dsh-read-url
Token-efficient URL reader and web scraper for DeepSeek Harness with encoding detection and body extraction.
Install
No clear install command was found in the current repository evidence.
Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Clean main-content extraction from HTML using container-level and heuristic filtering
- Multi-encoding detection including UTF-16 BOM, GBK/GB2312, Shift-JIS, Big5, and UTF-8
- Native support for JSON APIs and RSS/Atom feed rendering
- Token-saving paragraph-aligned truncation, URL fragment section slicing, and cache-backed offset continuation
- Batch URL processing (`read_url_batch`) with isolated failure handling
- Recursive same-host site crawling (`read_url_site`) and link extraction (`read_url_links`)
- Optional SPA rendering with Playwright and Readability engine integration
Useful For
- Reading web documentation, articles, and news directly into DeepSeek Harness LLM context without token waste
- Comparing content across multiple URLs in parallel via batch requests
- Indexing or discovering structure across documentation sites via recursive crawling
- Extracting structured Markdown or clean plain text from legacy encoded or multi-page articles
Who It Fits
- DeepSeek Harness users needing reliable web-reading tools for research and summarization
- Developers building DSH agent workflows requiring clean, low-token page body ingestion
Documented Limitations
- Cannot read pages protected behind login walls or interactive captchas
- Full client-side JavaScript SPA rendering requires optional Playwright and browser dependencies
- Flattens HTML into readable text, losing exact field-to-value relational associations found in raw APIs
- XML sitemaps and non-text binary formats (such as PDFs or images) are intentionally unsupported
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- 2672243194/dsh-read-url
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 5d19503 · 2026-10-16
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 20GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-03
- Last release
- 2026-10-03
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Free and multi-engine web search provider for DeepSeek Harness with automatic fallback and web settings UI.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →