Spaces:
Sleeping
Sleeping
Upload 4 files
Browse files
README.md
CHANGED
|
@@ -1,15 +1,101 @@
|
|
| 1 |
---
|
| 2 |
-
title: Amazon
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 6.
|
| 8 |
-
python_version: '3.12'
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
-
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Amazon Product Scraper
|
| 3 |
+
short_description: Scrape Amazon products, sellers and search results as JSON
|
| 4 |
+
emoji: 📦
|
| 5 |
+
colorFrom: yellow
|
| 6 |
+
colorTo: blue
|
| 7 |
sdk: gradio
|
| 8 |
+
sdk_version: 6.0.2
|
|
|
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
+
tags:
|
| 12 |
+
- amazon-scraper
|
| 13 |
+
- amazon
|
| 14 |
+
- product-data
|
| 15 |
+
- price-tracking
|
| 16 |
+
- ecommerce
|
| 17 |
+
- web-scraping
|
| 18 |
+
- scraper
|
| 19 |
+
- data-extraction
|
| 20 |
+
- anti-bot
|
| 21 |
+
- proxy
|
| 22 |
+
- smolagents
|
| 23 |
+
- tool
|
| 24 |
+
- scrape.do
|
| 25 |
---
|
| 26 |
|
| 27 |
+
# Amazon Product Scraper — Powered by Scrape.do
|
| 28 |
+
|
| 29 |
+
Pull structured JSON out of any Amazon marketplace: product detail pages, every
|
| 30 |
+
seller offer on an ASIN, and keyword or category search results. No HTML parsing.
|
| 31 |
+
|
| 32 |
+
Powered by the [Scrape.do Amazon Scraper API](https://scrape.do/documentation/amazon-scraper-api/):
|
| 33 |
+
|
| 34 |
+
- Bypasses AWS WAF, CAPTCHAs and rate limits automatically
|
| 35 |
+
- 21 Amazon marketplaces with ZIP-code level delivery targeting
|
| 36 |
+
- Parsed JSON — ASIN, brand, price, list price, rating, images, rankings, specs
|
| 37 |
+
- Organic vs. sponsored flags and exact on-page positions in search
|
| 38 |
+
- 1 credit per successful request
|
| 39 |
+
|
| 40 |
+
## 🔑 Get your free API token
|
| 41 |
+
|
| 42 |
+
👉 **[Sign up free on Scrape.do](https://dashboard.scrape.do/sign-up?utm_source=huggingface&utm_medium=amazon-scraper)** — 1,000 successful requests per month, no credit card required.
|
| 43 |
+
|
| 44 |
+
Paste your token into the UI and start scraping.
|
| 45 |
+
|
| 46 |
+
## Three modes
|
| 47 |
+
|
| 48 |
+
| Tab | Input | Output |
|
| 49 |
+
| --- | --- | --- |
|
| 50 |
+
| **Product page** | Product URL or ASIN | Title, brand, price, list price, rating, images, best seller rankings, technical details |
|
| 51 |
+
| **Seller offers** | Product URL or ASIN | Every active offer with price, condition, seller, fulfilment and Buy Box winner |
|
| 52 |
+
| **Search results** | Keyword + page | Ranked products with ASIN, price, rating, Prime, sponsored flag and badge |
|
| 53 |
+
|
| 54 |
+
Every tab returns the raw JSON response and a CSV download.
|
| 55 |
+
|
| 56 |
+
## Location targeting
|
| 57 |
+
|
| 58 |
+
Amazon shows different prices, stock and delivery depending on where the buyer is.
|
| 59 |
+
|
| 60 |
+
- **ZIP-level marketplaces** (`us`, `gb`, `de`, `fr`, `it`, `es`, `ca`, `jp`, `in`) — enter a postal code in the **Delivery location** field.
|
| 61 |
+
- **Country-level marketplaces** (`tr`, `br`, `au`, `mx`, `nl`, `pl`, `se`, `ae`, `sa`, `sg`, `eg`, `be`) — enter a delivery country name, or leave it blank to use the marketplace default.
|
| 62 |
+
|
| 63 |
+
ZIP format is validated per marketplace, so `SW1A 1AA` works for `gb` but not for `us`.
|
| 64 |
+
|
| 65 |
+
## Use as a smolagents Tool
|
| 66 |
+
|
| 67 |
+
```python
|
| 68 |
+
from smolagents import CodeAgent, InferenceClientModel
|
| 69 |
+
from tool import ScrapeDoAmazonTool
|
| 70 |
+
|
| 71 |
+
agent = CodeAgent(
|
| 72 |
+
tools=[ScrapeDoAmazonTool(api_token="YOUR_SCRAPEDO_TOKEN")],
|
| 73 |
+
model=InferenceClientModel(),
|
| 74 |
+
)
|
| 75 |
+
agent.run("Compare the price and Buy Box seller for ASIN B0BLRJ4R8F in the US and the UK")
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
You can also set `SCRAPE_DO_API_TOKEN` in your environment and instantiate
|
| 79 |
+
`ScrapeDoAmazonTool()` without arguments.
|
| 80 |
+
|
| 81 |
+
## Inputs
|
| 82 |
+
|
| 83 |
+
- `mode` *(required)* — `product`, `offers` or `search`.
|
| 84 |
+
- `query` *(required)* — Product URL or ASIN for `product` and `offers`; keyword for `search`.
|
| 85 |
+
- `geocode` *(optional)* — Marketplace country code, defaults to `us`.
|
| 86 |
+
- `zipcode` *(optional)* — ZIP code, or a delivery country name on country-level marketplaces.
|
| 87 |
+
- `page` *(optional)* — Search results page number, defaults to `1`.
|
| 88 |
+
- `language` *(optional)* — Uppercase ISO 639-1 code supported by the marketplace, e.g. `EN`, `DE`.
|
| 89 |
+
|
| 90 |
+
## Scope
|
| 91 |
+
|
| 92 |
+
Only publicly available product data. Anything behind an Amazon login — account
|
| 93 |
+
pages, the full customer review archive — is out of scope. See the
|
| 94 |
+
[Amazon scraping guide](https://scrape.do/blog/amazon-scraping/) for the legal
|
| 95 |
+
and ethical boundaries.
|
| 96 |
+
|
| 97 |
+
---
|
| 98 |
+
|
| 99 |
+
Learn more at [scrape.do](https://scrape.do/) · [Documentation](https://scrape.do/documentation/)
|
| 100 |
+
|
| 101 |
+
Check out the configuration reference at <https://huggingface.co/docs/hub/spaces-config-reference>.
|
app.py
ADDED
|
@@ -0,0 +1,470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from __future__ import annotations
|
| 2 |
+
|
| 3 |
+
import csv
|
| 4 |
+
import os
|
| 5 |
+
import tempfile
|
| 6 |
+
from typing import Any, Dict, List, Optional, Tuple
|
| 7 |
+
|
| 8 |
+
import gradio as gr
|
| 9 |
+
|
| 10 |
+
from tool import (
|
| 11 |
+
MARKETPLACES,
|
| 12 |
+
SCRAPE_DO_SIGNUP_URL,
|
| 13 |
+
ScrapeDoAmazonTool,
|
| 14 |
+
ZIP_LEVEL_MARKETS,
|
| 15 |
+
extract_asin,
|
| 16 |
+
)
|
| 17 |
+
|
| 18 |
+
MARKET_CHOICES = [(label, code) for code, label in MARKETPLACES.items()]
|
| 19 |
+
|
| 20 |
+
NO_TOKEN_MD = (
|
| 21 |
+
"⚠️ **Please paste your Scrape.do API token above.**\n\n"
|
| 22 |
+
f"Don't have one yet? [Get a free token in 30 seconds → ]({SCRAPE_DO_SIGNUP_URL})\n\n"
|
| 23 |
+
"Free tier includes 1,000 successful requests / month, no credit card required."
|
| 24 |
+
)
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
# --------------------------------------------------------------------- helpers
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
def _write_csv(rows: List[Dict[str, Any]], prefix: str) -> Optional[str]:
|
| 31 |
+
"""Write rows to a temp CSV and return its path."""
|
| 32 |
+
if not rows:
|
| 33 |
+
return None
|
| 34 |
+
fieldnames: List[str] = []
|
| 35 |
+
for row in rows:
|
| 36 |
+
for key in row:
|
| 37 |
+
if key not in fieldnames:
|
| 38 |
+
fieldnames.append(key)
|
| 39 |
+
|
| 40 |
+
handle = tempfile.NamedTemporaryFile(
|
| 41 |
+
mode="w", suffix=".csv", prefix=f"{prefix}-", delete=False,
|
| 42 |
+
newline="", encoding="utf-8-sig",
|
| 43 |
+
)
|
| 44 |
+
writer = csv.DictWriter(handle, fieldnames=fieldnames)
|
| 45 |
+
writer.writeheader()
|
| 46 |
+
for row in rows:
|
| 47 |
+
writer.writerow({key: row.get(key, "") for key in fieldnames})
|
| 48 |
+
handle.close()
|
| 49 |
+
return handle.name
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def _error_md(data: Dict[str, Any]) -> str:
|
| 53 |
+
message = data.get("errorMessage") or data.get("message") or data.get("error") or "Unknown error"
|
| 54 |
+
hint = data.get("hint")
|
| 55 |
+
text = f"❌ **{message}**"
|
| 56 |
+
if hint:
|
| 57 |
+
text += f"\n\n{hint}"
|
| 58 |
+
return text
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def _money(amount: Any, symbol: str = "", code: str = "") -> str:
|
| 62 |
+
if amount in (None, ""):
|
| 63 |
+
return "—"
|
| 64 |
+
if symbol:
|
| 65 |
+
return f"{symbol}{amount}"
|
| 66 |
+
if code:
|
| 67 |
+
return f"{amount} {code}"
|
| 68 |
+
return str(amount)
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
def _tool_or_none(token: str) -> Optional[ScrapeDoAmazonTool]:
|
| 72 |
+
if not token or not token.strip():
|
| 73 |
+
return None
|
| 74 |
+
return ScrapeDoAmazonTool(api_token=token.strip())
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
# --------------------------------------------------------------- product (PDP)
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
def scrape_product(
|
| 81 |
+
token: str, query: str, geocode: str, zipcode: str, language: str
|
| 82 |
+
) -> Tuple[str, List[str], Dict[str, Any], Optional[str]]:
|
| 83 |
+
tool = _tool_or_none(token)
|
| 84 |
+
if tool is None:
|
| 85 |
+
return NO_TOKEN_MD, [], {}, None
|
| 86 |
+
if not query or not query.strip():
|
| 87 |
+
return "⚠️ **Paste an Amazon product URL or ASIN.**", [], {}, None
|
| 88 |
+
|
| 89 |
+
data = tool.request("product", query, geocode, zipcode, language=language)
|
| 90 |
+
if data.get("status") != "success":
|
| 91 |
+
return _error_md(data), [], data, None
|
| 92 |
+
|
| 93 |
+
symbol = data.get("currency_symbol") or ""
|
| 94 |
+
code = data.get("currency") or ""
|
| 95 |
+
price = _money(data.get("price"), symbol, code)
|
| 96 |
+
list_price = data.get("list_price")
|
| 97 |
+
|
| 98 |
+
lines = [f"## {data.get('name') or 'Untitled product'}", ""]
|
| 99 |
+
|
| 100 |
+
facts = [
|
| 101 |
+
f"**ASIN** `{data.get('asin', '—')}`",
|
| 102 |
+
f"**Brand** {data.get('brand') or '—'}",
|
| 103 |
+
f"**Price** {price}",
|
| 104 |
+
]
|
| 105 |
+
if list_price:
|
| 106 |
+
facts.append(f"**List price** ~~{_money(list_price, symbol, code)}~~")
|
| 107 |
+
if data.get("rating") is not None:
|
| 108 |
+
facts.append(
|
| 109 |
+
f"**Rating** {data.get('rating')} ★ ({data.get('total_ratings') or 0:,} ratings)"
|
| 110 |
+
)
|
| 111 |
+
facts.append("**Prime** " + ("yes" if data.get("is_prime") else "no"))
|
| 112 |
+
lines.append(" · ".join(facts))
|
| 113 |
+
|
| 114 |
+
shipping = data.get("shipping_info") or []
|
| 115 |
+
if shipping:
|
| 116 |
+
lines += ["", "**Delivery**"] + [f"- {item}" for item in shipping[:4]]
|
| 117 |
+
|
| 118 |
+
rankings = data.get("best_seller_rankings") or []
|
| 119 |
+
if rankings:
|
| 120 |
+
lines += ["", "**Best seller rankings**"]
|
| 121 |
+
for rank in rankings[:6]:
|
| 122 |
+
lines.append(f"- #{rank.get('rank')} in {rank.get('category')}")
|
| 123 |
+
|
| 124 |
+
details = data.get("technical_details") or {}
|
| 125 |
+
if isinstance(details, dict) and details:
|
| 126 |
+
lines += ["", "**Technical details**", "", "| Field | Value |", "| --- | --- |"]
|
| 127 |
+
for key, value in list(details.items())[:15]:
|
| 128 |
+
lines.append(f"| {key} | {value} |")
|
| 129 |
+
|
| 130 |
+
description = data.get("description")
|
| 131 |
+
if description:
|
| 132 |
+
lines += ["", "**Description**", "", str(description)[:1200]]
|
| 133 |
+
|
| 134 |
+
if data.get("url"):
|
| 135 |
+
lines += ["", f"[Open on Amazon →]({data['url']})"]
|
| 136 |
+
|
| 137 |
+
images = [
|
| 138 |
+
image.get("url")
|
| 139 |
+
for image in (data.get("images") or [])
|
| 140 |
+
if isinstance(image, dict) and image.get("url")
|
| 141 |
+
]
|
| 142 |
+
if not images and data.get("thumbnail"):
|
| 143 |
+
images = [data["thumbnail"]]
|
| 144 |
+
|
| 145 |
+
flat = {
|
| 146 |
+
"asin": data.get("asin"),
|
| 147 |
+
"name": data.get("name"),
|
| 148 |
+
"brand": data.get("brand"),
|
| 149 |
+
"price": data.get("price"),
|
| 150 |
+
"list_price": data.get("list_price"),
|
| 151 |
+
"currency": data.get("currency"),
|
| 152 |
+
"rating": data.get("rating"),
|
| 153 |
+
"total_ratings": data.get("total_ratings"),
|
| 154 |
+
"is_prime": data.get("is_prime"),
|
| 155 |
+
"url": data.get("url"),
|
| 156 |
+
"thumbnail": data.get("thumbnail"),
|
| 157 |
+
}
|
| 158 |
+
csv_path = _write_csv([flat], f"amazon-product-{data.get('asin', 'result')}")
|
| 159 |
+
|
| 160 |
+
return "\n".join(lines), images[:12], data, csv_path
|
| 161 |
+
|
| 162 |
+
|
| 163 |
+
# ------------------------------------------------------------------- offers
|
| 164 |
+
|
| 165 |
+
|
| 166 |
+
OFFER_HEADERS = [
|
| 167 |
+
"Condition", "Seller", "Price", "Currency",
|
| 168 |
+
"Ships from", "FBA", "Prime", "Buy Box",
|
| 169 |
+
]
|
| 170 |
+
|
| 171 |
+
|
| 172 |
+
def scrape_offers(
|
| 173 |
+
token: str, query: str, geocode: str, zipcode: str, language: str
|
| 174 |
+
) -> Tuple[str, List[List[Any]], Dict[str, Any], Optional[str]]:
|
| 175 |
+
tool = _tool_or_none(token)
|
| 176 |
+
if tool is None:
|
| 177 |
+
return NO_TOKEN_MD, [], {}, None
|
| 178 |
+
if not query or not query.strip():
|
| 179 |
+
return "⚠️ **Paste an Amazon product URL or ASIN.**", [], {}, None
|
| 180 |
+
|
| 181 |
+
data = tool.request("offers", query, geocode, zipcode, language=language)
|
| 182 |
+
if data.get("status") != "success":
|
| 183 |
+
return _error_md(data), [], data, None
|
| 184 |
+
|
| 185 |
+
offers = data.get("offers") or []
|
| 186 |
+
if not offers:
|
| 187 |
+
return (
|
| 188 |
+
f"No competing offers returned for `{data.get('asin')}` in this "
|
| 189 |
+
"marketplace and delivery location. That is a valid result, not an "
|
| 190 |
+
"error — try another ZIP code or marketplace.",
|
| 191 |
+
[], data, None,
|
| 192 |
+
)
|
| 193 |
+
|
| 194 |
+
rows: List[List[Any]] = []
|
| 195 |
+
flat_rows: List[Dict[str, Any]] = []
|
| 196 |
+
for offer in offers:
|
| 197 |
+
listing = offer.get("listingPrice") or {}
|
| 198 |
+
prime = (offer.get("primeInformation") or {}).get("isPrime")
|
| 199 |
+
row = {
|
| 200 |
+
"asin": data.get("asin"),
|
| 201 |
+
"condition": offer.get("condition") or "",
|
| 202 |
+
"seller": offer.get("merchantName") or "",
|
| 203 |
+
"price": listing.get("amount", ""),
|
| 204 |
+
"currency": listing.get("currency", ""),
|
| 205 |
+
"ships_from": offer.get("shipsFrom") or "",
|
| 206 |
+
"fulfilled_by_amazon": bool(offer.get("isFulfilledByAmazon")),
|
| 207 |
+
"is_prime": bool(prime),
|
| 208 |
+
"is_buy_box_winner": bool(offer.get("isBuyBoxWinner")),
|
| 209 |
+
}
|
| 210 |
+
flat_rows.append(row)
|
| 211 |
+
rows.append([
|
| 212 |
+
row["condition"], row["seller"], row["price"], row["currency"],
|
| 213 |
+
row["ships_from"],
|
| 214 |
+
"✓" if row["fulfilled_by_amazon"] else "",
|
| 215 |
+
"✓" if row["is_prime"] else "",
|
| 216 |
+
"✓" if row["is_buy_box_winner"] else "",
|
| 217 |
+
])
|
| 218 |
+
|
| 219 |
+
prices = [
|
| 220 |
+
offer["price"] for offer in flat_rows
|
| 221 |
+
if isinstance(offer["price"], (int, float))
|
| 222 |
+
]
|
| 223 |
+
summary = f"**{len(rows)} offer(s)** for ASIN `{data.get('asin')}`"
|
| 224 |
+
if prices:
|
| 225 |
+
summary += f" · lowest {min(prices)} · highest {max(prices)}"
|
| 226 |
+
buy_box = next((o["seller"] for o in flat_rows if o["is_buy_box_winner"]), None)
|
| 227 |
+
if buy_box:
|
| 228 |
+
summary += f" · Buy Box: **{buy_box}**"
|
| 229 |
+
|
| 230 |
+
csv_path = _write_csv(flat_rows, f"amazon-offers-{data.get('asin', 'result')}")
|
| 231 |
+
return summary, rows, data, csv_path
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
# ------------------------------------------------------------------- search
|
| 235 |
+
|
| 236 |
+
|
| 237 |
+
SEARCH_HEADERS = [
|
| 238 |
+
"#", "ASIN", "Title", "Price", "Rating", "Reviews", "Prime", "Sponsored", "Badge",
|
| 239 |
+
]
|
| 240 |
+
|
| 241 |
+
|
| 242 |
+
def scrape_search(
|
| 243 |
+
token: str, keyword: str, geocode: str, zipcode: str, page: int, language: str
|
| 244 |
+
) -> Tuple[str, List[List[Any]], Dict[str, Any], Optional[str]]:
|
| 245 |
+
tool = _tool_or_none(token)
|
| 246 |
+
if tool is None:
|
| 247 |
+
return NO_TOKEN_MD, [], {}, None
|
| 248 |
+
if not keyword or not keyword.strip():
|
| 249 |
+
return "⚠️ **Enter a search keyword.**", [], {}, None
|
| 250 |
+
|
| 251 |
+
data = tool.request("search", keyword, geocode, zipcode, page=page, language=language)
|
| 252 |
+
if data.get("status") != "success":
|
| 253 |
+
return _error_md(data), [], data, None
|
| 254 |
+
|
| 255 |
+
products = data.get("products") or []
|
| 256 |
+
if not products:
|
| 257 |
+
return "No products returned for that keyword.", [], data, None
|
| 258 |
+
|
| 259 |
+
rows: List[List[Any]] = []
|
| 260 |
+
flat_rows: List[Dict[str, Any]] = []
|
| 261 |
+
for product in products:
|
| 262 |
+
price = product.get("price") or {}
|
| 263 |
+
rating = product.get("rating") or {}
|
| 264 |
+
row = {
|
| 265 |
+
"position": product.get("position"),
|
| 266 |
+
"asin": product.get("asin"),
|
| 267 |
+
"title": product.get("title"),
|
| 268 |
+
"price": price.get("amount", ""),
|
| 269 |
+
"currency": price.get("currencyCode", ""),
|
| 270 |
+
"rating": rating.get("value", ""),
|
| 271 |
+
"rating_count": rating.get("count", ""),
|
| 272 |
+
"review_count": product.get("reviewCount", ""),
|
| 273 |
+
"is_prime": bool(product.get("isPrime")),
|
| 274 |
+
"is_sponsored": bool(product.get("isSponsored")),
|
| 275 |
+
"badge": product.get("badge") or "",
|
| 276 |
+
"url": product.get("url"),
|
| 277 |
+
"image_url": product.get("imageUrl"),
|
| 278 |
+
}
|
| 279 |
+
flat_rows.append(row)
|
| 280 |
+
title = row["title"] or ""
|
| 281 |
+
rows.append([
|
| 282 |
+
row["position"], row["asin"],
|
| 283 |
+
title[:90] + ("…" if len(title) > 90 else ""),
|
| 284 |
+
f"{row['price']} {row['currency']}".strip(),
|
| 285 |
+
row["rating"], row["review_count"],
|
| 286 |
+
"✓" if row["is_prime"] else "",
|
| 287 |
+
"✓" if row["is_sponsored"] else "",
|
| 288 |
+
row["badge"],
|
| 289 |
+
])
|
| 290 |
+
|
| 291 |
+
sponsored = sum(1 for product in flat_rows if product["is_sponsored"])
|
| 292 |
+
summary = (
|
| 293 |
+
f"**{len(rows)} results** for “{data.get('keyword')}” · page {data.get('page')} · "
|
| 294 |
+
f"{sponsored} sponsored, {len(rows) - sponsored} organic"
|
| 295 |
+
)
|
| 296 |
+
if data.get("totalResults"):
|
| 297 |
+
summary += f" · {data['totalResults']}"
|
| 298 |
+
|
| 299 |
+
csv_path = _write_csv(flat_rows, "amazon-search")
|
| 300 |
+
return summary, rows, data, csv_path
|
| 301 |
+
|
| 302 |
+
|
| 303 |
+
# ----------------------------------------------------------------------- UI
|
| 304 |
+
|
| 305 |
+
|
| 306 |
+
HEADER_MD = f"""
|
| 307 |
+
# 📦 Amazon Product Scraper
|
| 308 |
+
|
| 309 |
+
**Pull structured JSON from any Amazon marketplace — product pages, every seller
|
| 310 |
+
offer, and keyword search results.** No HTML parsing, no ASIN spreadsheets, no blocks.
|
| 311 |
+
|
| 312 |
+
AWS WAF bypass, proxy rotation, session handling and CAPTCHAs are handled for you
|
| 313 |
+
across 21 marketplaces, with ZIP-code level delivery targeting.
|
| 314 |
+
Powered by [Scrape.do](https://scrape.do/).
|
| 315 |
+
|
| 316 |
+
### 🔑 Need an API token?
|
| 317 |
+
👉 **[Sign up free on Scrape.do]({SCRAPE_DO_SIGNUP_URL})** — 1,000 free requests / month, no credit card.
|
| 318 |
+
"""
|
| 319 |
+
|
| 320 |
+
FOOTER_MD = f"""
|
| 321 |
+
---
|
| 322 |
+
|
| 323 |
+
### Using this as a smolagents Tool
|
| 324 |
+
|
| 325 |
+
```python
|
| 326 |
+
from smolagents import CodeAgent, InferenceClientModel
|
| 327 |
+
from tool import ScrapeDoAmazonTool
|
| 328 |
+
|
| 329 |
+
agent = CodeAgent(
|
| 330 |
+
tools=[ScrapeDoAmazonTool(api_token="YOUR_SCRAPEDO_TOKEN")],
|
| 331 |
+
model=InferenceClientModel(),
|
| 332 |
+
)
|
| 333 |
+
agent.run("Compare the price and Buy Box seller for ASIN B0BLRJ4R8F in the US and the UK")
|
| 334 |
+
```
|
| 335 |
+
|
| 336 |
+
Or set `SCRAPE_DO_API_TOKEN` in your environment and instantiate without args.
|
| 337 |
+
|
| 338 |
+
Only publicly available product data is in scope. Anything behind an Amazon login —
|
| 339 |
+
account pages, full customer review archives — is out of bounds; see the
|
| 340 |
+
[Amazon scraping guide](https://scrape.do/blog/amazon-scraping/) for the legal and
|
| 341 |
+
ethical boundaries.
|
| 342 |
+
|
| 343 |
+
[Scrape.do](https://scrape.do/) · [Amazon Scraper API docs](https://scrape.do/documentation/amazon-scraper-api/) · [Sign up free]({SCRAPE_DO_SIGNUP_URL})
|
| 344 |
+
"""
|
| 345 |
+
|
| 346 |
+
ZIP_INFO = (
|
| 347 |
+
"ZIP code for us / gb / de / fr / it / es / ca / jp / in. "
|
| 348 |
+
"For other marketplaces, enter a delivery country name instead (or leave blank)."
|
| 349 |
+
)
|
| 350 |
+
|
| 351 |
+
|
| 352 |
+
def build_demo() -> gr.Blocks:
|
| 353 |
+
with gr.Blocks(title="Amazon Product Scraper — Scrape.do") as demo:
|
| 354 |
+
gr.Markdown(HEADER_MD)
|
| 355 |
+
|
| 356 |
+
api_token = gr.Textbox(
|
| 357 |
+
label="Scrape.do API Token",
|
| 358 |
+
placeholder="Paste your token here…",
|
| 359 |
+
type="password",
|
| 360 |
+
info="Don't have one? Get a free token from the link above.",
|
| 361 |
+
)
|
| 362 |
+
|
| 363 |
+
with gr.Row():
|
| 364 |
+
geocode = gr.Dropdown(
|
| 365 |
+
label="Marketplace",
|
| 366 |
+
choices=MARKET_CHOICES,
|
| 367 |
+
value="us",
|
| 368 |
+
)
|
| 369 |
+
zipcode = gr.Textbox(
|
| 370 |
+
label="Delivery location",
|
| 371 |
+
placeholder="10001",
|
| 372 |
+
info=ZIP_INFO,
|
| 373 |
+
)
|
| 374 |
+
language = gr.Textbox(
|
| 375 |
+
label="Language",
|
| 376 |
+
placeholder="EN",
|
| 377 |
+
info="Optional ISO 639-1 code, uppercase. Must be supported by the marketplace.",
|
| 378 |
+
)
|
| 379 |
+
|
| 380 |
+
with gr.Tabs():
|
| 381 |
+
# ------------------------------------------------ product tab
|
| 382 |
+
with gr.Tab("Product page"):
|
| 383 |
+
gr.Markdown(
|
| 384 |
+
"Paste a product URL or a bare ASIN. Returns title, brand, price, "
|
| 385 |
+
"list price, rating, images, best seller rankings and specs."
|
| 386 |
+
)
|
| 387 |
+
product_query = gr.Textbox(
|
| 388 |
+
label="Amazon product URL or ASIN",
|
| 389 |
+
placeholder="https://www.amazon.com/dp/B0BLRJ4R8F · or just B0BLRJ4R8F",
|
| 390 |
+
)
|
| 391 |
+
product_btn = gr.Button("Scrape product", variant="primary")
|
| 392 |
+
|
| 393 |
+
product_summary = gr.Markdown()
|
| 394 |
+
product_gallery = gr.Gallery(
|
| 395 |
+
label="Product images", columns=6, height=180, preview=False
|
| 396 |
+
)
|
| 397 |
+
product_csv = gr.File(label="Download CSV")
|
| 398 |
+
with gr.Accordion("Raw JSON response", open=False):
|
| 399 |
+
product_json = gr.JSON()
|
| 400 |
+
|
| 401 |
+
product_btn.click(
|
| 402 |
+
fn=scrape_product,
|
| 403 |
+
inputs=[api_token, product_query, geocode, zipcode, language],
|
| 404 |
+
outputs=[product_summary, product_gallery, product_json, product_csv],
|
| 405 |
+
)
|
| 406 |
+
|
| 407 |
+
# ------------------------------------------------- offers tab
|
| 408 |
+
with gr.Tab("Seller offers"):
|
| 409 |
+
gr.Markdown(
|
| 410 |
+
"Every active offer on an ASIN: price, condition, seller, "
|
| 411 |
+
"fulfilment and who currently holds the Buy Box."
|
| 412 |
+
)
|
| 413 |
+
offers_query = gr.Textbox(
|
| 414 |
+
label="Amazon product URL or ASIN",
|
| 415 |
+
placeholder="B0DZDBWM5B",
|
| 416 |
+
)
|
| 417 |
+
offers_btn = gr.Button("Scrape offers", variant="primary")
|
| 418 |
+
|
| 419 |
+
offers_summary = gr.Markdown()
|
| 420 |
+
offers_table = gr.Dataframe(
|
| 421 |
+
headers=OFFER_HEADERS, wrap=True, label="Offers"
|
| 422 |
+
)
|
| 423 |
+
offers_csv = gr.File(label="Download CSV")
|
| 424 |
+
with gr.Accordion("Raw JSON response", open=False):
|
| 425 |
+
offers_json = gr.JSON()
|
| 426 |
+
|
| 427 |
+
offers_btn.click(
|
| 428 |
+
fn=scrape_offers,
|
| 429 |
+
inputs=[api_token, offers_query, geocode, zipcode, language],
|
| 430 |
+
outputs=[offers_summary, offers_table, offers_json, offers_csv],
|
| 431 |
+
)
|
| 432 |
+
|
| 433 |
+
# ------------------------------------------------- search tab
|
| 434 |
+
with gr.Tab("Search results"):
|
| 435 |
+
gr.Markdown(
|
| 436 |
+
"Keyword and category search with organic vs. sponsored "
|
| 437 |
+
"placements and exact on-page positions."
|
| 438 |
+
)
|
| 439 |
+
with gr.Row():
|
| 440 |
+
search_query = gr.Textbox(
|
| 441 |
+
label="Search keyword",
|
| 442 |
+
placeholder="laptop stands",
|
| 443 |
+
scale=3,
|
| 444 |
+
)
|
| 445 |
+
search_page = gr.Number(
|
| 446 |
+
label="Page", value=1, precision=0, minimum=1, scale=1
|
| 447 |
+
)
|
| 448 |
+
search_btn = gr.Button("Scrape search results", variant="primary")
|
| 449 |
+
|
| 450 |
+
search_summary = gr.Markdown()
|
| 451 |
+
search_table = gr.Dataframe(
|
| 452 |
+
headers=SEARCH_HEADERS, wrap=True, label="Results"
|
| 453 |
+
)
|
| 454 |
+
search_csv = gr.File(label="Download CSV")
|
| 455 |
+
with gr.Accordion("Raw JSON response", open=False):
|
| 456 |
+
search_json = gr.JSON()
|
| 457 |
+
|
| 458 |
+
search_btn.click(
|
| 459 |
+
fn=scrape_search,
|
| 460 |
+
inputs=[api_token, search_query, geocode, zipcode, search_page, language],
|
| 461 |
+
outputs=[search_summary, search_table, search_json, search_csv],
|
| 462 |
+
)
|
| 463 |
+
|
| 464 |
+
gr.Markdown(FOOTER_MD)
|
| 465 |
+
|
| 466 |
+
return demo
|
| 467 |
+
|
| 468 |
+
|
| 469 |
+
if __name__ == "__main__":
|
| 470 |
+
build_demo().launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
gradio
|
| 2 |
+
requests
|
| 3 |
+
smolagents
|
tool.py
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from __future__ import annotations
|
| 2 |
+
|
| 3 |
+
import json
|
| 4 |
+
import os
|
| 5 |
+
import re
|
| 6 |
+
import urllib.parse
|
| 7 |
+
from typing import Any, Dict, Optional
|
| 8 |
+
|
| 9 |
+
import requests
|
| 10 |
+
from smolagents.tools import Tool
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
SCRAPE_DO_SIGNUP_URL = (
|
| 14 |
+
"https://dashboard.scrape.do/sign-up?utm_source=huggingface&utm_medium=amazon-scraper"
|
| 15 |
+
)
|
| 16 |
+
API_BASE = "https://api.scrape.do/plugin/amazon"
|
| 17 |
+
|
| 18 |
+
# geocode -> human label, shown in the UI dropdown.
|
| 19 |
+
MARKETPLACES: Dict[str, str] = {
|
| 20 |
+
"us": "United States (amazon.com)",
|
| 21 |
+
"gb": "United Kingdom (amazon.co.uk)",
|
| 22 |
+
"de": "Germany (amazon.de)",
|
| 23 |
+
"fr": "France (amazon.fr)",
|
| 24 |
+
"it": "Italy (amazon.it)",
|
| 25 |
+
"es": "Spain (amazon.es)",
|
| 26 |
+
"ca": "Canada (amazon.ca)",
|
| 27 |
+
"jp": "Japan (amazon.co.jp)",
|
| 28 |
+
"in": "India (amazon.in)",
|
| 29 |
+
"au": "Australia (amazon.com.au)",
|
| 30 |
+
"br": "Brazil (amazon.com.br)",
|
| 31 |
+
"mx": "Mexico (amazon.com.mx)",
|
| 32 |
+
"nl": "Netherlands (amazon.nl)",
|
| 33 |
+
"pl": "Poland (amazon.pl)",
|
| 34 |
+
"se": "Sweden (amazon.se)",
|
| 35 |
+
"tr": "Turkey (amazon.com.tr)",
|
| 36 |
+
"ae": "UAE (amazon.ae)",
|
| 37 |
+
"sa": "Saudi Arabia (amazon.sa)",
|
| 38 |
+
"sg": "Singapore (amazon.sg)",
|
| 39 |
+
"eg": "Egypt (amazon.eg)",
|
| 40 |
+
"be": "Belgium (amazon.com.be)",
|
| 41 |
+
}
|
| 42 |
+
|
| 43 |
+
# Marketplaces where Amazon localises delivery by postal code. Everything else
|
| 44 |
+
# takes a country-level location instead, via countryName.
|
| 45 |
+
ZIP_LEVEL_MARKETS = {"us", "gb", "uk", "de", "fr", "it", "es", "ca", "jp", "in"}
|
| 46 |
+
|
| 47 |
+
COUNTRY_NAMES: Dict[str, str] = {
|
| 48 |
+
"tr": "Turkey",
|
| 49 |
+
"br": "Brazil",
|
| 50 |
+
"au": "Australia",
|
| 51 |
+
"mx": "Mexico",
|
| 52 |
+
"nl": "Netherlands",
|
| 53 |
+
"pl": "Poland",
|
| 54 |
+
"se": "Sweden",
|
| 55 |
+
"ae": "United Arab Emirates",
|
| 56 |
+
"sa": "Saudi Arabia",
|
| 57 |
+
"sg": "Singapore",
|
| 58 |
+
"eg": "Egypt",
|
| 59 |
+
"be": "Belgium",
|
| 60 |
+
}
|
| 61 |
+
|
| 62 |
+
_ASIN_PATTERN = re.compile(r"(?:/dp/|/gp/product/|/gp/aw/d/|/product/|[?&]asin=)([A-Z0-9]{10})", re.I)
|
| 63 |
+
_BARE_ASIN = re.compile(r"^[A-Z0-9]{10}$", re.I)
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def extract_asin(value: str) -> Optional[str]:
|
| 67 |
+
"""Accept a full Amazon URL or a bare ASIN and return the ASIN."""
|
| 68 |
+
if not value:
|
| 69 |
+
return None
|
| 70 |
+
value = value.strip()
|
| 71 |
+
|
| 72 |
+
if _BARE_ASIN.match(value):
|
| 73 |
+
return value.upper()
|
| 74 |
+
|
| 75 |
+
match = _ASIN_PATTERN.search(value)
|
| 76 |
+
if match:
|
| 77 |
+
return match.group(1).upper()
|
| 78 |
+
|
| 79 |
+
return None
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
class ScrapeDoAmazonTool(Tool):
|
| 83 |
+
name = "amazon_product_scraper"
|
| 84 |
+
description = """
|
| 85 |
+
Scrape structured product data from any Amazon marketplace: product detail
|
| 86 |
+
pages (title, brand, price, rating, images, rankings, technical specs),
|
| 87 |
+
all seller offers for an ASIN, or keyword search results with organic and
|
| 88 |
+
sponsored positions. Returns clean JSON, no HTML parsing required.
|
| 89 |
+
Powered by Scrape.do's Amazon Scraper API, which handles AWS WAF, proxy
|
| 90 |
+
rotation, sessions and CAPTCHAs automatically across 21 marketplaces.
|
| 91 |
+
Use this when you need Amazon pricing, catalogue or competitive data.
|
| 92 |
+
"""
|
| 93 |
+
output_type = "string"
|
| 94 |
+
|
| 95 |
+
def __init__(self, api_token: Optional[str] = None) -> None:
|
| 96 |
+
# Token can be passed explicitly (e.g. by a Gradio UI) or read from the
|
| 97 |
+
# SCRAPE_DO_API_TOKEN environment variable for programmatic use.
|
| 98 |
+
self._api_token = api_token
|
| 99 |
+
self.inputs = {
|
| 100 |
+
"mode": {
|
| 101 |
+
"type": "string",
|
| 102 |
+
"description": (
|
| 103 |
+
"What to scrape: 'product' for a product detail page, "
|
| 104 |
+
"'offers' for every seller offer on an ASIN, or 'search' "
|
| 105 |
+
"for keyword/category search results."
|
| 106 |
+
),
|
| 107 |
+
},
|
| 108 |
+
"query": {
|
| 109 |
+
"type": "string",
|
| 110 |
+
"description": (
|
| 111 |
+
"An Amazon product URL or ASIN for 'product' and 'offers'. "
|
| 112 |
+
"A search keyword for 'search'."
|
| 113 |
+
),
|
| 114 |
+
},
|
| 115 |
+
"geocode": {
|
| 116 |
+
"type": "string",
|
| 117 |
+
"description": (
|
| 118 |
+
"Marketplace country code: 'us', 'gb', 'de', 'jp', 'tr'… "
|
| 119 |
+
"Defaults to 'us'."
|
| 120 |
+
),
|
| 121 |
+
"nullable": True,
|
| 122 |
+
},
|
| 123 |
+
"zipcode": {
|
| 124 |
+
"type": "string",
|
| 125 |
+
"description": (
|
| 126 |
+
"Postal code for ZIP-level marketplaces (us, gb, de, fr, it, "
|
| 127 |
+
"es, ca, jp, in) to localise price, stock and delivery. "
|
| 128 |
+
"Ignored elsewhere, where a country-level location is used."
|
| 129 |
+
),
|
| 130 |
+
"nullable": True,
|
| 131 |
+
},
|
| 132 |
+
"page": {
|
| 133 |
+
"type": "integer",
|
| 134 |
+
"description": "Search results page number. Only used when mode='search'.",
|
| 135 |
+
"nullable": True,
|
| 136 |
+
},
|
| 137 |
+
"language": {
|
| 138 |
+
"type": "string",
|
| 139 |
+
"description": (
|
| 140 |
+
"ISO 639-1 language code in uppercase, e.g. 'EN', 'DE', 'FR'. "
|
| 141 |
+
"Must be supported by the target marketplace."
|
| 142 |
+
),
|
| 143 |
+
"nullable": True,
|
| 144 |
+
},
|
| 145 |
+
}
|
| 146 |
+
super().__init__()
|
| 147 |
+
|
| 148 |
+
# ------------------------------------------------------------------ token
|
| 149 |
+
|
| 150 |
+
def _resolve_token(self) -> Optional[str]:
|
| 151 |
+
if self._api_token:
|
| 152 |
+
return self._api_token.strip()
|
| 153 |
+
env_token = os.getenv("SCRAPE_DO_API_TOKEN")
|
| 154 |
+
return env_token.strip() if env_token else None
|
| 155 |
+
|
| 156 |
+
# ---------------------------------------------------------------- request
|
| 157 |
+
|
| 158 |
+
def request(
|
| 159 |
+
self,
|
| 160 |
+
mode: str,
|
| 161 |
+
query: str,
|
| 162 |
+
geocode: str = "us",
|
| 163 |
+
zipcode: Optional[str] = None,
|
| 164 |
+
page: Optional[int] = None,
|
| 165 |
+
language: Optional[str] = None,
|
| 166 |
+
) -> Dict[str, Any]:
|
| 167 |
+
"""Call the Amazon Scraper API and return a parsed dict."""
|
| 168 |
+
token = self._resolve_token()
|
| 169 |
+
if not token:
|
| 170 |
+
return {
|
| 171 |
+
"status": "error",
|
| 172 |
+
"errorMessage": "Missing Scrape.do API token.",
|
| 173 |
+
"hint": f"Get a free token at {SCRAPE_DO_SIGNUP_URL}",
|
| 174 |
+
}
|
| 175 |
+
|
| 176 |
+
if not query or not query.strip():
|
| 177 |
+
return {"status": "error", "errorMessage": "No ASIN, URL or keyword provided."}
|
| 178 |
+
|
| 179 |
+
geocode = (geocode or "us").strip().lower()
|
| 180 |
+
params: Dict[str, Any] = {"token": token, "geocode": geocode}
|
| 181 |
+
|
| 182 |
+
if mode in ("product", "offers"):
|
| 183 |
+
asin = extract_asin(query)
|
| 184 |
+
if not asin:
|
| 185 |
+
return {
|
| 186 |
+
"status": "error",
|
| 187 |
+
"errorMessage": (
|
| 188 |
+
"Could not read an ASIN from that input. Paste a full "
|
| 189 |
+
"Amazon product URL (…/dp/B0BLRJ4R8F) or the 10-character "
|
| 190 |
+
"ASIN on its own."
|
| 191 |
+
),
|
| 192 |
+
}
|
| 193 |
+
params["asin"] = asin
|
| 194 |
+
endpoint = f"{API_BASE}/pdp" if mode == "product" else f"{API_BASE}/offer-listing"
|
| 195 |
+
elif mode == "search":
|
| 196 |
+
params["keyword"] = query.strip()
|
| 197 |
+
params["page"] = int(page or 1)
|
| 198 |
+
endpoint = f"{API_BASE}/search"
|
| 199 |
+
else:
|
| 200 |
+
return {"status": "error", "errorMessage": f"Unknown mode: {mode}"}
|
| 201 |
+
|
| 202 |
+
# Location: ZIP for ZIP-level marketplaces, country name for the rest.
|
| 203 |
+
if geocode in ZIP_LEVEL_MARKETS:
|
| 204 |
+
if zipcode and zipcode.strip():
|
| 205 |
+
params["zipcode"] = zipcode.strip()
|
| 206 |
+
elif geocode in COUNTRY_NAMES:
|
| 207 |
+
# Passing the marketplace's own country is a no-op, so only send it
|
| 208 |
+
# when the caller explicitly asked for a different delivery country.
|
| 209 |
+
if zipcode and zipcode.strip():
|
| 210 |
+
params["countryName"] = zipcode.strip()
|
| 211 |
+
|
| 212 |
+
if language and language.strip():
|
| 213 |
+
params["language"] = language.strip().upper()
|
| 214 |
+
|
| 215 |
+
url = endpoint + "?" + urllib.parse.urlencode(params, quote_via=urllib.parse.quote)
|
| 216 |
+
|
| 217 |
+
try:
|
| 218 |
+
response = requests.get(url, timeout=90)
|
| 219 |
+
except requests.exceptions.RequestException as exc:
|
| 220 |
+
return {"status": "error", "errorMessage": f"Request failed: {exc}"}
|
| 221 |
+
|
| 222 |
+
try:
|
| 223 |
+
data = response.json()
|
| 224 |
+
except ValueError:
|
| 225 |
+
return {
|
| 226 |
+
"status": "error",
|
| 227 |
+
"errorMessage": f"Unexpected non-JSON response (HTTP {response.status_code}).",
|
| 228 |
+
"details": response.text[:500],
|
| 229 |
+
}
|
| 230 |
+
|
| 231 |
+
if response.status_code == 401 or "token" in str(data.get("error", "")).lower():
|
| 232 |
+
data.setdefault(
|
| 233 |
+
"hint", f"Check your token or create one at {SCRAPE_DO_SIGNUP_URL}"
|
| 234 |
+
)
|
| 235 |
+
|
| 236 |
+
if isinstance(data, dict) and "status" not in data:
|
| 237 |
+
data["status"] = "success" if response.ok else "error"
|
| 238 |
+
if isinstance(data, dict) and not response.ok and not data.get("errorMessage"):
|
| 239 |
+
data["errorMessage"] = data.get("message") or f"HTTP {response.status_code}"
|
| 240 |
+
|
| 241 |
+
return data
|
| 242 |
+
|
| 243 |
+
# ---------------------------------------------------------------- forward
|
| 244 |
+
|
| 245 |
+
def forward(
|
| 246 |
+
self,
|
| 247 |
+
mode: str = "product",
|
| 248 |
+
query: str = "",
|
| 249 |
+
geocode: Optional[str] = None,
|
| 250 |
+
zipcode: Optional[str] = None,
|
| 251 |
+
page: Optional[int] = None,
|
| 252 |
+
language: Optional[str] = None,
|
| 253 |
+
) -> str:
|
| 254 |
+
result = self.request(
|
| 255 |
+
mode=mode,
|
| 256 |
+
query=query,
|
| 257 |
+
geocode=geocode or "us",
|
| 258 |
+
zipcode=zipcode,
|
| 259 |
+
page=page,
|
| 260 |
+
language=language,
|
| 261 |
+
)
|
| 262 |
+
return json.dumps(result, ensure_ascii=False, indent=2)
|