This commit is contained in:
37
docs/snippets/go/metadata/page_boundaries.md
Normal file
37
docs/snippets/go/metadata/page_boundaries.md
Normal file
@@ -0,0 +1,37 @@
|
||||
```go title="Go"
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log"
|
||||
|
||||
"github.com/kreuzberg-dev/kreuzberg/v5"
|
||||
)
|
||||
|
||||
func main() {
|
||||
result, err := kreuzberg.ExtractFileSync("document.pdf", nil)
|
||||
if err != nil {
|
||||
log.Fatal(err)
|
||||
}
|
||||
|
||||
if result.Metadata.Pages == nil || result.Metadata.Pages.Boundaries == nil {
|
||||
return
|
||||
}
|
||||
|
||||
contentBytes := []byte(result.Content)
|
||||
for i, boundary := range result.Metadata.Pages.Boundaries {
|
||||
if i >= 3 {
|
||||
break
|
||||
}
|
||||
pageText := string(contentBytes[boundary.ByteStart:boundary.ByteEnd])
|
||||
preview := pageText
|
||||
if len(preview) > 100 {
|
||||
preview = preview[:100]
|
||||
}
|
||||
|
||||
fmt.Printf("Page %d:\n", boundary.PageNumber)
|
||||
fmt.Printf(" Byte range: %d-%d\n", boundary.ByteStart, boundary.ByteEnd)
|
||||
fmt.Printf(" Preview: %s...\n", preview)
|
||||
}
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user