Baidu ERNIE Bot User Agents

Complete guide to Baidu ERNIE Bot (文心一言) crawlers - China's largest LLM with 200M+ users

Back to Documentation

Baidu ERNIE Bot (文心一言, Yiyan) is China's largest AI language model with over 200 million monthly active users. Developed by Baidu (百度), China's leading search engine, ERNIE Bot is deeply integrated into Baidu's search ecosystem and represents approximately 35% of the Chinese LLM market.

About Baidu ERNIE Bot

Company

Baidu (百度)

Founded

2023 (ERNIE models since 2019)

Latest Model

ERNIE Bot 4.0

Context Window

8K-32K tokens

Website

yiyan.baidu.com

Key Feature

Baidu Search integration

🏆 Market Leader

ERNIE Bot is the largest LLM deployment in China with over 200 million monthly active users and ~35% market share. It's integrated directly into Baidu Search, giving it unprecedented reach across Chinese internet users.

What is Baidu ERNIE Bot's Main User Agent String?

Baidu ERNIE Bot uses multiple user agent identifiers for different crawling purposes. Understanding these patterns is crucial for Chinese market optimization.

ERNIE Bot Crawler

Mozilla/5.0 (compatible; ERNIEBot/1.0; +https://yiyan.baidu.com/bot)

Primary user agent for ERNIE Bot's AI-specific crawling operations.

Baiduspider (Traditional Crawler)

Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)

Baidu's traditional search crawler, also used for ERNIE Bot content indexing.

Alternative ERNIE User Agents

ERNIE-Bot
YiyanBot
Baidu-YunGuanCe

Additional crawler patterns used by Baidu for AI training and monitoring.

Detection Patterns

To detect Baidu ERNIE crawlers in your web analytics or server logs:

JavaScript Detection

// Detect Baidu ERNIE user agents
const isERNIE = /ERNIEBot|ERNIE-Bot|YiyanBot|Baiduspider|Baidu-YunGuanCe/i.test(navigator.userAgent);

if (isERNIE) {
  console.log('Baidu ERNIE crawler detected');
  // Track visit, customize content for Chinese market
}

Server-Side Detection (Node.js)

// Express.js middleware
app.use((req, res, next) => {
  const userAgent = req.headers['user-agent'] || '';
  const isErnieBot = /ERNIEBot|ERNIE-Bot|YiyanBot|Baidu-YunGuanCe/i.test(userAgent);
  const isBaiduspider = /Baiduspider/i.test(userAgent);
  
  if (isErnieBot || isBaiduspider) {
    console.log('Baidu AI crawler detected:', userAgent);
    req.isBaiduAI = true;
  }
  next();
});

How Many Users Does Baidu ERNIE Bot Have?

Baidu ERNIE Bot dominates the Chinese LLM market:

200M+

Monthly Active Users

~35%

Chinese LLM Market Share

#1

Largest in China

Why ERNIE Bot is Important for SEO

ERNIE Bot's integration with Baidu Search makes it critical for Chinese market visibility:

🔍 Baidu Search Integration

ERNIE Bot powers AI-generated answers in Baidu Search results. Content that performs well with ERNIE Bot gets featured in AI overviews, significantly increasing visibility to Chinese users.

🇨🇳 Market Dominance

With 200M+ users and ~70% search market share in China, Baidu's ecosystem is essential for reaching Chinese audiences. ERNIE Bot optimization = Baidu Search optimization.

🎯 Direct User Access

ERNIE Bot is accessible via yiyan.baidu.com, Baidu App, and integrated into various Baidu services including Maps, Translation, and Cloud, giving it massive distribution.

🏢 Enterprise Adoption

Widely adopted by Chinese enterprises and government organizations, making it critical for B2B and official communications in China.

How Baidu ERNIE Accesses Web Content

ERNIE Bot uses multiple methods to gather and process web content:

🔍 Search Enhancement

Actively crawls content to enhance Baidu Search results with AI-generated summaries and answers. This is the primary use case affecting most websites.

💬 Conversational Queries

When users ask questions in ERNIE Bot chat interface, it may access specific URLs to provide current, accurate information.

📚 Knowledge Base

Regular crawling maintains an updated understanding of Chinese web content, news, and trending topics for better response quality.

🎓 Model Training

Content is used for continuous model training and improvement, particularly for Chinese language understanding and cultural context.

How Do I Block Baidu ERNIE from Crawling My Website?

Control Baidu ERNIE's access using robots.txt directives:

Block All Baidu AI Crawlers

To completely prevent Baidu's AI crawlers from accessing your website:

# Block all Baidu AI/ERNIE crawlers
User-agent: Baiduspider
User-agent: ERNIEBot
User-agent: ERNIE-Bot
User-agent: YiyanBot
User-agent: Baidu-YunGuanCe
Disallow: /

⚠️ Warning: Blocking Baiduspider will affect your Baidu Search rankings in China!

Block Only AI Features (Recommended)

Allow traditional search crawling but block AI-specific features:

# Block AI features but allow search indexing
User-agent: ERNIEBot
User-agent: ERNIE-Bot
User-agent: YiyanBot
User-agent: Baidu-YunGuanCe
Disallow: /

# Allow Baiduspider for search indexing
User-agent: Baiduspider
Allow: /

Selective Access

Allow public content while protecting sensitive areas:

# Selective blocking for Baidu AI
User-agent: Baiduspider
User-agent: ERNIEBot
User-agent: YiyanBot
Disallow: /admin/
Disallow: /private/
Disallow: /user/
Disallow: /api/
Allow: /blog/
Allow: /products/
Allow: /docs/

Optimizing Content for ERNIE Bot

Best practices for maximizing visibility in ERNIE Bot and Baidu Search:

🇨🇳 Chinese Language

  • Use Simplified Chinese (简体中文) for mainland China
  • Ensure proper character encoding (UTF-8)
  • Use natural, colloquial Chinese expressions
  • Consider regional dialects and preferences

🏗️ Content Structure

  • Clear headings and logical organization
  • Use Baidu-friendly meta tags
  • Include summaries and key points
  • Mobile-first design (most Chinese users are mobile)

🎯 Local Context

  • Use China-specific examples and references
  • Include Chinese social media links (WeChat, Weibo)
  • Reference Chinese brands and companies
  • Comply with Chinese content regulations

⚡ Technical SEO

  • Host in China for better crawl rates (ICP license)
  • Use Chinese CDN (Alibaba Cloud, Tencent Cloud)
  • Fast loading times (critical for Chinese networks)
  • Baidu Webmaster Tools verification

ERNIE Bot API Integration

Baidu provides APIs for integrating ERNIE Bot into applications:

API Configuration

// ERNIE Bot API endpoint
const API_ENDPOINT = 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1';

// Available models
const MODELS = {
  'ernie-bot-4': 'ERNIE Bot 4.0',      // Latest flagship
  'ernie-bot-3.5': 'ERNIE Bot 3.5',    // Balanced performance
  'ernie-speed': 'ERNIE Speed',        // Fast responses
  'ernie-lite': 'ERNIE Lite'           // Lightweight
};

// Get access token first
const getAccessToken = async () => {
  const response = await fetch(
    `https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=${API_KEY}&client_secret=${SECRET_KEY}`
  );
  const data = await response.json();
  return data.access_token;
};

// Example API call
const callERNIE = async (message) => {
  const accessToken = await getAccessToken();
  
  const response = await fetch(
    `${API_ENDPOINT}/wenxinworkshop/chat/ernie-bot-4?access_token=${accessToken}`,
    {
      method: 'POST',
      headers: { 'Content-Type': 'application/json' },
      body: JSON.stringify({
        messages: [{ role: 'user', content: message }]
      })
    }
  );
  
  return await response.json();
};

💡 API Access

To access ERNIE Bot APIs, register at Baidu Cloud and apply for WENXIN Workshop access. Note: May require Chinese business registration for full access.

Tracking ERNIE Bot Visits with xSeek

xSeek provides comprehensive tracking for Baidu ERNIE crawler activity:

📊 Comprehensive Monitoring

Track all Baidu AI crawler visits including ERNIEBot, YiyanBot, and Baiduspider separately to understand different access patterns.

🇨🇳 Chinese Market Insights

Understand how your content performs in China's AI ecosystem and track citation frequency in ERNIE Bot responses.

📈 Search Integration Analysis

Monitor how ERNIE Bot crawling correlates with Baidu Search visibility and AI Overview appearances.

🔔 Market Alerts

Receive notifications when Baidu's crawling behavior changes or when your content gets featured in AI-generated answers.

FAQ

What is Baidu ERNIE Bot's main user agent string?

Baidu ERNIE Bot uses 'Mozilla/5.0 (compatible; ERNIEBot/1.0; +https://yiyan.baidu.com/bot)' as its primary user agent. It also uses the traditional Baiduspider crawler for content indexing.

How many users does Baidu ERNIE Bot have?

Baidu ERNIE Bot has over 200 million monthly active users, making it the largest LLM deployment in China with approximately 35% market share as of 2024.

How do I block Baidu ERNIE from crawling my website?

Add 'User-agent: ERNIEBot', 'User-agent: Baiduspider', and 'User-agent: YiyanBot' followed by 'Disallow: /' to your robots.txt file. However, blocking Baiduspider will affect your Baidu Search rankings in China.

Should I block Baiduspider if I don't want AI training?

You can block ERNIEBot and YiyanBot specifically while allowing Baiduspider for search indexing. This lets you maintain search visibility while limiting AI-specific features. However, Baiduspider also feeds ERNIE Bot, so complete separation isn't possible.

How important is ERNIE Bot for reaching Chinese users?

Extremely important. With 200M+ users and integration into Baidu Search (70% market share in China), ERNIE Bot is critical for reaching Chinese audiences. Optimizing for ERNIE Bot = optimizing for the Chinese market.

Related Chinese LLM User Agents

Learn about other Chinese AI user agents:

Related User Agents

Learn about other AI user agents:

Track Baidu ERNIE & Chinese LLMs

Monitor Baidu ERNIE Bot crawler visits, optimize for Chinese AI search engines, and dominate the Chinese market with xSeek.