Pangolin SERP & Scrape#

New canonical (AI SERP): https://clawhub.ai/pangolinfo/pangolinfo-ai-serp

Amazon skill: https://clawhub.ai/pangolinfo/pangolinfo-amazon-scraper

Search Google and scrape Amazon programmatically via Pangolin APIs. Extract AI overviews, organic search results, Amazon product data, and page screenshots.

Prerequisites#

• Python 3.6+ (uses only standard library)

• Pangolin account at pangolinfo.com

• Environment variables (one of):

  • PANGOLIN_TOKEN -- existing bearer token
  • PANGOLIN_EMAIL + PANGOLIN_PASSWORD -- for automatic login

Quick Start#

AI Mode Search (Google AI Overview)#

bash

python3 scripts/pangolin.py --q "what is quantum computing" --mode ai-mode

Standard SERP with AI Overview#

bash

python3 scripts/pangolin.py --q "how does java work" --mode serp --screenshot

Multi-Turn Dialogue#

bash

python3 scripts/pangolin.py --q "python web frameworks" --mode ai-mode \
  --follow-up "compare flask vs django" \
  --follow-up "which is better for beginners"

Amazon Product Detail#

bash

python3 scripts/pangolin.py --url "https://www.amazon.com/dp/B0DYTF8L2W" --mode amazon

Amazon Keyword Search#

bash

python3 scripts/pangolin.py --q "wireless mouse" --mode amazon --parser amzKeyword

Workflow#

1. Authenticate -- Token resolved from env var, cache ( ~/.pangolin_token), or fresh login
2. Choose API mode -- ai-mode | serp | amazon
3. Execute -- Script builds the request, calls the API with retry logic
4. Parse output -- Structured JSON to stdout

Usage#

AI Mode ( --mode ai-mode)#

Uses parserName: "googleAISearch" with udm=50 to get Google AI Mode results.

bash

python3 scripts/pangolin.py --q "explain machine learning" --mode ai-mode

Output includes ai_overview with content paragraphs and source references.

AI Overview SERP ( --mode serp)#

Uses parserName: "googleSearch" for standard SERP results with AI overview extraction.

bash

python3 scripts/pangolin.py --q "best programming languages 2025" --mode serp

Output includes both organic_results and optional ai_overview.

Multi-Turn Follow-Up#

Add follow-up questions to an AI Mode search. Keep to 5 or fewer for optimal performance (more is allowed but slower):

bash

python3 scripts/pangolin.py --q "kubernetes" --mode ai-mode \
  --follow-up "how to deploy" \
  --follow-up "monitoring tools" \
  --follow-up "cost optimization"

Amazon ( --mode amazon)#

Scrape Amazon product data using various parsers.

Product detail by URL:

bash

python3 scripts/pangolin.py --url "https://www.amazon.com/dp/B0DYTF8L2W" --mode amazon

Keyword search:

bash

python3 scripts/pangolin.py --q "mechanical keyboard" --mode amazon --parser amzKeyword

Best sellers:

bash

python3 scripts/pangolin.py --url "https://www.amazon.com/gp/bestsellers/electronics" \
  --mode amazon --parser amzBestSellers

With custom zipcode and raw HTML:

bash

python3 scripts/pangolin.py --url "https://www.amazon.com/dp/B0DYTF8L2W" \
  --mode amazon --zipcode 90210 --format rawHtml

Available Amazon parsers:

ParserUse CaseamzProductDetailSingle product page (default)amzKeywordKeyword search resultsamzProductOfCategoryCategory listingamzProductOfSellerSeller's productsamzBestSellersBest sellers rankingamzNewReleasesNew releases rankingamzFollowSellerProduct variants / other sellers

Authentication Only#

bash

python3 scripts/pangolin.py --auth-only

Raw API Response#

bash

python3 scripts/pangolin.py --q "test" --mode ai-mode --raw

All CLI Options#

text

--q QUERY          Search query
--url URL          Target URL (for Amazon product pages, category pages, etc.)
--mode MODE        ai-mode (default) | serp | amazon
--screenshot       Capture page screenshot (Google only)
--follow-up TEXT   Follow-up question (repeatable, ai-mode only)
--num N            Number of results (default: 10, Google only)
--parser PARSER    Amazon parser name (default: amzProductDetail)
--zipcode CODE     Amazon zipcode (default: 10041)
--format FMT       Amazon response format: json (default) | rawHtml | markdown
--auth-only        Authenticate and show token info
--raw              Output raw API response

Choosing the Right API#

FeatureAI ModeSERPAmazonParsergoogleAISearch``googleSearch``amz* (7 types)Input--q``--q``--url or --qPrimary outputAI-generated answerOrganic results + AI overviewProduct dataMulti-turnYes (via --follow-up)NoNoScreenshotYesYesNoBest forAI answersSearch results with AI contextProduct & market dataCost2 credits2 credits1 credit (json) / 0.75 (raw)

Output Format#

Google (ai-mode / serp)#

json

{
  "success": true,
  "task_id": "...",
  "results_num": 1,
  "ai_overview_count": 1,
  "ai_overview": [{"content": ["..."], "references": [{"title": "...", "url": "...", "domain": "..."}]}],
  "organic_results": [{"title": "...", "url": "...", "text": "..."}],
  "screenshot": "https://..."
}

Amazon#

json

{
  "success": true,
  "task_id": "...",
  "url": "https://www.amazon.com/dp/...",
  "results_count": 1,
  "product": {"asin": "...", "title": "...", "price": "...", "star": "...", "rating": "..."}
}

See reference files for full response schemas.

Exit Codes#

CodeMeaning0Success1API error (non-zero response code)2Usage error (invalid arguments)3Network error4Authentication error

Troubleshooting#

ProblemSolutionAuth failsCheck PANGOLIN_EMAIL and PANGOLIN_PASSWORD env varsEmpty AI overviewNot all queries trigger AI overview; try informational queriesToken invalid (1004)Script auto-refreshes; ensure email/password env vars are setInsufficient credits (2001)Top up at pangolinfo.comTimeoutScript retries 3x with backoff; check networkAmazon returns emptyVerify the URL and parser match (e.g. product URL + amzProductDetail)

See references/error-codes.md for the full error code reference.

Deep-Dive Documentation#

ReferenceContentreferences/ai-mode-api.mdAI Mode API schema, multi-turn dialogue mechanismreferences/ai-overview-serp-api.mdAI Overview SERP API schema, organic result structurereferences/amazon-api.mdAmazon Scrape API, all parser types, product fieldsreferences/error-codes.mdError codes, auth lifecycle, credit management