skills.rest
hexian2001
hexian2001COMMUNITY
Explore all skills by this author →
𝕏@Nepnep_HRPGitHub

soushen-hunter

Perform API-free Bing and Google searches and extract page elements as JSON.

100|3|Updated Mar 4, 2026
Search Tags:#automation#search#playwright#google#web#data-extraction#bing
One-click install
npx skills add https://github.com/hexian2001/soushen-hunter --skill soushen-hunter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: soushen-hunter
Source: https://github.com/hexian2001/soushen-hunter/tree/main
Command: npx skills add https://github.com/hexian2001/soushen-hunter --skill soushen-hunter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) components.

What problem does it solve?

The tool addresses the need for high-performance, API-free web search and deep page element extraction across Bing and Google, enabling structured results and comprehensive page analysis without external API costs.

Core Features & Use Cases

  • Fast, API-free Bing and Google search with structured results (title, url, snippet, source)
  • Deep page analysis extracting links, forms, buttons, scripts, and metadata
  • Configurable engine switching and CLI/API access for automation

Quick Start

Run soushen-hunter with a query to fetch search results and perform a deep-page analysis.

Frequently Asked Questions about soushen-hunter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform web search and extract page elements without using a paid API?▼

You can perform API-free web search and deep page element extraction using Playwright browser automation. It retrieves structured search results and extracts links, forms, scripts, and metadata across Bing or Google without external API costs.

Can I use Playwright to extract forms and scripts from web pages?▼

Yes, Playwright drives the browser automation to extract forms, buttons, scripts, links, and metadata from web pages. It performs deep page analysis and outputs the extracted elements as structured JSON for downstream processing.

Does this tool support both Bing and Google search engines for automation?▼

Yes, the tool supports configurable engine switching between Bing and Google. You can execute automated web searches across either engine and receive structured results containing titles, URLs, snippets, and source data.

What is the best way to get structured JSON results from Bing or Google searches?▼

The best way to get structured JSON results is by using the provided CLI or Python API. You run a query to fetch search results and perform deep-page analysis, which outputs structured JSON containing titles, URLs, and snippets for immediate processing.

How do I integrate automated web search and data extraction into a Python script?▼

You integrate automated web search and data extraction by using the Python API. It leverages Playwright for browser automation, allowing your Python script to execute queries, switch between Bing and Google, and process the JSON output.

Do I need Playwright installed to run automated search and page extraction?▼

Yes, Playwright is a required dependency. It provides the underlying browser automation needed to execute searches, bypass the need for external APIs, and extract deep page elements like forms and scripts.

Related Skills

Explore More Software Engineering Skills→
HsnSaboorHsnSaboor

webapp-testing

Automate local web application testing with Playwright scripts.

Community
Intermediate
semaes111semaes111

search

Retrieve Google search results via Bright Data's SERP API with pagination.

Community
Intermediate
jiahao-shao1jiahao-shao1
5

cmux

Orchestrate terminal sessions across cmux panes to automate workflows.

Community
Advanced
Khamel83Khamel83

search-fallback

Coordinate Tavily, Perplexity, Context7, Brave, and Bing APIs for fallback search results.

Community
Advanced