InputPath <- system.file("extdata", package = "ORscraper")
files <- read_pdf_files(InputPath)
lines <- read_pdf_content(files[1]) # Example with the first file
diagnostic <- gender <- tumor_cell_percentage <- quality <- c()
diagnostic <- extract_values_start_end(diagnostic, lines, ".*Diagnóstico:\\s")
gender <- extract_values_start_end(gender, lines, ".*Sexo:\\s*")
tumor_cell_percentage <- extract_values_start_end(
tumor_cell_percentage,
lines,
".*% células tumorales:\\s")
quality <- extract_values_start_end(
quality,
lines,
".*CALIDAD DE LA MUESTRA /LIMITACIONES PARA SU ANÁLISIS:\\s")
Run the code above in your browser using DataLab