21 lines
549 B
Markdown
21 lines
549 B
Markdown
|
|
```r title="R"
|
||
|
|
library(kreuzberg)
|
||
|
|
|
||
|
|
# Extract a document
|
||
|
|
result <- extract_file_sync("document.docx")
|
||
|
|
|
||
|
|
# Access core content fields
|
||
|
|
cat(sprintf("MIME type: %s\n", mime_type(result)))
|
||
|
|
cat(sprintf("Content length: %d characters\n", nchar(content(result))))
|
||
|
|
|
||
|
|
# Access structured data
|
||
|
|
cat(sprintf("Number of tables: %d\n", length(result$tables)))
|
||
|
|
cat(sprintf("Detected language: %s\n", detected_language(result)))
|
||
|
|
|
||
|
|
# Access metadata
|
||
|
|
author <- metadata_field(result, "author")
|
||
|
|
if (!is.null(author)) {
|
||
|
|
cat(sprintf("Document author: %s\n", author))
|
||
|
|
}
|
||
|
|
```
|