agentleFS
Sign inStart free
nearthinknearthink/agent-skills/skills/smart-web-scraper/SKILL.md

smart-web-scraper

Skill0 starsChanged 7 months agoMITView on GitHub

Extract structured data from web pages into clean JSON or CSV.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Default: 1 request per second (respectful crawling)

    line 89
  2. Distinctive:

    No JavaScript rendering (use for static HTML pages)

    line 98

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Smart Web Scraper

Extract structured data from web pages into clean JSON or CSV.

Quick Start

# Scrape a page, extract all text content
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract "https://example.com"

# Extract specific elements with CSS selector
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract "https://example.com/products" -s ".product-card"

# Auto-detect and extract tables
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py tables "https://example.com/pricing"

# Extract all links from a page
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py links "https://example.com"

# Extract structured data (title, meta, headings, links)
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py structure "https://example.com"

# Output as JSON
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract "https://example.com" -s ".item" -f json

# Output as CSV
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract "https://example.com" -s "table tr" -f csv

# Save to file
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract "https://example.com" -s ".product" -f json -o products.json

# Multi-page scrape (follow pagination)
uv run --with beautifulsoup4 --with lxml python scripts/scraper.py crawl "https://example.com/page/1" --pages 5 -s ".article"

Commands

CommandArgsDescription
extract<url> [-s selector] [-f format] [-o file]Extract content, optionally filtered by CSS selector
tables<url> [-f format] [-o file]Auto-detect and extract all HTML tables
links<url> [--external] [--internal]Extract all links (href + text)
structure<url>Extract page structure: title, meta, headings, images, links
crawl<url> --pages N [-s selector] [-f format] [-o file]Follow pagination links, extract from multiple pages

Output Formats

FormatFlagDescription
Text-f textPlain text (default)
JSON-f jsonStructured JSON array
CSV-f csvComma-separated values
Markdown-f mdMarkdown-formatted

Examples

Extract product listings

uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract "https://shop.example.com" -s ".product" -f json

Output:

[
  {"text": "Widget Pro - $29.99", "tag": "div", "class": "product"},
  {"text": "Widget Max - $49.99", "tag": "div", "class": "product"}
]

Extract pricing table

uv run --with beautifulsoup4 --with lxml python scripts/scraper.py tables "https://example.com/pricing" -f csv

Get all external links

uv run --with beautifulsoup4 --with lxml python scripts/scraper.py links "https://example.com" --external

Rate Limiting

  • Default: 1 request per second (respectful crawling)
  • Override with --delay 0.5 (seconds between requests)
  • Respects robots.txt by default (override with --ignore-robots)

Notes

  • Requires beautifulsoup4 and lxml (auto-installed by uv run --with)
  • Uses a standard browser User-Agent to avoid blocks
  • Handles redirects, encoding detection, and error pages gracefully
  • No JavaScript rendering (use for static HTML pages)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free