Created
January 31, 2024 21:23
-
-
Save alaingilbert/d9ee32efb41ffc9789ddd4ef0fb73435 to your computer and use it in GitHub Desktop.
quick hack to extract and decode text out of a pdf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package main | |
import ( | |
"bytes" | |
"os" | |
"os/exec" | |
"regexp" | |
"strconv" | |
) | |
func main() { | |
_ = getContent() | |
by, _ := os.ReadFile("BS_22_23_Content_page_1.txt") | |
processPdfRaw(by) | |
} | |
func processPdfRaw(in []byte) { | |
// Remove all new lines | |
in = bytes.Join(bytes.Split(in, []byte{'\n'}), []byte{' '}) | |
// Replace all hex values with their corresponding text | |
rgx := regexp.MustCompile(`<(\w+)>`) | |
in = rgx.ReplaceAllFunc(in, func(b []byte) []byte { | |
return []byte("<" + hexToTxt(string(b[1:len(b)-1])) + ">") | |
}) | |
in = bytes.ReplaceAll(in, []byte(" Q q "), []byte("\nQ q\n")) | |
// Put all BT (Begin Text) on their own line | |
in = bytes.ReplaceAll(in, []byte(" ET "), []byte(" ET\n")) | |
in = bytes.ReplaceAll(in, []byte(" BT"), []byte("\nBT")) | |
in = bytes.ReplaceAll(in, []byte(" f "), []byte(" f\n")) | |
// Save to file | |
_ = os.WriteFile("test.txt", in, 0644) | |
} | |
func hexToTxt(h string) (out string) { | |
for i := 0; i < len(h); i += 4 { | |
n, _ := strconv.ParseInt(h[i:i+4], 16, 64) | |
out += string(rune(n + 29)) | |
} | |
return | |
} | |
func getContent() error { | |
cmd := exec.Command("pdfcpu", "extract", "-mode", "content", "BS_22_23.pdf", ".") | |
_, err := cmd.Output() | |
return err | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment