功能描述

Analyze Instagram profiles and posts with detailed engagement metrics, view-to-follower ratios, and Reels-focused analytics including JSON/CSV export.

使用说明 (SKILL.md)

Instagram Analyzer

Name: Instagram Analyzer Wulongcha
Author: wulooongcha

A comprehensive Instagram profile and post analysis tool with engagement metrics, view tracking, and Reels-focused analytics.

name: instagram-analyzer-wulongcha description: "Analyze Instagram profiles and posts with engagement metrics, view counts, follower ratios, and Reels analytics. Use when: user wants to analyze Instagram data, check engagement rates, or extract Reels information." homepage: https://clawhub.com metadata: { "openclaw": { "emoji": "📊", "requires": { "bins": ["python3", "chromium"] } } }

🎯 Features

📊 Single Post Analysis

✅ Like count
✅ Comment count
✅ Save count
✅ View count (Reels)
✅ Follower count
✅ View-to-Follower ratio (%)
✅ Time posted (hours/days ago)

👤 Profile Analysis

✅ Minimum 60 posts analyzed
✅ Reels-focused analytics
✅ All Reels links extraction
✅ Engagement rate calculations
✅ JSON/CSV export

🔧 Technical

🌐 Browser simulation with Playwright
🛡️ Stealth mode (human behavior)
📁 Structured JSON/CSV output
⚡ Batch processing support

🚀 Usage

Profile Analysis (Default: Reels Only! 🎯)

# Full profile analysis - REELS FOCUS (default behavior)
analyze-profile "username"

# With custom post count
analyze-profile "username" --posts 60

# All posts (including regular posts)
analyze-profile "username" --include-posts

Single Post Analysis

# Analyze a Reel/post URL
analyze-post "https://www.instagram.com/reel/ABC123xyz/"

# With JSON output
analyze-post "https://www.instagram.com/reel/ABC123xyz/" --output json

📊 Output Examples

Single Post Response

{
  "post_type": "reel",
  "url": "https://www.instagram.com/reel/ABC123xyz/",
  "username": "example_user",
  "metrics": {
    "views": 125000,
    "likes": 8542,
    "comments": 312,
    "saves": 892,
    "followers": 125000,
    "shares": 156
  },
  "ratios": {
    "view_to_follower_percent": 100.0,
    "like_to_view_percent": 6.83,
    "comment_to_view_percent": 0.25,
    "save_to_view_percent": 0.71
  },
  "timing": {
    "posted_at": "2026-02-11T14:30:00",
    "time_ago": "6 hours ago",
    "age_hours": 6
  }
}

Profile Analysis Response

{
  "profile": {
    "username": "example_user",
    "full_name": "Example User",
    "followers": 125000,
    "following": 1500,
    "posts_count": 450,
    "is_verified": false
  },
  "analysis_summary": {
    "total_posts_analyzed": 60,
    "reels_analyzed": 45,
    "analysis_mode": "reels_only",
    "total_views": 5420000,
    "average_views": 120444,
    "average_engagement_rate": 8.2,
    "top_reels": [...],
    "reels_links": [
      "https://www.instagram.com/reel/ABC123/",
      "https://www.instagram.com/reel/DEF456/",
      ...
    ]
  },
  "engagement_breakdown": {
    "avg_likes": 8542,
    "avg_comments": 312,
    "avg_saves": 892,
    "engagement_rate": 7.8
  }
}

📈 Engagement Metrics Explained

Metric	Formula	Interpretation
View Rate	(Views / Followers) × 100	How many followers actually watched
Engagement Rate	((Likes + Comments + Saves) / Views) × 100	Overall audience interaction
Like Rate	(Likes / Views) × 100	Content appreciation
Save Rate	(Saves / Views) × 100	Content value indicator

⚙️ Configuration

Edit config/analyzer_config.json:

{
  "scraper": {
    "headless": false,
    "min_followers": 1000,
    "posts_to_analyze": 60,
    "scroll_pause": 2,
    "timeout": 30000
  },
  "browser": {
    "stealth_mode": true,
    "human_behavior": true,
    "user_agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_0 like Mac OS X)"
  },
  "output": {
    "default_format": "json",
    "save_reels_links": true,
    "export_csv": true
  }
}

📁 File Outputs

Profile data: data/profiles/{username}.json
Post analysis: data/posts/{post_id}.json
Batch results: data/output/batch_{timestamp}.json
Reels links: data/output/{username}_reels.txt

🔧 Troubleshooting

Login Required

Some metrics require login (view count, saves)
Configure Instagram credentials in .env

Rate Limiting

Increase scroll_pause in config
Reduce batch size
Use multiple accounts

Missing Data

Check if account is private
Verify post exists and is accessible
Instagram may hide some metrics

📝 Requirements

Python 3.8+
Playwright
Chromium browser
BeautifulSoup4
lxml parser

安全使用建议

This repository looks like a local Playwright-based Instagram scraper and is internally coherent for that purpose, but there are a few red flags to review before you run it: - Playwright/Chromium: The tool requires Playwright and a Chromium browser (requirements.txt and SKILL.md instruct installing them). Expect the installer to download browser binaries. If you have network or security policies, run the install in a controlled environment. - Credentials: SKILL.md and config mention putting Instagram credentials in a .env or config file, but the registry manifest does not declare any required env vars. If you provide credentials, store them securely (not in shared repos) and prefer a throwaway or read-only account. Confirm how the script uses/stores credentials and that it does not send them to any external server. - Data handling: The tool writes analysis to data/ directories. Confirm the output path and remove sensitive data after use if needed. - Legal and policy: Automated scraping of Instagram can violate terms of service. Ensure you have permission to access accounts and data you analyze. - Missing/placeholder behavior: parts of the script are simplified or placeholder (e.g., get_follower_count returns 0). Ask the author for clarification on how follower counts and logged-in scraping are implemented. What would increase confidence: clear declaration of required env vars (and how credentials are used/kept local), documented login flow and secure credential handling, and confirmation there's no network traffic to non-Instagram/standard endpoints. If you can't get those answers, run the tool in an isolated VM/container and avoid using primary/personal Instagram credentials.

功能分析

Type: OpenClaw Skill Name: instagram-analyzer-wulongcha Version: 1.0.0 The Instagram Analyzer skill bundle is a legitimate tool designed for scraping and analyzing Instagram profile and post metrics using Playwright and BeautifulSoup. The code in `scripts/instagram_analyzer.py` implements standard scraping logic, such as browser automation, page scrolling, and data extraction, with results stored locally in the `data/` directory. No evidence of data exfiltration, malicious execution, or prompt injection was found; the tool's behavior is entirely consistent with its stated purpose.

能力评估

ℹ Purpose & Capability

Name/description align with the code and SKILL.md: it implements Instagram post/profile analysis using Playwright. However, SKILL.md metadata lists required binaries (python3, chromium) while the registry metadata lists none — an inconsistency. The code requires Playwright/Chromium (via requirements.txt and runtime comments), which is expected for this purpose but should be declared.

⚠ Instruction Scope

Runtime instructions and SKILL.md ask users to configure Instagram credentials in a .env and to run CLI-like commands; the code performs browser automation (page.goto, page.content, selectors) and writes local files. The SKILL.md suggests login is needed for some metrics but the repository does not declare or document how credentials are supplied securely, nor are credentials listed in requires.env. The skill also suggests using multiple accounts for rate-limiting which implies asking for additional credentials — this broadens scope without justification.

ℹ Install Mechanism

There is no explicit install spec in the registry (instruction-only), which limits automatic installation risk. But requirements.txt and SKILL.md indicate Playwright and Chromium must be installed (including running 'playwright install chromium'). This requires downloading browsers at runtime (standard for Playwright) — not inherently malicious but higher friction and a network download that users should expect.

⚠ Credentials

The skill requests credentials in SKILL.md/config (instagram.username/password in config/analyzer_config.json and a suggestion to use .env), but the registry manifest declares no required env vars or primary credential. This mismatch is important: credentials may be needed for functionality but are not declared. The code also reads INSTAGRAM_ANALYZER_CONFIG env var if set. Requesting user Instagram credentials is proportionate to a scraper, but the skill doesn't explicitly declare or explain secure handling, storage, or transmission of those credentials.

✓ Persistence & Privilege

The skill is not forced-always, is user-invocable, and does not request system-wide privileges. It writes outputs to its own data/ directories; no evidence it modifies other skills or global agent settings.

版本历史

v1.0.0

Initial release of Instagram Analyzer – comprehensive tool for Instagram profile and post analytics. - Analyze individual Reels and posts for likes, comments, saves, views, follower counts, and ratios (view-to-follower, like-to-view, etc.). - Profile analytics with Reels-focused summaries, engagement metrics, minimum 60 posts analyzed, and links extraction. - Structured JSON/CSV exports of analyzed data. - Uses Playwright browser automation with stealth human-like behavior. - Batch processing and configurable scraping options. - Requires Python 3.8+, Chromium, Playwright, BeautifulSoup4, and lxml.

元数据

Slug instagram-analyzer-wulongcha

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题