Scrape Instagram with AI

# Scrape Instagram — SoloStack Skill File
> Drop this file into your SoloStack repo and Claude Code will use it as
> context to run this workflow automatically.
---
## Overview
Extract Instagram posts, profiles, followers, and hashtag data using Apify actors and Claude Code.
**Apify Actor:** `apify/instagram-scraper`
**Pricing:** ~$1.00 per 1,000 profiles
## Capabilities
1. **Profile Data Extraction** — Pull username, full name, bio, follower/following counts, post count, profile picture URL, verification status, and account category.
2. **Post & Reel Scraping** — Extract recent posts with captions, likes, comments, timestamps, media URLs, tagged accounts, and location tags.
3. **Hashtag Research** — Scrape top and recent posts for any hashtag. Discover post volume, average engagement, and top contributors for content strategy.
4. **Engagement Rate Calculation** — Automatically calculate engagement rates (likes + comments / followers) to identify genuinely influential accounts vs vanity metrics.
5. **Comment Extraction** — Pull individual comments with commenter usernames and timestamps for sentiment analysis and community research.
6. **Location-Based Discovery** — Scrape posts tagged at specific locations — restaurants, events, landmarks — to find local influencers and user-generated content.
## Pipeline
1. **Target accounts** — Provide usernames, hashtags, or location tags — or define criteria like follower range, niche, and engagement threshold
2. **Scrape profiles & posts** — Apify extracts full profile bios, follower counts, post content, engagement metrics, and media URLs
3. **Analyze & rank** — Calculate true engagement rates, identify fake followers, and rank accounts by influence quality and relevance
4. **Export or outreach** — Push ranked influencer lists to your CRM or generate outreach templates with personalized talking points
## Use Cases
- **Influencer discovery & vetting:** Find influencers in any niche by hashtag, location, or follower range. Calculate real engagement rates and flag accounts with fake followers before you spend budget on partnerships.
- **Brand monitoring:** Track competitor posting frequency, content themes, and engagement trends over time. Get alerts when competitors launch new campaigns or shift their messaging strategy.
- **Hashtag & content research:** Analyze which hashtags drive the most engagement in your niche. Discover trending content formats, optimal posting times, and caption styles that resonate with your target audience.
- **User-generated content sourcing:** Find customers and fans posting about your brand or products. Collect UGC with proper attribution for repurposing in ads, email campaigns, and social proof on your website.
## Warnings
- Instagram private accounts cannot be scraped. Only public profiles and posts are accessible. Expect 10-15% of discovered accounts to be private.
- Instagram's API changes frequently. Apify maintains their actors, but occasional downtime (1-2 days) can occur after major Instagram updates.
- Engagement rates below 1% on accounts with 10K+ followers often indicate purchased followers. Always cross-reference engagement quality before outreach.
## Sample Output
```json
{
  "username": "yogawith_mia",
  "fullName": "Mia Rodriguez",
  "bio": "Yoga teacher & wellness coach \ud83e\uddd8\u200d\u2640\ufe0f\nOnline classes & retreats\nBali | LA | NYC\nLink below for free 7-day challenge",
  "followers": 67420,
  "following": 892,
  "postsCount": 1245,
  "isVerified": false,
  "category": "Health/Beauty",
  "profilePicUrl": "https://instagram.com/...",
  "externalUrl": "https://yogawithmia.com",
  "engagementRate": 5.2,
  "recentPosts": [
    {
      "caption": "Morning flow with a view. This sequence is perfect for...",
      "likes": 3421,
      "comments": 187,
      "timestamp": "2026-03-05T08:30:00Z",
      "type": "carousel",
      "hashtags": ["yoga", "morningyoga", "yogaflow", "wellness"],
      "location": "Ubud, Bali"
    }
  ]
}
```
Download the complete skill file with full implementation details,
agent prompts, and ready-to-run scripts.