Extract text content from a PDF using the Instaparser PDF API. Use when the user wants to parse or extract text from a PDF URL or file.From its SKILL.md
npx -y skills add Instapaper/instaparser-claude-plugin --skill pdfAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, as published. Nobody here has run it
Instaparser PDF Extraction
Extract text content from a PDF document using the Instaparser PDF API.
Instructions
- Determine whether the source is a URL or a local file path, then make the appropriate API request using curl via the Bash tool.
For a PDF URL, use the GET method:
curl -s -G "https://www.instaparser.com/api/1/pdf" \
-H "Authorization: Bearer ${user_config.INSTAPARSER_API_KEY}" \
--data-urlencode "url=<URL>"
For a local file, use the POST method with multipart form-data:
curl -s -X POST "https://www.instaparser.com/api/1/pdf" \
-H "Authorization: Bearer ${user_config.INSTAPARSER_API_KEY}" \
-F "file=@/path/to/file.pdf"
Before uploading a local file, verify it exists. Only include the output parameter if the user explicitly requests a format. Valid values are text, html, or markdown.
- Present the results clearly:
- Show the title and word count as metadata
- Display the extracted body text
The PDF API uses 5 credits per page.