ghostcrawl-langchain
LangChain tool integration for the GhostCrawl web data API.
Exposes the GhostCrawl scrape / content / map / search / extract / crawl /
usage / Google-vertical surfaces as LangChain BaseTool subclasses with shared
Pydantic params validation.
Install
pip install ghostcrawl-langchain
Publish = yes (public PyPI ghostcrawl-langchain).
Framework-lane surface (idiomatic retrieval subset vs N/A)
ghostcrawl-langchain is a framework lane, not a full SDK: it wraps the
idiomatic retrieval subset of the GhostCrawl API as LangChain tools an agent
can call. Everything else is an explicit N/A — not a gap, just not idiomatic
as an LC retrieval Tool/loader (zero blank cells, zero padded-green; D-10/D-11).
| Capability | Status | Tool / rationale |
|---|---|---|
| scrape | ✅ GREEN | GhostCrawlScrapeTool → POST /v1/scrape |
| content | ✅ GREEN | GhostCrawlContentTool → POST /v1/content |
| extract | ✅ GREEN | GhostCrawlExtractTool → POST /v1/extract |
| map | ✅ GREEN | GhostCrawlMapTool → POST /v1/map |
| crawl | ✅ GREEN | GhostCrawlCrawlTool → POST /v1/crawl (seeds seed_urls) |
| search | N/A (BYO) | GhostCrawlSearchTool reaches /v1/search, which needs a user-supplied search-backend key (X-Provider-Authorization); a keyless call returns 401 search_backend_key_missing. The keyless ghostcrawl_google_search tool is the LC-idiomatic alternative. |
| crawl-runs, schedules, webhooks, recordings, kv, profiles, sessions, datasets, identity, me, storage-states | N/A | management / mutation — not a retrieval tool for an agent |
| pdf, screenshot | N/A | binary capture — not idiomatic as a text-returning LC tool/loader |
| agent | N/A (BYO) | agent is BYO/not-hosted (require_agent_enabled() 404); the developer supplies the LLM |
Every tool is verified by a real-execution parity suite (transcripts record counts
- variable names only); re-run with
make -C sdks/python-langchain parity-e2e.
License
Proprietary — GhostCrawl Software License. See LICENSE.
1 maintainer
Metadata
1 maintainer
Release files for ghostcrawl-langchain 2.3.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ghostcrawl_langchain-2.3.5.tar.gz | 50.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ghostcrawl_langchain-2.3.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 66.7 kB
Release files / ghostcrawl_langchain-2.3.5.tar.gz
| Download URL | ghostcrawl_langchain-2.3.5.tar.gz |
|---|---|
| Size | 50.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f1aa3f460c6b4f62773deceddc845e3fab256adab48ebc2640cfdbabe460b9e9
|
|
BLAKE2b-256 checksum How to use checksums |
120b9293b0f054ea1c7cf2261ef99b4fe78a4343b54e3d53ffa50f679dad61be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / ghostcrawl_langchain-2.3.5-py3-none-any.whl
| Download URL | ghostcrawl_langchain-2.3.5-py3-none-any.whl |
|---|---|
| Size | 16.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8614a5077d0c372d747adcf96975dff66495f034c0850c6de53fe6a3be39a951
|
|
BLAKE2b-256 checksum How to use checksums |
66efe9b3065e6b116d2988f7ce78388766a94273221e62e485cab45c0b749a8c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
