9router-web-fetch
This skill routes web content extraction through multiple providers—Firecrawl, Jina Reader, Tavily, and Exa—returning structured markdown, text, or HTML output. Configure your preferred provider or use auto-fallback chaining to ensure reliable scraping and article parsing.
9router-web-fetch extracts webpage content and converts it to markdown, text, or HTML via multiple providers.
AI-generated summary based on this skill's SKILL.md
Install
decolua/9router/9router-web-fetch · repository language: JavaScript
git clone https://github.com/decolua/9router
cp -r 9router/skills/9router-web-fetch ~/.claude/skills/9router-web-fetchnpx skillfed install decolua/9router/9router-web-fetchFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does 9router-web-fetch fetch webpage content as markdown?
9router-web-fetch routes your request through multiple providers—Firecrawl, Jina Reader, Tavily, and Exa—to extract and convert webpage content into structured markdown format. You can configure your preferred provider or enable auto-fallback chaining to automatically try the next provider if one fails, ensuring reliable content extraction.
What providers does 9router-web-fetch use for web scraping?
9router-web-fetch supports Firecrawl, Jina Reader, Tavily, and Exa as extraction providers. Each provider has different strengths for scraping URLs and converting content to markdown or text. The skill lets you select a specific provider or use automatic fallback to chain through providers until one succeeds.
Can 9router-web-fetch scrape URL and convert to text without rendering?
Yes. 9router-web-fetch accesses web content via API without requiring client-side rendering. It fetches article or page text directly and converts it to your chosen format—markdown, text, or HTML—making it ideal for programmatic content processing and analysis.
What output formats does 9router-web-fetch support?
9router-web-fetch returns structured markdown, plain text, or HTML output depending on your configuration. This flexibility lets you extract webpage content in the format best suited for downstream tasks like content analysis, article parsing, or data processing.
How does the auto-fallback feature work in 9router-web-fetch?
9router-web-fetch chains multiple providers automatically when auto-fallback is enabled. If your configured primary provider fails to scrape a URL, the skill tries the next provider in sequence until one successfully extracts the webpage content, improving reliability for web scraping operations.
Is 9router-web-fetch open source?
Yes, 9router-web-fetch is released under the MIT license, making it free to use, modify, and distribute for both commercial and personal projects.
SKILL.md
rendered from the published skill — quoted content, verbatim
9Router — Web Fetch
Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.
Discover
curl $NINEROUTER_URL/v1/models/web | jq '.data[] | select(.kind=="webFetch") | .id'
# Per-provider params
curl "$NINEROUTER_URL/v1/models/info?id=firecrawl/fetch"
IDs end in /fetch (e.g. firecrawl/fetch, jina/fetch). fetch-combo chains providers with auto-fallback.
Endpoint
POST $NINEROUTER_URL/v1/web/fetch
| Field | Required | Notes |
|---|---|---|
model (or provider) |
yes | from /v1/models/web (e.g. firecrawl or jina-reader) |
url |
yes | URL to extract |
format |
no | markdown (default) / text / html |
max_characters |
no | truncate output |
Examples
Jina Reader
```bash curl -X POST $NINEROUTER_URL/v1/web/fetch \ -H
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/9router-web-fetch/SKILL.md