Web Scraping & Data Collection Habilidades de Claude

YouTube Transcript Downloader

Downloads, cleans, and polishes YouTube video transcripts and captions into structured markdown files.

LinkedIn Lead Finder

Identifies hiring managers and key decision-makers on LinkedIn to streamline job outreach and lead generation.

Production Pyspider Crawler SOP

Streamlines Pyspider crawler development and refactoring using production-grade strategy patterns and strict engineering redlines.

Tavily Web Search

Integrates real-time web search and content extraction capabilities into Claude Code using the Tavily API.

Structured Output Fabric

Transforms unstructured text from any source into clean, validated JSON based on specific user-defined fields or schemas.

Brave Web Search & Extraction

Performs headless web searches and extracts clean markdown content using the Brave Search API without requiring a browser.

YouTube Video Downloader

Downloads YouTube videos and audio with customizable quality and format settings using yt-dlp.

Web Research (Dual AI)

Conducts deep technical research using Gemini and Codex to provide verified information while preserving Claude's context window.

PySpider Task Manager

Automates web scraping task creation and management across social media, e-commerce, and SEO platforms via Feishu API integration.

Job Filtering & Lead Deduplication

Filters, deduplicates, and scores job listings to isolate high-quality technical roles from direct employers.

Firecrawl Scraper

Automates deep web scraping, PDF parsing, and website crawling using the Firecrawl API to extract structured content.

Europeana Collections Search

Searches over 50 million cultural heritage items from thousands of European museums, libraries, and archives.

Summarize Web & Video

Summarizes web pages, YouTube videos, and local files into concise insights directly within your CLI environment.

Harvard Library Catalog

Searches over 13 million bibliographic records from Harvard University libraries to retrieve detailed book metadata and research sources.

Columbia CLIO Catalog Search

Searches Columbia University Libraries' CLIO catalog for books, journals, and manuscripts via its JSON API.

Indeed Germany Job Scraper

Automates the extraction of real-time job listings from Indeed Germany with advanced filtering and deep-dive capabilities.

Firecrawl Scraper

Extracts deep web data, captures screenshots, and parses PDFs using the Firecrawl API for comprehensive data collection.

Web to Markdown

Converts web pages into clean Markdown files for local documentation storage and AI context.

Bright Data Progressive Scraper

Automates web content retrieval using a four-tier escalation strategy to bypass bot detection and CAPTCHAs.

News Summary & AI Insight

Automates multi-source news gathering and generates interactive HTML dashboards with on-demand AI deep-dive analysis.

Competitive Ads Extractor

Extracts and analyzes competitor advertisements from platforms like Facebook and LinkedIn to provide strategic messaging and creative insights.

Bright Data Progressive Scraper

Automates resilient web content extraction using a four-tier fallback strategy to bypass bot detection and JavaScript hurdles.

Scrape.do Web Scraper

Extracts content from websites using the Scrape.do API to bypass anti-bot protections and render dynamic JavaScript.

IPO Tracker & TradingView Watchlist Generator

Tracks recent Initial Public Offerings and generates ready-to-import TradingView watchlists with enriched market data.

YouTube Transcript Downloader

Downloads and processes YouTube video transcripts, captions, and subtitles into clean text or VTT formats.

NotebookLM Research Assistant

Queries your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed documentation answers.

YouTube Video Downloader

Downloads YouTube videos and extracts audio with customizable quality settings and format options.

Google Places CLI Integration

Searches, resolves, and extracts detailed business information using the New Google Places API directly within the terminal.

YouTube & HLS Video Downloader

Downloads high-quality video and audio from YouTube and HLS streaming platforms like Vimeo and Mux using yt-dlp and ffmpeg.

Gemini Web Search

Integrates Google Gemini's web search capabilities into Claude Code for comprehensive, real-time information retrieval.