parallel-web-extract
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseURL Extraction
URL 内容提取
Extract content from: $ARGUMENTS
提取以下来源的内容:$ARGUMENTS
Command
命令
bash
parallel-cli extract "$ARGUMENTS" --jsonOptions if needed:
- to focus on specific content
--objective "focus area"
bash
parallel-cli extract "$ARGUMENTS" --json如需使用可添加以下选项:
- :聚焦特定内容
--objective "focus area"
Claude Code
Claude Code
If you are running in Claude Code, run this command in a forked context using the Task tool:
Task tool:
subagent_type: "parallel:parallel-subagent"
prompt: |
Run: parallel-cli extract "$ARGUMENTS" --json
Parse the JSON from stdout. Return content as:
**[Page Title](URL)**
<extracted content verbatim - skip navigation, menus, boilerplate>
Keep content verbatim. Strip only obvious noise.如果在Claude Code环境中运行,请使用Task工具在forked上下文中执行此命令:
Task tool:
subagent_type: "parallel:parallel-subagent"
prompt: |
Run: parallel-cli extract "$ARGUMENTS" --json
Parse the JSON from stdout. Return content as:
**[Page Title](URL)**
<extracted content verbatim - skip navigation, menus, boilerplate>
Keep content verbatim. Strip only obvious noise.Response format
响应格式
Return content as:
Page Title
Then the extracted content verbatim, with these rules:
- Keep content verbatim - do not paraphrase or summarize
- Parse lists exhaustively - extract EVERY numbered/bulleted item
- Strip only obvious noise: nav menus, footers, ads
- Preserve all facts, names, numbers, dates, quotes
请按照以下格式返回内容:
页面标题
然后原样返回提取的内容,需遵循以下规则:
- 内容原样保留,不得改写或总结
- 完整解析列表——提取所有编号/项目符号项
- 仅去除明显冗余内容:导航菜单、页脚、广告
- 保留所有事实、名称、数字、日期、引用内容
Setup
安装配置
If is not found, install and authenticate:
parallel-clibash
curl -fsSL https://parallel.ai/install.sh | bash
parallel-cli loginOr set an API key:
export PARALLEL_API_KEY="your-key"如果未找到,请进行安装和认证:
parallel-clibash
curl -fsSL https://parallel.ai/install.sh | bash
parallel-cli login或设置API密钥:
export PARALLEL_API_KEY="your-key"