Baidu Search MCP server

<!-- Language toggle --> English | 中文

🔍 Baidu API: Structured Baidu Search Results in Clean JSON

The most efficient, reliable, and developer-friendly way to use the Baidu API.

Actor page: apify.com/johnvc/Baidu-Search-Scraper Input schema: apify.com/johnvc/Baidu-Search-Scraper/input-schema

The Baidu API (百度) runs a Baidu search for any keyword and returns clean, structured JSON. Each run gives you organic results (title, link, snippet, position), answer boxes, related videos, "people also search for" suggestions, related searches, and trending top searches, plus per-page metadata and pagination details. It supports desktop, mobile, and tablet results, Simplified and Traditional Chinese localization, time-range filtering, and multi-page pagination.

Video Walkthrough

Quick Start

Prerequisites

• Python 3.11 or higher
• An Apify account and API key (get a free key here)

1. Clone the repository

git clone https://github.com/johnisanerd/Apify-Baidu-Search-Scraper.git
   cd Apify-Baidu-Search-Scraper

1. Install dependencies with UV

# Install UV if you do not have it:
   curl -LsSf https://astral.sh/uv/install.sh | sh

   # Install project dependencies:
   uv sync

1. Configure your API key

cp .env.example .env
   # Edit .env and add your Apify API key
   # Get your free API key at: https://apify.com?fpr=9n7kx3

1. Run the example

uv run python baidu-search-scraper.py

Alternative: set the API key directly

export APIFY_API_TOKEN="your_api_key_here"
uv run python baidu-search-scraper.py

Why Use This Baidu API?

Complete SERP coverage. One call returns the full Baidu results page as structured data: organic listings, answer boxes, related videos, "people also search for", related searches, and trending top searches. You get the whole page, not just ten blue links.

Built for China-market research. Target Simplified or Traditional Chinese results, switch between desktop, mobile, and tablet, and filter by a precise date range. That makes it practical for SEO, market research, and brand monitoring in Chinese-language markets.

Predictable, pay-per-use pricing. Billing is per run plus per page processed, with no monthly rental. You pay for the searches you actually make, and you control cost directly with the page limit.

Clean, consistent JSON. Every response uses the same shape, so you parse results once and reuse the code across queries. Per-page metadata and pagination details make it easy to page through larger result sets.

Easy to automate. Call it from Python in a few lines, or load it as an MCP tool so assistants like Claude and Cursor can run Baidu searches for you on demand.

Features

Core Capabilities

• Keyword search across Baidu with full results-page extraction
• Device targeting for desktop, mobile, and tablet results
• Language localization for all languages, Simplified Chinese, or Traditional Chinese
• Time-range filtering using Unix timestamp windows
• Multi-page pagination with a configurable page limit

Data Quality

• Structured organic results with title, link, snippet, position, and rich data
• Rich result blocks: answer boxes, related videos, people also search for, related searches, top searches
• Per-page metadata with result counts and pagination details
• Consistent JSON shape across every query
• Per-page billing so larger searches stay transparent

Usage Examples

Shortened. The full README is on GitHub.