Review Site Scraper
Scrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback from review sites.
by Athina AInpx gooseworks install --all # then, in Claude Code, Cursor, or Codex: /gooseworks use the review-site-scraper skill
Review Site Scraper
Scrape product reviews from G2, Capterra, and Trustpilot using platform-specific Apify actors.
Quick Start
Requires APIFY_API_TOKEN env var (or --token flag). No external dependencies needed (uses stdlib urllib).
# Trustpilot reviews
python3 skills/capabilities/review-site-scraper/scripts/scrape_reviews.py \
--platform trustpilot \
--url "https://www.trustpilot.com/review/example.com" \
--max-reviews 10 --output summary
# G2 reviews with keyword filter
python3 skills/capabilities/review-site-scraper/scripts/scrape_reviews.py \
--platform g2 \
--url "https://www.g2.com/products/example/reviews" \
--keywords "pricing,support"
# Capterra reviews (uses company name, not URL)
python3 skills/capabilities/review-site-scraper/scripts/scrape_reviews.py \
--platform capterra \
--company-name "HubSpot CRM" \
--max-reviews 20Supported Platforms
| Platform | Actor | Input | Cost |
|---|---|---|---|
| G2 | focused_vanguard/g2-reviews-scraper | --url (G2 product page URL) | Free tier available |
| Capterra | getdataforme/capterra-reviews-scraper-bulk | --company-name (company name, not a URL) | Pay-per-result |
| Trustpilot | agents/trustpilot-reviews | --url (Trustpilot review page URL) | ~$0.20/1k reviews |
CLI Reference
| Flag | Default | Description |
|---|---|---|
--platform | required | g2, capterra, or trustpilot |
--url | none | Product review page URL (required for G2 and Trustpilot) |
--company-name | none | Company name to search (Capterra only) |
--max-reviews | 50 | Max reviews to scrape |
--keywords | none | Keywords to filter (comma-separated, OR logic) |
--days | none | Only include reviews from last N days |
--output | json | Output format: json or summary |
--token | env var | Apify token (prefer APIFY_API_TOKEN env var) |
--timeout | 300 | Max seconds for Apify run |
Normalized Output Schema
All platforms are normalized but each has platform-specific fields.
G2 output fields:
{
"platform": "g2",
"id": "review-id",
"product_name": "Product Name",
"title": null,
"text": "Review body text",
"rating": 4,
"author": "Reviewer Name",
"author_title": "Job Title",
"author_company": "Company Name",
"author_company_size": "51-200",
"author_industry": "Software",
"date": "2026-02-18",
"source": "organic",
"url": "https://..."
}Capterra output fields:
{
"platform": "capterra",
"title": "Review title",
"text": "Review body text",
"overall_rating": 4,
"ease_of_use": 5,
"customer_service": 3,
"features": 4,
"author": "Reviewer Name",
"job_title": "Marketing Manager",
"industry": "Marketing and Advertising",
"usage_duration": "1-2 years",
"date": "2026-02-18",
"url": "https://..."
}Trustpilot output fields:
{
"platform": "trustpilot",
"id": "review-id",
"title": "Review title",
"text": "Review body text",
"rating": 4,
"author": "Reviewer Name",
"date": "2026-02-18T12:00:00.000Z",
"experienced_date": "2026-02-15T00:00:00.000Z",
"likes": 2,
"input_source": "organic",
"url": "https://..."
}Video Production Harness
Full video production sequence with script review, actual ingredient choices, controlled generation, editing, evidence-based quality review, polish, captions and delivery. A host binding supplies project storage, authentic approvals, provider access and billing.
Render Street Interview
Build a vox-pop street interview video ad. An interviewer with a handheld mic asks passers-by one question about the brand's product, they give blunt wrong guesses, one gives the real answer, and the cut lands on a branded end card. Generates the takes through the GooseWorks fal proxy (Seedance 2.0 with native voice), then grades, re-cuts, captions and gates them locally. Use for the street-interview format.
Write Video Ad Script
Write the words of a short-form video ad (voiceover, dialogue, chat bubbles, on-screen lines) the way performance creative teams do instead of from a blank page. Builds the script from the buyers' own words, the beat sheet of an ad that already works and three deliberately different angles, filters them with a rule check and a second non-Claude model, and takes the strongest into the review with the other two as one-line swaps. Use it in every video ad run before any paid step, and whenever the user asks to write, rewrite or improve a video ad script or says a script sounds generic or AI-written.