res-x

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

X/Twitter Fetch & Search

X/Twitter 内容抓取与搜索

Fetch tweet content by URL and search X posts using xAI Responses API with Grok's

x_search

tool. Solves the problem of X/Twitter blocking WebFetch with "JavaScript disabled" errors.

借助Grok的

x_search

工具，通过xAI Responses API实现通过URL抓取推文内容、搜索X帖子的功能，解决了X/Twitter以「JavaScript未启用」错误拦截WebFetch抓取的问题。

Architecture

架构

Capability	API Tool	Cost
Fetch tweet by URL	xAI `x_search`	~$0.005/call
Search X	xAI `x_search`	~$0.005/call

Fetching batches URLs in groups of 3 per API call to reduce cost.

能力	API工具	成本
按URL抓取推文	xAI `x_search`	单次调用约$0.005
搜索X内容	xAI `x_search`	单次调用约$0.005

每次API调用将URL按3个一组批量处理以降低成本。

Prerequisites

前置条件

Required Tools

所需工具

Tool	Purpose	Install
uv	Python package manager (handles dependencies)	`curl -LsSf https://astral.sh/uv/install.sh \| sh`

工具	用途	安装方式
uv	Python包管理器（处理依赖）	`curl -LsSf https://astral.sh/uv/install.sh \| sh`

API Key

API密钥

Service	Purpose	Required	Get Key
xAI	X/Twitter access via Grok	Yes	https://console.x.ai

This skill requires an xAI API key. There is no fallback mode.

服务	用途	是否必填	密钥获取地址
xAI	通过Grok访问X/Twitter	是	https://console.x.ai

本工具需要xAI API密钥，无备用运行模式。

Keychain Setup (One-Time)

密钥链设置（仅需配置一次）

bash

undefined

bash

undefined

1. Create a dedicated keychain (skip if already exists)

1. 创建专用密钥链（如果已存在可跳过）

security create-keychain -p 'YourPassword' ~/Library/Keychains/claude-keys.keychain-db

2. Add keychain to search list

2. 将密钥链添加到搜索列表

security list-keychains -s ~/Library/Keychains/claude-keys.keychain-db ~/Library/Keychains/login.keychain-db /Library/Keychains/System.keychain

3. Store your xAI API key

3. 存储你的xAI API密钥

echo -n "Enter xAI API key: " && read -s key && security add-generic-password -s "xai-api" -a "$USER" -w "$key" ~/Library/Keychains/claude-keys.keychain-db && unset key && echo


Before using: `security unlock-keychain ~/Library/Keychains/claude-keys.keychain-db`

echo -n "Enter xAI API key: " && read -s key && security add-generic-password -s "xai-api" -a "$USER" -w "$key" ~/Library/Keychains/claude-keys.keychain-db && unset key && echo


使用前执行：`security unlock-keychain ~/Library/Keychains/claude-keys.keychain-db`

Script Usage

脚本用法

bash

undefined

bash

undefined

Fetch single tweet

抓取单条推文

uv run scripts/x_fetch.py fetch "https://x.com/user/status/123456"

Fetch multiple tweets (batched, 3 per API call)

抓取多条推文（批量处理，每次API调用处理3条）

uv run scripts/x_fetch.py fetch "url1" "url2" "url3" "url4" "url5"

Force one-per-URL for max fidelity

强制每个URL单独调用以获得最高保真度

uv run scripts/x_fetch.py fetch "url1" "url2" --single

Search X

搜索X内容

uv run scripts/x_fetch.py search "query terms" uv run scripts/x_fetch.py search "query terms" --quick

JSON output (both commands)

输出JSON格式结果（上述两个命令均支持）

uv run scripts/x_fetch.py fetch "url" --json uv run scripts/x_fetch.py search "query" --json

undefined

uv run scripts/x_fetch.py fetch "url" --json uv run scripts/x_fetch.py search "query" --json

undefined

Workflow

工作流程

Step 0: Detect xAI Key (Mandatory)

步骤0：检测xAI密钥（必填）

Run before every invocation:

bash

security find-generic-password -s "xai-api" -w ~/Library/Keychains/claude-keys.keychain-db 2>/dev/null && echo "XAI_AVAILABLE=true" || echo "XAI_AVAILABLE=false"

XAI_AVAILABLE=false

, report that this skill requires an xAI key and show the keychain setup instructions above.

每次调用前运行：

bash

security find-generic-password -s "xai-api" -w ~/Library/Keychains/claude-keys.keychain-db 2>/dev/null && echo "XAI_AVAILABLE=true" || echo "XAI_AVAILABLE=false"

如果

XAI_AVAILABLE=false

，提示本工具需要xAI密钥并展示上述密钥链设置指引。

Step 1: Detect Intent

步骤1：识别意图

URLs present in user input or referenced note -> fetch
Query text only -> search

用户输入或引用的笔记中存在URL → 执行抓取
仅包含查询文本 → 执行搜索

Step 2: Execute

步骤2：执行操作

For fetch:

Extract all X/Twitter URLs from user input or referenced file
Run the script with all URLs as arguments
The script batches them (3 per API call) automatically

For search:

Run the script with the search query
Use
```
--quick
```
for fast overview, omit for deeper results

抓取场景：

从用户输入或引用的文件中提取所有X/Twitter URL
将所有URL作为参数运行脚本
脚本自动将URL按3个一组批量处理

搜索场景：

携带搜索查询词运行脚本
如需快速概览使用
```
--quick
```
参数，如需更深度的结果则省略该参数

Step 3: Present Results

步骤3：展示结果

For fetch: present tweet-by-tweet with full content, engagement, thread/quote context
For search: present as a list with engagement metrics

抓取场景：逐推文展示完整内容、互动数据、推文串/引用上下文
搜索场景：以列表形式展示附带互动指标的结果

URL Patterns Accepted

支持的URL格式

https://x.com/{user}/status/{id}
https://twitter.com/{user}/status/{id}
https://x.com/{user}/status/{id}?s=20
https://x.com/{user}/status/{id}?t=...&s=...
https://x.com/i/article/{id}

Tweets normalized to

https://x.com/{user}/status/{id}

, articles to

https://x.com/i/article/{id}

before processing.

https://x.com/{user}/status/{id}
https://twitter.com/{user}/status/{id}
https://x.com/{user}/status/{id}?s=20
https://x.com/{user}/status/{id}?t=...&s=...
https://x.com/i/article/{id}

处理前会将推文统一格式化为

https://x.com/{user}/status/{id}

，文章统一格式化为

https://x.com/i/article/{id}

。

Batch Processing

批量处理

For processing saved X links from a file (e.g., Obsidian daily note):

Read the file content

Extract all X/Twitter URLs (tweets:

https?://(?:x\.com|twitter\.com)/\w+/status/\d+

, articles:

https?://(?:x\.com|twitter\.com)/i/article/[\w\-]+

)

Pass all URLs to the script:

uv run scripts/x_fetch.py fetch "url1" "url2" ...

Present results organized by URL

如需处理保存在文件（例如Obsidian每日笔记）中的X链接：

读取文件内容

提取所有X/Twitter URL（推文匹配规则：

https?://(?:x\.com|twitter\.com)/\w+/status/\d+

，文章匹配规则：

https?://(?:x\.com|twitter\.com)/i/article/[\w\-]+

）

将所有URL传递给脚本：

uv run scripts/x_fetch.py fetch "url1" "url2" ...

按URL分类展示结果

Cost

成本说明

Action	API Calls	Cost
Fetch 1-3 tweets	1	~$0.005
Fetch 4-6 tweets	2	~$0.010
Fetch 10 tweets	4	~$0.020
Fetch 10 tweets (--single)	10	~$0.050
X search	1	~$0.005
X search (--quick)	1	~$0.005

操作	API调用次数	成本
抓取1-3条推文	1	约$0.005
抓取4-6条推文	2	约$0.010
抓取10条推文	4	约$0.020
抓取10条推文（使用--single参数）	10	约$0.050
X搜索	1	约$0.005
X搜索（使用--quick参数）	1	约$0.005

Constraints

使用约束

DO:

Run Step 0 before every invocation
Validate URLs before calling the script
Use
```
--json
```
when parsing results programmatically
Present full tweet content without truncation

DON'T:

Try WebFetch on X URLs (fails with JS disabled)
Skip the xAI key check
Use this for general web search (use
```
res-web
```
or
```
res-deep
```
)

允许的操作：

每次调用前执行步骤0的密钥检测
调用脚本前校验URL有效性
程序化解析结果时使用
```
--json
```
参数
完整展示推文内容不做截断

禁止的操作：

尝试对X URL使用WebFetch（会因JavaScript未启用报错失败）
跳过xAI密钥检测步骤
将本工具用于通用网页搜索（请使用
```
res-web
```
或
```
res-deep
```
）

Troubleshooting

故障排查

xAI key not found:

bash

security find-generic-password -s "xai-api" ~/Library/Keychains/claude-keys.keychain-db

If not found, run keychain setup above.

Keychain locked:

bash

security unlock-keychain ~/Library/Keychains/claude-keys.keychain-db

Script errors: Ensure uv is installed:

which uv

找不到xAI密钥：

bash

security find-generic-password -s "xai-api" ~/Library/Keychains/claude-keys.keychain-db

如果未查询到结果，请运行上述密钥链设置步骤。

密钥链已锁定：

bash

security unlock-keychain ~/Library/Keychains/claude-keys.keychain-db

脚本报错： 确认已安装uv：

which uv