Skip to content

Reference

TextRedactor

Redact a text from a pdf file

Methods:

  • redact_text(file_path: Path, text_to_redact: str, output_file_name:Path) -> bool

  • redact_all_files_in_dir(base_path: Path, text_to_redact: str, output_file_suffix: str) -> None

Source code in redact_pdf/redact.py 
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
class TextRedactor:
    """Redact a text from a pdf file

    Methods:

    - redact_text(file_path: Path, text_to_redact: str, output_file_name:Path) -> bool

    - redact_all_files_in_dir(base_path: Path, text_to_redact: str, output_file_suffix: str) -> None
    """

    def redact_text(self, file_path: Path, text_to_redact: str, output_file_name: Path) -> bool:
        """Open the document and redact the text

        Args:
            file_path (Path): PDF file path.
            text_to_redact (str): Text or phrase to be redacted in every page of pdf file.
            output_file_name (Path): PDF file name (include .pdf) to be saved after redact.

        Returns:
            bool: If successfully redacts the text in pdf

        Examples:
            >>> from redact_pdf.redact import TextRedactor
            >>> tr = TextRedactor()
            >>> pdf_file = Path("path/to/input.pdf")
            >>> TEXT_TO_REDACT = "Confidential"
            >>> save_path = Path("path/to/output.pdf")
            >>> tr.redact_text(file_path=pdf_file, text_to_redact=TEXT_TO_REDACT, output_file_name=save_path)
        """
        doc = None
        try:
            logger.info("Opening file...")
            doc = fitz.open(file_path)
            redacted = False
            logger.success("File Opened.")

            for i in range(doc.page_count):
                logger.info("Checking page {}", i + 1)
                page = doc.load_page(i)
                redaction_list = page.search_for(text_to_redact, quads=True)

                if redaction_list:  # Ensure results were found before proceeding
                    logger.info("Found text at page {}", i + 1)
                    redacted = True
                    for redact_area in redaction_list:
                        page.add_redact_annot(redact_area)
                        page.apply_redactions()  # Apply redactions
                    logger.success("Applied Redactions.")

            if redacted:
                logger.info("Saving file...")
                doc.save(output_file_name, compression_effort=5)
                logger.info(f"Successfully redacted and saved: {output_file_name}")

                return True
            else:
                logger.info(f"No text found to redact in: {file_path}")
                return False
        except Exception as e:
            logger.error(f"Error processing {file_path}: {e}")
            return False
        finally:
            if doc is not None:
                doc.close()

    def redact_all_files_in_dir(self, base_path: Path, text_to_redact: str, output_file_suffix: str) -> None:
        """Redact all files in a local directory

        Args:
            base_path (Path): Base directory to find all *.pdf files (recursively)
            text_to_redact (str): Text or phrase to be redacted in every page of pdf file.
            output_file_suffix (Path): Suffix to append to original file name to be saved.

        Returns:
            None

        Examples:
            >>> from redact_pdf.redact import TextRedactor
            >>> tr = TextRedactor()
            >>> base_path = Path("path/to/files/")
            >>> TEXT_TO_REDACT = "Confidential"
            >>> suffix = "redacted"
            >>> tr.redact_all_files_in_dir(base_path=base_path, text_to_redact=TEXT_TO_REDACT, output_file_suffix=suffix)
        """
        processed_count = 0
        error_count = 0
        try:
            for file in base_path.rglob("*.pdf"):
                try:
                    file_stem = file.stem
                    result = self.redact_text(
                        file, text_to_redact, file.with_name(file_stem + f"_{output_file_suffix}.pdf")
                    )
                    if result:
                        processed_count += 1
                except Exception as e:
                    logger.error(f"Failed to process {file}: {e}")
                    error_count += 1

            logger.info(f"Processing complete. Successfully processed: {processed_count}, Errors: {error_count}")

        except Exception as e:
            logger.error(f"Fatal error during processing: {e}")

redact_all_files_in_dir(base_path, text_to_redact, output_file_suffix)

Redact all files in a local directory

Parameters:

Name Type Description Default
base_path Path

Base directory to find all *.pdf files (recursively)

 required
text_to_redact str

Text or phrase to be redacted in every page of pdf file.

 required
output_file_suffix Path

Suffix to append to original file name to be saved.

 required

Returns:

Type Description
None

None

Examples:

>>> from redact_pdf.redact import TextRedactor
>>> tr = TextRedactor()
>>> base_path = Path("path/to/files/")
>>> TEXT_TO_REDACT = "Confidential"
>>> suffix = "redacted"
>>> tr.redact_all_files_in_dir(base_path=base_path, text_to_redact=TEXT_TO_REDACT, output_file_suffix=suffix)
Source code in redact_pdf/redact.py 
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
def redact_all_files_in_dir(self, base_path: Path, text_to_redact: str, output_file_suffix: str) -> None:
    """Redact all files in a local directory

    Args:
        base_path (Path): Base directory to find all *.pdf files (recursively)
        text_to_redact (str): Text or phrase to be redacted in every page of pdf file.
        output_file_suffix (Path): Suffix to append to original file name to be saved.

    Returns:
        None

    Examples:
        >>> from redact_pdf.redact import TextRedactor
        >>> tr = TextRedactor()
        >>> base_path = Path("path/to/files/")
        >>> TEXT_TO_REDACT = "Confidential"
        >>> suffix = "redacted"
        >>> tr.redact_all_files_in_dir(base_path=base_path, text_to_redact=TEXT_TO_REDACT, output_file_suffix=suffix)
    """
    processed_count = 0
    error_count = 0
    try:
        for file in base_path.rglob("*.pdf"):
            try:
                file_stem = file.stem
                result = self.redact_text(
                    file, text_to_redact, file.with_name(file_stem + f"_{output_file_suffix}.pdf")
                )
                if result:
                    processed_count += 1
            except Exception as e:
                logger.error(f"Failed to process {file}: {e}")
                error_count += 1

        logger.info(f"Processing complete. Successfully processed: {processed_count}, Errors: {error_count}")

    except Exception as e:
        logger.error(f"Fatal error during processing: {e}")

redact_text(file_path, text_to_redact, output_file_name)

Open the document and redact the text

Parameters:

Name Type Description Default
file_path Path

PDF file path.

 required
text_to_redact str

Text or phrase to be redacted in every page of pdf file.

 required
output_file_name Path

PDF file name (include .pdf) to be saved after redact.

 required

Returns:

Name Type Description
bool bool

If successfully redacts the text in pdf

Examples:

>>> from redact_pdf.redact import TextRedactor
>>> tr = TextRedactor()
>>> pdf_file = Path("path/to/input.pdf")
>>> TEXT_TO_REDACT = "Confidential"
>>> save_path = Path("path/to/output.pdf")
>>> tr.redact_text(file_path=pdf_file, text_to_redact=TEXT_TO_REDACT, output_file_name=save_path)
Source code in redact_pdf/redact.py 
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
def redact_text(self, file_path: Path, text_to_redact: str, output_file_name: Path) -> bool:
    """Open the document and redact the text

    Args:
        file_path (Path): PDF file path.
        text_to_redact (str): Text or phrase to be redacted in every page of pdf file.
        output_file_name (Path): PDF file name (include .pdf) to be saved after redact.

    Returns:
        bool: If successfully redacts the text in pdf

    Examples:
        >>> from redact_pdf.redact import TextRedactor
        >>> tr = TextRedactor()
        >>> pdf_file = Path("path/to/input.pdf")
        >>> TEXT_TO_REDACT = "Confidential"
        >>> save_path = Path("path/to/output.pdf")
        >>> tr.redact_text(file_path=pdf_file, text_to_redact=TEXT_TO_REDACT, output_file_name=save_path)
    """
    doc = None
    try:
        logger.info("Opening file...")
        doc = fitz.open(file_path)
        redacted = False
        logger.success("File Opened.")

        for i in range(doc.page_count):
            logger.info("Checking page {}", i + 1)
            page = doc.load_page(i)
            redaction_list = page.search_for(text_to_redact, quads=True)

            if redaction_list:  # Ensure results were found before proceeding
                logger.info("Found text at page {}", i + 1)
                redacted = True
                for redact_area in redaction_list:
                    page.add_redact_annot(redact_area)
                    page.apply_redactions()  # Apply redactions
                logger.success("Applied Redactions.")

        if redacted:
            logger.info("Saving file...")
            doc.save(output_file_name, compression_effort=5)
            logger.info(f"Successfully redacted and saved: {output_file_name}")

            return True
        else:
            logger.info(f"No text found to redact in: {file_path}")
            return False
    except Exception as e:
        logger.error(f"Error processing {file_path}: {e}")
        return False
    finally:
        if doc is not None:
            doc.close()