Skip to main content
skill CX Codex

taobao-shop-catalog — Claude Code skill: Taobao shop catalog scraper

taobao-shop-catalog pulls a Taobao or Tmall store's product list by shopId, page by page: itemId, title, image link and item link.

MIT 1 installs ★ 6,409 updated 2026-08-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add browser-act/skills --skill taobao-shop-catalog -a claude-code
Open on GitHub

What taobao-shop-catalog does

The skill loads a shop's catalog at https://shop{shopId}.taobao.com/category.htm, waits for it to settle, then runs scripts/extract-catalog.py to read the listings. Every entry comes back with itemId, title, imageUrl and itemUrl. Tmall stores redirect to {shopName}.tmall.com, and both URL shapes are handled.

Paging goes through the pageNo parameter, up to 60 products per page. It stops on an empty result or once no next-page link is left in the DOM. Keep one session for all pages of a shop, and write output as you go, so a failure on page five resumes there instead of restarting.

Prices are absent on purpose. Taobao hides them with font tricks on catalog pages, so DOM extraction gets nothing usable; fetch a price per itemId with the taobao-product-detail skill. A browser already signed in to Taobao is required too, because the skill looks for a nickname in the header and stops when it sees a login button. browser-act itself has to be loaded through the Skill tool.

What it helps with

  • collect every itemId from a store for later work
  • track a competitor's assortment page by page
  • export titles and images from a Tmall shop
  • spot new listings after a catalog refresh
  • gather item links for a bulk price lookup

Example prompts for the agent

  • Walk the catalog of shop shopId 67095450 and save every itemId to a file
  • Go through this shop's pages to the last one and tell me how many items there are
  • List the products in a competitor's Tmall store

How to install taobao-shop-catalog

1Skills CLI (Vercel)

npx skills add browser-act/skills --skill taobao-shop-catalog -a claude-code

2Manually: put the files in place

~/.claude/skills/taobao-shop-catalog/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/taobao-shop-catalog/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about taobao-shop-catalog

How do I install taobao-shop-catalog in Claude Code?

Run npx skills add browser-act/skills --skill taobao-shop-catalog -a claude-code. The skill file lands at ~/.claude/skills/taobao-shop-catalog/SKILL.md.

What does taobao-shop-catalog do?

It opens a Taobao or Tmall shop's catalog by shopId and returns paginated listings with itemId, title, image URL and item URL.

Why are there no prices in the output?

Catalog pages hide prices behind font obfuscation, so DOM extraction cannot read them. Use taobao-product-detail to get the price for a specific itemId.

Source text

SKILL.md · MIT
---
name: taobao-shop-catalog
description: "Browse a Taobao or Tmall shop's product catalog by shopId, returning paginated product listings with itemId and title. Use when user asks to scrape a Taobao shop, get all products from a store, list items in a Taobao/Tmall shop, fetch shop catalog by userId or shopId, 采集淘宝店铺商品, 抓取淘宝店铺所有商品, 获取天猫店铺商品列表, 淘宝店铺目录, 按店铺ID采集商品. Also applies to shop inventory monitoring, competitor store analysis, and bulk itemId collection from a specific seller."
---

# Taobao — Shop Catalog

> shopId → paginated shop product listing (itemId, title, image URL)

## Language

All process output to user (progress updates, process notifications) follows the user's language.

## Objective

Navigate to a Taobao or Tmall shop's catalog page and extract product listings.

## Prerequisites

- Target page is already open in the browser: `https://shop{shopId}.taobao.com/category.htm`
- User is logged in to Taobao (user avatar or nickname visible in the page header)

## Pre-execution Checks

### 1. Tool Readiness

If browser-act has been confirmed available in the current session → skip this step.

Invoke `browser-act` via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.

### 2. Login Verification

If login status for Taobao has been confirmed in the current session → skip this step.

Otherwise: open `https://www.taobao.com` and observe the page header:
- User nickname visible → logged in, continue execution
- Login button visible → not logged in, inform the user that Taobao login is needed first, assist the user in completing the login flow

User refuses or cannot log in → terminate execution.

## Capability Components

> This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page, never bypassing authentication or access controls. JS code is encapsulated in Python files under the `scripts/` directory, invoked via `eval "$(python scripts/xxx.py {params})"`. `$(...)` is bash syntax; it is recommended to use the bash tool for execution.

### DOM: shop catalog product list (data extraction)

Navigate to the shop's catalog page, then extract:

1. `navigate "https://shop{shopId}.taobao.com/category.htm?search=y&pageNo={page}"`
   - Note: Tmall shops redirect to `https://{shopName}.tmall.com/category.htm?search=y&pageNo={page}`
   - The `search=y` parameter activates the paginated search mode
2. `wait stable`
3. `eval "$(python scripts/extract-catalog.py '{shopId}' --page {page})"`

Parameters:
- `shopId`: numerical shop ID (e.g., `67095450`); found in shop URL as `shop{shopId}.taobao.com`
- `--page`: page number, 1-based, default `1`

Output example:
```json
[
  {
    "itemId": "1041516493508",
    "title": "绿联T8梯形排插插座转换器插线板大间距宿舍桌面充电多孔位插排",
    "imageUrl": "https://img.alicdn.com/imgextra/...",
    "itemUrl": "https://detail.tmall.com/item.htm?id=1041516493508"
  }
]
```

Notes:
- `price` is not included — Taobao shop catalog pages use font-based price obfuscation that cannot be decoded via DOM extraction. Use the `taobao-product-detail` skill to fetch prices for specific items.
- `imageUrl` may be a lazy-loaded URL from `data-ks-lazyload-custom` attribute when the image has not scrolled into view

Error handling: if result count = 0, check that the page loaded correctly (`screenshot`), confirm the shopId is valid, and retry. Some shops may be Tmall-only and require following the redirect URL.

## Pagination

**URL Pagination**: URL pattern `https://shop{shopId}.taobao.com/category.htm?search=y&pageNo={N}` (or `https://{shopName}.tmall.com/category.htm?search=y&pageNo={N}` after redirect), increment `pageNo` from 1. Each page returns up to 60 items. Termination: when `result count = 0` or next page link `href` with `pageNo={N+1}` is absent from the DOM.

Next page link selector: `a[href*="pageNo"]` (contains the next page number).

## Success Criteria

`result count >= 1` and `itemId` non-null rate = 100%

## Known Limitations

- Prices are font-obfuscated on the shop catalog page and cannot be extracted; fetch individual item prices via `taobao-product-detail`
- Some shop categories are not shown in the default `category.htm` view; category-specific browsing requires clicking category links in the shop nav
- Shop redirect from `shop{id}.taobao.com` to `{name}.tmall.com` changes the URL structure; the script handles both

## Execution Efficiency

- **Batch orchestration**: Write a bash script to loop through pages serially; add 2–3 second intervals between navigations.
- **Test before batch execution**: After writing a batch script, you must first test with 1–2 pages to verify the script runs correctly; only then run the full batch. Never skip testing and execute in batch directly.
- **Reduce redundant pre-operations**: Stay in the same session for all pages of one shop without re-login checks.
- **Error resumption**: Save results page by page during batch processing; on failure, resume from the last successful page rather than starting over.

## Experience Notes

Path: `{working-directory}/browser-act-skill-forge-memories/taobao-shop-catalog.memory.md`

**Before execution**: If the file exists, read it first — it records unexpected situations encountered during past executions (e.g., a strategy has become ineffective); adjust strategy order accordingly.

**After execution**: If an unexpected situation is encountered (strategy became ineffective, page redesigned, anti-scraping upgraded, better path discovered), append a line:
`{YYYY-MM-DD}: {what happened} → {conclusion}`

Normal execution does not write to the file. Do not record what keywords were used or how many results were returned — those are task outputs, not experience.

© browser-act · MIT · browser-act/skills

Similar skills

All skills for Browser and scraping →

From the same set11

The whole set →
browser-act browser-act — a skill that hands your agent a browser CLI: navigate, wait for JavaScript, pull data, fill forms, take screenshots. Useful when plain fetch falls short. CX Codex +1 108,500installs browser-act-skill-forge browser-act-skill-forge explores a website through browser-act and forges a skill package with SKILL.md and Python scripts. Later runs skip the exploration step. CX Codex +1 85,200installs amazon-competitor-analyzer amazon-competitor-analyzer pulls product data from Amazon by ASIN and compares pricing, specs, and reviews across competitors. Identifies weak points in rival strategies and uncovers market gaps for your own product. CX Codex +1 133installs youtube-channel-api-skill youtube-channel-api-skill is a skill that searches YouTube channels through BrowserAct API. Find creators by topic or gather competitor channel data. CX Codex +1 5installs ecommerce-listing ecommerce-listing extracts structured product listings from e-commerce search results and category pages with filters and pagination. CX Codex +1 1installs facebook-page-profile-posts facebook-page-profile-posts reads posts from a public Facebook Page or profile and returns reactions, media, links, and author details. Use it for exports or timeline monitoring. CX Codex +1 1installs social-media-finder-skill social-media-finder-skill looks up public profiles of a person or a brand on Facebook, Twitter, Instagram, LinkedIn, TikTok and hands back a CSV with the links and follower counts. CX Codex +1 1installs facebook-page-posts facebook-page-posts extracts posts from public Facebook pages with engagement counts, external links, and reactions using an active browser session. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open