mirror of
https://github.com/0xMassi/webclaw.git
synced 2026-06-07 22:15:12 +02:00
Initial release: webclaw v0.1.0 — web content extraction for LLMs
CLI + MCP server for extracting clean, structured content from any URL. 6 Rust crates, 10 MCP tools, TLS fingerprinting, 5 output formats. MIT Licensed | https://webclaw.io
This commit is contained in:
commit
c99ec684fa
79 changed files with 24074 additions and 0 deletions
14
crates/webclaw-pdf/src/error.rs
Normal file
14
crates/webclaw-pdf/src/error.rs
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
/// PDF extraction errors. Kept simple -- no OCR, no complex recovery.
|
||||
use thiserror::Error;
|
||||
|
||||
#[derive(Debug, Error)]
|
||||
pub enum PdfError {
|
||||
#[error("PDF extraction failed: {0}")]
|
||||
ExtractionFailed(String),
|
||||
|
||||
#[error("invalid PDF: {0}")]
|
||||
InvalidPdf(String),
|
||||
|
||||
#[error("empty PDF: no text content found")]
|
||||
EmptyPdf,
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue