A high-performance scraping skill for Yandex.Archive that extracts historical documents, newspapers, and directories while bypassing advanced bot protections.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install yandex-archive-scraper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install yandex-archive-scraper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Yandex Archive Scraper?
The Yandex Archive Scraper is a specialized addition to the collection of Openclaw Skills, engineered to navigate and extract deep historical data from the Yandex.Archive portal (Яндекс.Архив). It provides a programmatic interface to retrieve records that are otherwise difficult to access due to complex search interfaces and aggressive anti-bot measures.
By leveraging the Scrapling framework and StealthyFetcher, this skill ensures reliable data retrieval by bypassing Cloudflare Turnstile and Yandex bot detection. It is an essential tool for researchers needing to digitize information from metric books, revision tales, and historical gazettes without manual data entry.
Yandex Archive Scraper Use Cases
- Genealogical research for tracing family lineage through metric books and revision tales.
- Academic historical research involving old newspapers like the Senate Gazette or Provincial Gazette.
- Professional data gathering from historical address calendars and resident lists for demographic studies.
- Automated monitoring and collection of newly digitized archival records across Russian historical databases.
How Yandex Archive Scraper Works
- The skill receives a natural language query specifying names, locations, or specific historical dates.
- It converts the input into an optimized Yandex.Archive search URL targeting one of three specific indexes: archive, mass_media, or directories.
- A stealthy browser instance is initialized via Scrapling to bypass anti-bot shields and Cloudflare Turnstile.
- The tool parses the resulting HTML to extract document titles, text snippets, and direct source links.
- If requested, the skill handles pagination to collect data across multiple search result pages.
Yandex Archive Scraper Setup
To utilize this skill within your Openclaw Skills environment, ensure you have the necessary dependencies installed:
pip install scrapling playwright curl_cffi patchright msgspec browserforge
playwright install chromium
Once installed, configure the skill in your AI agent's toolset to begin querying the Yandex.Archive indexes.
Yandex Archive Scraper Data Schema & Taxonomy
The skill returns structured data from the archive searches. The schema includes:
| Attribute | Description |
|---|---|
| title | The name of the archived document, record, or newspaper issue. |
| snippet | A text fragment containing the search terms found within the document. |
| link | Direct URL to the specific document image or portal page. |
| index | The specific database searched (archive, mass_media, or directories). |
| page | The current page number within the paginated results. |
Yandex Archive Scraper Advanced Features
- Integrated StealthyFetcher to navigate Cloudflare Turnstile and Yandex bot protection seamlessly.
- Support for targeted index searching, allowing users to filter by periodicals or administrative directories.
- Multi-page scraping capabilities for comprehensive data collection on common search terms.
- Natural language processing that converts simple user prompts into complex, index-specific search parameters.
SKILL.md
Loading
Related Openclaw Skills
Free Text to Video Generator
A powerful tool that transforms written scripts and concepts into fully rendered, engaging videos without requiring manual editing or footage.
Claude API Builder
A specialized skill designed to architect and implement robust integrations for Anthropic's Claude API, covering everything from streaming to complex tool use.
Photo Editor AI
A sophisticated AI-driven image editing assistant that automates complex retouching, background removal, and professional color grading through natural language commands.
WeChat Article Extractor
A robust extraction tool for converting WeChat Official Account articles into structured Markdown or JSON data.
Claude MD Initializer
An automated utility to generate or enhance CLAUDE.md files, ensuring AI agents understand your repository's unique architecture and commands.
Free AI Video Editor Online
A conversational AI video editor that transforms raw clips into polished content using text commands and cloud-based rendering.
Featured*
