ecommerce-listing

Name: ecommerce-listing
Author: browser-act

3installs220forks

How to install ecommerce-listing?

browser-act/skills/ecommerce-listing

$npx -y skills add browser-act/skills --skill ecommerce-listing

Installs into the current project.

Summary

Extract product list from any e-commerce category page, search results page, or keyword search with filters. Returns paginated product arrays with URL, name, price, currency, image, rating, review count per item. Supports URL input, keyword search, and site-scoped search with fil

Files · 1

View on GitHub

SKILL.md

1	# E-commerce — Product Listing
2
3	> Category/search URL or keyword + filters → paginated product list (URL, name, price, image, rating per item)
4
5	## Language
6
7	All process output to user (progress updates, process notifications) follows the user's language.
8
9	## Objective
10
11	Extract a structured list of products from any e-commerce category, search results, or keyword search page, with support for price/brand/rating filters and multi-page pagination.
12
13	## Prerequisites
14
15	- Target browser is open and connected
16	- No login required for public listing pages
17
18	## Pre-execution Checks
19
20	### 1. Tool Readiness
21
22	If browser-act has been confirmed available in the current session → skip this step.
23
24	Invoke `browser-act` via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
25
26	## Capability Components
27
28	> 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. JS code is encapsulated in Python files under the `scripts/` directory, invoked via `eval "$(python scripts/xxx.py {params})"`. Use the bash tool for execution.
29
30	### DOM: Extract product list from current page
31
32	Navigate to the listing/search page first, then extract:
33
34	```bash
35	eval "$(python scripts/extract-listing.py --max-results 20)"
36	```
37
38	Parameters:
39	- `--max-results`: max items to return per page, default 20
40
41	Output example:
42	```json
43	{
44	"count": 20,
45	"items": [
46	{
47	"url": "https://www.amazon.com/dp/B09WNK39JN",
48	"name": "Amazon Echo Pop",
49	"price": 39.99,
50	"currency": "USD",
51	"image": "https://m.media-amazon.com/images/I/...jpg",
52	"rating": 4.7,
53	"review_count": 103789,
54	"asin": "B09WNK39JN"
55	}
56	]
57	}
58	```
59
60	### DOM: Get next page URL
61
62	After extracting a page, get the URL to navigate to for the next page:
63
64	```bash
65	eval "$(python scripts/extract-listing-next-page.py)"
66	```
67
68	Output example:
69	```json
70	{"next_url": "https://www.amazon.com/s?k=headphones&page=2", "has_next": true, "method": "amazon"}
71	```
72
73	When `has_next` is false, pagination is complete.
74
75	### Composite: Keyword search with filters → product list
76
77	Step 1 — Build search URL with filters:
78
79	Construct the URL based on target site and desired filters using the patterns below, then navigate:
80
81	Amazon (`amazon.com`):
82	```
83	https://www.amazon.com/s?k={keyword_urlencoded}&s={sort}&rh={filter_params}
84	```
85	- Sort (`s`): `price-asc-rank` \| `price-desc-rank` \| `review-rank` \| `date-desc-rank` (omit for relevance)
86	- Price filter: append `p_36:{min_cents}-{max_cents}` to `rh` (dollars × 100, e.g. $50–$200 → `p_36:5000-20000`)
87	- Rating filter: append `avg_customer_review:four-and-above` \| `three-and-above` \| `two-and-above` to `rh`
88	- In-stock: append `p_n_availability:1248801011` to `rh`
89	- Multiple `rh` values: comma-separate (e.g. `rh=p_36:5000-20000,avg_customer_review:four-and-above`)
90
91	eBay (`ebay.com`):
92	```
93	https://www.ebay.com/sch/i.html?_nkw={keyword_urlencoded}&_udlo={min_price}&_udhi={max_price}&_sop={sort_num}
94	```
95	- Sort: `12`=BestMatch \| `15`=PriceLow \| `16`=PriceHigh \| `24`=NewlyListed
96
97	Walmart (`walmart.com`):
98	```
99	https://www.walmart.com/search?q={keyword_urlencoded}&min_price={min}&max_price={max}&sort={sort}
100	```
101	- Sort: `best_match` \| `price_low` \| `price_high` \| `rating_high`
102
103	Google Shopping (cross-site, no `--site`):
104	```
105	https://www.google.com/search?tbm=shop&q={keyword_urlencoded}&tbs=p_ord:{sort}
106	```
107	- Sort: `rv`=relevance \| `pd`=price ascending \| `prd`=price descending
108
109	Any site with `--site` (generic):
110	```
111	https://{site}/search?q={keyword_urlencoded}
112	```
113
114	Step 2 — Navigate and extract:
115	1. `navigate {constructed_url}` → `wait stable`
116	2. `eval "$(python scripts/extract-listing.py --max-results {n})"`
117
118	Step 3 — Paginate (repeat until done):
119	1. `eval "$(python scripts/extract-listing-next-page.py)"`
120	2. If `has_next` is true: `navigate {next_url}` → `wait stable` → re-run extract-listing.py
121	3. If `has_next` is false: stop
122
123	## Pagination
124
125	URL Pagination: `extract

People who liked this also viewed

6 picks

Type

ecommerce-listing

3installs220forks

View on GitHub

How to install ecommerce-listing?

browser-act/skills/ecommerce-listing

$npx -y skills add browser-act/skills --skill ecommerce-listing

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# E-commerce — Product Listing
2
3	> Category/search URL or keyword + filters → paginated product list (URL, name, price, image, rating per item)
4
5	## Language
6
7	All process output to user (progress updates, process notifications) follows the user's language.
8
9	## Objective
10
11	Extract a structured list of products from any e-commerce category, search results, or keyword search page, with support for price/brand/rating filters and multi-page pagination.
12
13	## Prerequisites
14
15	- Target browser is open and connected
16	- No login required for public listing pages
17
18	## Pre-execution Checks
19
20	### 1. Tool Readiness
21
22	If browser-act has been confirmed available in the current session → skip this step.
23
24	Invoke `browser-act` via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
25
26	## Capability Components
27
28	> 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. JS code is encapsulated in Python files under the `scripts/` directory, invoked via `eval "$(python scripts/xxx.py {params})"`. Use the bash tool for execution.
29
30	### DOM: Extract product list from current page
31
32	Navigate to the listing/search page first, then extract:
33
34	```bash
35	eval "$(python scripts/extract-listing.py --max-results 20)"
36	```
37
38	Parameters:
39	- `--max-results`: max items to return per page, default 20
40
41	Output example:
42	```json
43	{
44	"count": 20,
45	"items": [
46	{
47	"url": "https://www.amazon.com/dp/B09WNK39JN",
48	"name": "Amazon Echo Pop",
49	"price": 39.99,
50	"currency": "USD",
51	"image": "https://m.media-amazon.com/images/I/...jpg",
52	"rating": 4.7,
53	"review_count": 103789,
54	"asin": "B09WNK39JN"
55	}
56	]
57	}
58	```
59
60	### DOM: Get next page URL
61
62	After extracting a page, get the URL to navigate to for the next page:
63
64	```bash
65	eval "$(python scripts/extract-listing-next-page.py)"
66	```
67
68	Output example:
69	```json
70	{"next_url": "https://www.amazon.com/s?k=headphones&page=2", "has_next": true, "method": "amazon"}
71	```
72
73	When `has_next` is false, pagination is complete.
74
75	### Composite: Keyword search with filters → product list
76
77	Step 1 — Build search URL with filters:
78
79	Construct the URL based on target site and desired filters using the patterns below, then navigate:
80
81	Amazon (`amazon.com`):
82	```
83	https://www.amazon.com/s?k={keyword_urlencoded}&s={sort}&rh={filter_params}
84	```
85	- Sort (`s`): `price-asc-rank` \| `price-desc-rank` \| `review-rank` \| `date-desc-rank` (omit for relevance)
86	- Price filter: append `p_36:{min_cents}-{max_cents}` to `rh` (dollars × 100, e.g. $50–$200 → `p_36:5000-20000`)
87	- Rating filter: append `avg_customer_review:four-and-above` \| `three-and-above` \| `two-and-above` to `rh`
88	- In-stock: append `p_n_availability:1248801011` to `rh`
89	- Multiple `rh` values: comma-separate (e.g. `rh=p_36:5000-20000,avg_customer_review:four-and-above`)
90
91	eBay (`ebay.com`):
92	```
93	https://www.ebay.com/sch/i.html?_nkw={keyword_urlencoded}&_udlo={min_price}&_udhi={max_price}&_sop={sort_num}
94	```
95	- Sort: `12`=BestMatch \| `15`=PriceLow \| `16`=PriceHigh \| `24`=NewlyListed
96
97	Walmart (`walmart.com`):
98	```
99	https://www.walmart.com/search?q={keyword_urlencoded}&min_price={min}&max_price={max}&sort={sort}
100	```
101	- Sort: `best_match` \| `price_low` \| `price_high` \| `rating_high`
102
103	Google Shopping (cross-site, no `--site`):
104	```
105	https://www.google.com/search?tbm=shop&q={keyword_urlencoded}&tbs=p_ord:{sort}
106	```
107	- Sort: `rv`=relevance \| `pd`=price ascending \| `prd`=price descending
108
109	Any site with `--site` (generic):
110	```
111	https://{site}/search?q={keyword_urlencoded}
112	```
113
114	Step 2 — Navigate and extract:
115	1. `navigate {constructed_url}` → `wait stable`
116	2. `eval "$(python scripts/extract-listing.py --max-results {n})"`
117
118	Step 3 — Paginate (repeat until done):
119	1. `eval "$(python scripts/extract-listing-next-page.py)"`
120	2. If `has_next` is true: `navigate {next_url}` → `wait stable` → re-run extract-listing.py
121	3. If `has_next` is false: stop
122
123	## Pagination
124
125	URL Pagination: `extract

People who liked this also viewed

6 picks

Type