Product Review Scraper

Review scraper

by gooseworks-ai · MIT license · ★ 1,220 on GitHub · updated Sep 21

Scrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch.

---
name: review-scraper
description: >
  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.
---

# Review 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). Install dependency: `pip install requests`.

```bash
# Trustpilot reviews

Overview

Scrape product reviews from G2, Capterra, and Trustpilot using platform-specific Apify actors.

Manual install (npx, ZIP)

Claude Codenpx skills add gooseworks-ai/goose-skills --skill review-scraper -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/gooseworks-ai/goose-skills/tar.gz/615c685f34f8 \
  | tar -xz -C ~/.claude/skills --strip-components=4 goose-skills-615c685f34f8/skills/monitoring/capabilities/review-scraper

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/92ad90852ad8da7b0144/review-scraper.zip" -OutFile "$env:TEMP\review-scraper.zip"; Expand-Archive "$env:TEMP\review-scraper.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.2 KB
skill.meta.json253 B
scripts/1 file · 10.7 KB

Read the files here

gooseworks-ai/615c6853 files

SKILL.md

Show the full text74 lines

review-scraper/SKILL.md74 lines · 2.2 KB

PreviewCode

Outline

RawView on GitHub

Review 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). Install dependency: pip install requests.

# Trustpilot reviews
python3 skills/review-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/review-scraper/scripts/scrape_reviews.py \
  --platform g2 \
  --url "https://www.g2.com/products/example/reviews" \
  --keywords "pricing,support"

# Capterra reviews
python3 skills/review-scraper/scripts/scrape_reviews.py \
  --platform capterra \
  --url "https://www.capterra.com/p/12345/Example"

Supported Platforms

Platform	Actor	Cost
G2	`zen-studio/g2-reviews-scraper`	Free tier available
Capterra	`imadjourney/capterra-reviews-scraper`	Pay-per-result
Trustpilot	`agents/trustpilot-reviews`	~$0.20/1k reviews

CLI Reference

Flag	Default	Description
`--platform`	required	`g2`, `capterra`, or `trustpilot`
`--url`	required	Product review page URL
`--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 to the same schema:

{
  "platform": "trustpilot",
  "title": "Review title",
  "text": "Review body text",
  "rating": 4,
  "author": "Reviewer Name",
  "date": "2026-02-18",
  "pros": "What they liked (G2/Capterra only)",
  "cons": "What they disliked (G2/Capterra only)",
  "url": "https://..."
}

1	---
2	name: review-scraper
3	description: >
4	Scrape product reviews from G2, Capterra, and Trustpilot using Apify.
5	Single script with platform dispatch. Use when you need to monitor competitor
6	reviews, track product sentiment, or gather customer feedback from review sites.
7	---
8
9	# Review Scraper
10
11	Scrape product reviews from G2, Capterra, and Trustpilot using platform-specific Apify actors.
12
13	## Quick Start
14
15	Requires `APIFY_API_TOKEN` env var (or `--token` flag). Install dependency: `pip install requests`.
16
17	```bash
18	# Trustpilot reviews
19	python3 skills/review-scraper/scripts/scrape_reviews.py \
20	--platform trustpilot \
21	--url "https://www.trustpilot.com/review/example.com" \
22	--max-reviews 10 --output summary
23
24	# G2 reviews with keyword filter
25	python3 skills/review-scraper/scripts/scrape_reviews.py \
26	--platform g2 \
27	--url "https://www.g2.com/products/example/reviews" \
28	--keywords "pricing,support"
29
30	# Capterra reviews
31	python3 skills/review-scraper/scripts/scrape_reviews.py \
32	--platform capterra \
33	--url "https://www.capterra.com/p/12345/Example"
34	```
35
36	## Supported Platforms
37
38	\| Platform \| Actor \| Cost \|
39	\|----------\|-------\|------\|
40	\| G2 \| `zen-studio/g2-reviews-scraper` \| Free tier available \|
41	\| Capterra \| `imadjourney/capterra-reviews-scraper` \| Pay-per-result \|
42	\| Trustpilot \| `agents/trustpilot-reviews` \| ~$0.20/1k reviews \|
43
44	## CLI Reference
45
46	\| Flag \| Default \| Description \|
47	\|------\|---------\|-------------\|
48	\| `--platform` \| required \| `g2`, `capterra`, or `trustpilot` \|
49	\| `--url` \| required \| Product review page URL \|
50	\| `--max-reviews` \| 50 \| Max reviews to scrape \|
51	\| `--keywords` \| none \| Keywords to filter (comma-separated, OR logic) \|
52	\| `--days` \| none \| Only include reviews from last N days \|
53	\| `--output` \| json \| Output format: `json` or `summary` \|
54	\| `--token` \| env var \| Apify token (prefer `APIFY_API_TOKEN` env var) \|
55	\| `--timeout` \| 300 \| Max seconds for Apify run \|
56
57	## Normalized Output Schema
58
59	All platforms are normalized to the same schema:
60
61	```json
62	{
63	"platform": "trustpilot",
64	"title": "Review title",
65	"text": "Review body text",
66	"rating": 4,
67	"author": "Reviewer Name",
68	"date": "2026-02-18",
69	"pros": "What they liked (G2/Capterra only)",
70	"cons": "What they disliked (G2/Capterra only)",
71	"url": "https://..."
72	}
73	```
74