goofish-item-detail

Name: goofish-item-detail
Author: browser-act

2installs220forks

How to install goofish-item-detail?

browser-act/skills/goofish-item-detail

$npx -y skills add browser-act/skills --skill goofish-item-detail

Installs into the current project.

Summary

Extracts full detail data from a single Goofish (闲鱼/xianyu, goofish.com) second-hand item page. Input: item URL or item ID. Output: title, price, seller info (name, labels), full description, image gallery, item tags/attributes, want-count. Use when user mentions goofish item det

Files · 1

View on GitHub

SKILL.md

1	# Goofish (闲鱼) — Item Detail
2
3	> item URL (or item_id + category_id) → full listing data: title, price, seller info, description, images, tags, want-count
4
5	## Language
6
7	All process output to user (progress updates, process notifications) follows the user's language.
8
9	## Objective
10
11	Load a single Goofish item detail page and extract its complete listing data including seller information, item description, image gallery, and attribute tags.
12
13	## Prerequisites
14
15	- Browser with an active Goofish session (login required — item detail pages require authenticated access)
16	- Target item URL format: `https://www.goofish.com/item?id={item_id}&categoryId={category_id}`
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	### 2. Login Verification
27
28	If login status for Goofish has been confirmed in the current session → skip this step.
29
30	Otherwise: open `https://www.goofish.com/` and observe the page:
31	- User avatar or account entry exists → logged in, continue
32	- Login/register prompt → not logged in; inform user that login is required; assist login flow
33
34	User refuses or cannot log in → terminate execution.
35
36	## Capability Components
37
38	> This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed on the page. JS code is encapsulated in Python files under the `scripts/` directory, invoked via `eval "$(python scripts/xxx.py {params})"`. `$(...)` is bash syntax; use the bash tool for execution.
39
40	### Network Capture: load item detail page
41
42	The item detail API (`mtop.taobao.idle.pc.detail/1.0/`) auto-fires when navigating to the item URL. Provide parameters via URL:
43
44	1. `navigate https://www.goofish.com/item?id={item_id}&categoryId={category_id}`
45	2. `wait stable`
46	3. Proceed to DOM extraction below
47
48	Error handling:
49	- If a CAPTCHA slider appears ("Please slide to verify"): the session is rate-limited. Wait 5–10 minutes, or use remote-assist to complete the slider manually, then re-navigate.
50	- If "网络不见了" error page appears: the item page API call failed. Retry once after 30 seconds; if it persists, the session may be temporarily blocked.
51	- If item shows "该宝贝已下架" or similar: item has been removed/sold — skip and move to next item.
52
53	Note: Navigating to item detail pages in rapid succession (e.g., less than 2 seconds apart) increases the probability of CAPTCHA. Add 2–5 second delays between items in batch mode.
54
55	### DOM: extract item detail data
56
57	After navigating and waiting stable, extract all available fields:
58
59	`eval "$(python scripts/extract-item-detail.py)"`
60
61	Output example:
62	```json
63	{
64	"item_id": "1054899470781",
65	"item_url": "https://www.goofish.com/item?id=1054899470781&categoryId=126862528",
66	"title": "出一台iPhone 15 128G，电池健康度高，成色九新以上...",
67	"price": "898.00",
68	"original_price": "899.00",
69	"seller_name": "小王数码严选",
70	"seller_avatar": "https://img.alicdn.com/bao/uploaded/...",
71	"seller_labels": ["成都", "刚刚擦亮", "来闲鱼5年", "卖出204件宝贝", "好评率100%"],
72	"description": "出一台iPhone 15 128G，电池健康度高，成色九新以上...",
73	"images": [
74	"https://img.alicdn.com/bao/uploaded/i4/...",
75	"https://img.alicdn.com/bao/uploaded/i2/..."
76	],
77	"tags": ["品牌：Apple/苹果", "型号：iPhone 15", "存储容量：128GB", "运行内存：6GB", "成色：几乎全新"],
78	"want_count": "8人想要"
79	}
80	```
81
82	Fields that may be null: `original_price`, `seller_labels`, `description`, `tags`, `want_count` (depending on listing completeness). Note: on Goofish detail pages, `title` and `description` contain the same text — there is no separate title element.
83
84	## Pagination
85
86	N/A — single item page, no pagination.
87
88	## Success Criteria
89
90	`item_id non-null` and `title non-null` and `price non-null`
91
92	## Known Limitations
93
94	- Seller user ID (numeric) is not exposed in the DOM — only seller display name is available
95	- Item detail pages trigger CAPTCHA if accessed too rapidly; recommended minimum interval: 3 seconds between items
96	- Some items may require login even for viewing; the Skill will return an error if the page fails to load
97	- Rapid successive navigation may trigger "网络不见了" error — wait 30 seconds before retrying
98
99	## Execution Efficiency
100
101	- Batch orchestration

People who liked this also viewed

6 picks

Type

goofish-item-detail

2installs220forks

View on GitHub

How to install goofish-item-detail?

browser-act/skills/goofish-item-detail

$npx -y skills add browser-act/skills --skill goofish-item-detail

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Goofish (闲鱼) — Item Detail
2
3	> item URL (or item_id + category_id) → full listing data: title, price, seller info, description, images, tags, want-count
4
5	## Language
6
7	All process output to user (progress updates, process notifications) follows the user's language.
8
9	## Objective
10
11	Load a single Goofish item detail page and extract its complete listing data including seller information, item description, image gallery, and attribute tags.
12
13	## Prerequisites
14
15	- Browser with an active Goofish session (login required — item detail pages require authenticated access)
16	- Target item URL format: `https://www.goofish.com/item?id={item_id}&categoryId={category_id}`
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	### 2. Login Verification
27
28	If login status for Goofish has been confirmed in the current session → skip this step.
29
30	Otherwise: open `https://www.goofish.com/` and observe the page:
31	- User avatar or account entry exists → logged in, continue
32	- Login/register prompt → not logged in; inform user that login is required; assist login flow
33
34	User refuses or cannot log in → terminate execution.
35
36	## Capability Components
37
38	> This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed on the page. JS code is encapsulated in Python files under the `scripts/` directory, invoked via `eval "$(python scripts/xxx.py {params})"`. `$(...)` is bash syntax; use the bash tool for execution.
39
40	### Network Capture: load item detail page
41
42	The item detail API (`mtop.taobao.idle.pc.detail/1.0/`) auto-fires when navigating to the item URL. Provide parameters via URL:
43
44	1. `navigate https://www.goofish.com/item?id={item_id}&categoryId={category_id}`
45	2. `wait stable`
46	3. Proceed to DOM extraction below
47
48	Error handling:
49	- If a CAPTCHA slider appears ("Please slide to verify"): the session is rate-limited. Wait 5–10 minutes, or use remote-assist to complete the slider manually, then re-navigate.
50	- If "网络不见了" error page appears: the item page API call failed. Retry once after 30 seconds; if it persists, the session may be temporarily blocked.
51	- If item shows "该宝贝已下架" or similar: item has been removed/sold — skip and move to next item.
52
53	Note: Navigating to item detail pages in rapid succession (e.g., less than 2 seconds apart) increases the probability of CAPTCHA. Add 2–5 second delays between items in batch mode.
54
55	### DOM: extract item detail data
56
57	After navigating and waiting stable, extract all available fields:
58
59	`eval "$(python scripts/extract-item-detail.py)"`
60
61	Output example:
62	```json
63	{
64	"item_id": "1054899470781",
65	"item_url": "https://www.goofish.com/item?id=1054899470781&categoryId=126862528",
66	"title": "出一台iPhone 15 128G，电池健康度高，成色九新以上...",
67	"price": "898.00",
68	"original_price": "899.00",
69	"seller_name": "小王数码严选",
70	"seller_avatar": "https://img.alicdn.com/bao/uploaded/...",
71	"seller_labels": ["成都", "刚刚擦亮", "来闲鱼5年", "卖出204件宝贝", "好评率100%"],
72	"description": "出一台iPhone 15 128G，电池健康度高，成色九新以上...",
73	"images": [
74	"https://img.alicdn.com/bao/uploaded/i4/...",
75	"https://img.alicdn.com/bao/uploaded/i2/..."
76	],
77	"tags": ["品牌：Apple/苹果", "型号：iPhone 15", "存储容量：128GB", "运行内存：6GB", "成色：几乎全新"],
78	"want_count": "8人想要"
79	}
80	```
81
82	Fields that may be null: `original_price`, `seller_labels`, `description`, `tags`, `want_count` (depending on listing completeness). Note: on Goofish detail pages, `title` and `description` contain the same text — there is no separate title element.
83
84	## Pagination
85
86	N/A — single item page, no pagination.
87
88	## Success Criteria
89
90	`item_id non-null` and `title non-null` and `price non-null`
91
92	## Known Limitations
93
94	- Seller user ID (numeric) is not exposed in the DOM — only seller display name is available
95	- Item detail pages trigger CAPTCHA if accessed too rapidly; recommended minimum interval: 3 seconds between items
96	- Some items may require login even for viewing; the Skill will return an error if the page fails to load
97	- Rapid successive navigation may trigger "网络不见了" error — wait 30 seconds before retrying
98
99	## Execution Efficiency
100
101	- Batch orchestration

People who liked this also viewed

6 picks

Type