apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-05-13 00:42:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

feat: structured data in markdown/LLM output + v0.3.6

Browse source 
__NEXT_DATA__, SvelteKit, and JSON-LD now appear as a
## Structured Data section in -f markdown and -f llm output.
Works with --only-main-content and all extraction flags.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Valerio 2026-04-02 19:16:56 +02:00
parent b219fc3648
commit 344eea74d9
5 changed files with 37 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

13
crates/webclaw-cli/src/main.rs
View file

@ -535,6 +535,13 @@ fn format_output(result: &ExtractionResult, format: &OutputFormat, show_metadata
out.push_str(&format_frontmatter(&result.metadata));
}
out.push_str(&result.content.markdown);
if !result.structured_data.is_empty() {
out.push_str("\n\n## Structured Data\n\n```json\n");
out.push_str(
&serde_json::to_string_pretty(&result.structured_data).unwrap_or_default(),
);
out.push_str("\n```");
}
out
}
OutputFormat::Json => serde_json::to_string_pretty(result).expect("serialization failed"),
@ -838,6 +845,12 @@ fn print_output(result: &ExtractionResult, format: &OutputFormat, show_metadata:
print!("{}", format_frontmatter(&result.metadata));
}
println!("{}", result.content.markdown);
if !result.structured_data.is_empty() {
println!(
"\n## Structured Data\n\n```json\n{}\n```",
serde_json::to_string_pretty(&result.structured_data).unwrap_or_default()
);
}
}
OutputFormat::Json => {
// serde_json::to_string_pretty won't fail on our types