor

This actor fetches web pages and extracts their clean text content by stripping all HTML tags, scripts, and styles. It identifies the main content area (article, main, etc.), extracts headings structure, page links, and metadata like author, publish date, and language. Use it for LLM input...

Scrape Wikipedia articles by search term or exact titles via the official MediaWiki API — summary extract, page image, canonical URL and last-edited date. Keyless, clean JSON, no personal data.