instagram-caption-scraper

v1.0.0

Scrapes and returns the caption from any public Instagram post or reel URL. Use this when the user shares an Instagram link and wants to extract, read, summa...

1· 150·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for rdk14/instagram-caption-scraper.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "instagram-caption-scraper" (rdk14/instagram-caption-scraper) from ClawHub.
Skill page: https://clawhub.ai/rdk14/instagram-caption-scraper
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install instagram-caption-scraper

ClawHub CLI

Package manager switcher

npx clawhub@latest install instagram-caption-scraper
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description match the implementation: the script extracts the shortcode from /p/ or /reel/ URLs and uses instaloader to fetch caption and basic metadata. There are no unrelated requirements (no cloud credentials, no access to other services).
Instruction Scope
SKILL.md instructs the agent to run the included python script with a provided Instagram URL and to display the raw caption before any summary. The script only reads the provided URL (or stdin/argv) and performs a network fetch to Instagram via the instaloader library; it does not reference other files, environment variables, or external endpoints.
Install Mechanism
This is an instruction-only skill with a requirements.txt pointing to instaloader==4.14.1 (PyPI). Installing a PyPI dependency is expected for a Python scraper; this is moderate-risk compared with no installs but there are no downloads from unknown hosts or archive extraction. Note: the SKILL.md includes a dependency declaration (python3 + instaloader) while registry metadata listed no required binaries — a minor metadata inconsistency.
Credentials
No environment variables or credentials are required by default. The README and script comment mention optionally adding Instagram login credentials to access private posts; that would require the user to provide credentials (prefer secure storage instead of embedding credentials in the script). The current skill does not attempt to access any unrelated secrets or config paths.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request permanent presence or modify other skills or system-wide settings. The instaloader library may create session/cache files if you log in, but the skill itself does not persist or alter agent configuration.
Assessment
This skill is coherent with its stated purpose: it runs a Python script that uses the well-known instaloader package to fetch captions from public Instagram posts. Before installing, consider: (1) installing packages from PyPI carries routine risk — verify the instaloader version and source; (2) the tool will make HTTP requests to instagram.com (expected), may be rate-limited or blocked, and cannot access private posts without login; (3) do NOT paste Instagram credentials into the script file — if you need to log in, use secure credential storage or the library's recommended session handling; (4) because it's an instruction-only skill, it only runs when invoked, so limit use to cases where a user supplies a valid Instagram URL. If you want higher assurance, inspect the included instagram_scraper.py file (provided) and review the instaloader package release notes for the pinned version.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fe6saqe2fzsac4hapfzz19n8368xb
150downloads
1stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Instagram Caption Scraper

Purpose

Extract the caption text from a public Instagram post or reel URL provided by the user.

When to Use This Skill

Trigger this skill when the user:

  • Shares an Instagram URL containing /p/ or /reel/
  • Says "get the caption", "what does this post say", "read this reel", "summarise this Instagram post"
  • Wants to translate, rewrite, or analyse an Instagram caption

How to Run

Execute the following shell command, replacing {{url}} with the Instagram URL:

python3 {{skill_dir}}/instagram_scraper.py {{url}}

The script will return one of:

  • CAPTION: <text> — successfully extracted caption with metadata
  • ERROR: <reason> — failure with explanation

Example Triggers

Output Format

On success the script returns:

CAPTION: <full caption text>

---
Owner   : @username
Type    : GraphImage / GraphVideo / GraphSidecar
Likes   : 1234
Shortcode: ABC123

Rules

  • Only trigger when a valid Instagram URL (/p/ or /reel/) is present
  • Never fabricate or guess caption content if the script returns an error
  • If the post is private, inform the user and suggest they check the account's privacy settings
  • Always display the full caption before offering any summary or analysis
  • If the user asks to summarise or translate, do so AFTER displaying the raw caption

Setup Notes

Requires Python 3.8+ and the instaloader library:

pip3 install instaloader==4.14.1

Comments

Loading comments...