Skip to content

Pdf Module

PDF file handler for text extraction.

Classes:

Name Description
PDFHandler

Handler for extracting text from PDF files with improved error handling.

Classes

PDFHandler

Bases: FileTypeHandler

Handler for extracting text from PDF files with improved error handling.

Methods:

Name Description
extract
extract_async
Source code in textxtract/handlers/pdf.py 
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
class PDFHandler(FileTypeHandler):
    """Handler for extracting text from PDF files with improved error handling."""

    def extract(self, file_path: Path, config: Optional[dict] = None) -> str:
        try:
            try:
                import fitz  # PyMuPDF
            except ImportError:
                raise ExtractionError(
                    "PyMuPDF package is not installed. Install with 'pip install text-extractor[pdf]'"
                )

            doc = fitz.open(file_path)
            extracted_text = []
            empty_pages = 0

            for page_num, page in enumerate(doc):
                page_text = page.get_text("text").strip()
                if not page_text:
                    empty_pages += 1
                    # Try OCR-like text extraction for images
                    page_text = page.get_text("dict")  # Get structured text
                    if page_text and "blocks" in page_text:
                        # Check if page has images but no text
                        has_images = any(
                            block.get("type") == 1
                            for block in page_text.get("blocks", [])
                        )
                        if has_images:
                            extracted_text.append(
                                f"[Page {page_num + 1}: Contains images but no extractable text]"
                            )
                        else:
                            extracted_text.append(f"[Page {page_num + 1}: Empty page]")
                    else:
                        extracted_text.append(f"[Page {page_num + 1}: Empty page]")
                else:
                    extracted_text.append(page_text)

            doc.close()

            # Only raise error if ALL pages are empty and there's no content at all
            if not any(
                text.strip() and not text.startswith("[Page") for text in extracted_text
            ):
                if empty_pages == len(extracted_text):
                    raise InvalidFileError(
                        f"PDF contains {empty_pages} empty pages with no extractable text. "
                        "This may be a scanned PDF that requires OCR."
                    )

            result = "\n".join(extracted_text)
            return result

        except fitz.FileDataError as e:
            raise InvalidFileError(f"Invalid or corrupted PDF file: {e}")
        except fitz.EmptyFileError:
            raise InvalidFileError("PDF file is empty")
        except Exception as e:
            if isinstance(e, (ExtractionError, InvalidFileError)):
                raise
            raise ExtractionError(f"PDF extraction failed: {e}")

    async def extract_async(
        self, file_path: Path, config: Optional[dict] = None
    ) -> str:
        import asyncio

        return await asyncio.to_thread(self.extract, file_path, config)

Functions

extract 
extract(file_path, config=None)
Source code in textxtract/handlers/pdf.py 
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
def extract(self, file_path: Path, config: Optional[dict] = None) -> str:
    try:
        try:
            import fitz  # PyMuPDF
        except ImportError:
            raise ExtractionError(
                "PyMuPDF package is not installed. Install with 'pip install text-extractor[pdf]'"
            )

        doc = fitz.open(file_path)
        extracted_text = []
        empty_pages = 0

        for page_num, page in enumerate(doc):
            page_text = page.get_text("text").strip()
            if not page_text:
                empty_pages += 1
                # Try OCR-like text extraction for images
                page_text = page.get_text("dict")  # Get structured text
                if page_text and "blocks" in page_text:
                    # Check if page has images but no text
                    has_images = any(
                        block.get("type") == 1
                        for block in page_text.get("blocks", [])
                    )
                    if has_images:
                        extracted_text.append(
                            f"[Page {page_num + 1}: Contains images but no extractable text]"
                        )
                    else:
                        extracted_text.append(f"[Page {page_num + 1}: Empty page]")
                else:
                    extracted_text.append(f"[Page {page_num + 1}: Empty page]")
            else:
                extracted_text.append(page_text)

        doc.close()

        # Only raise error if ALL pages are empty and there's no content at all
        if not any(
            text.strip() and not text.startswith("[Page") for text in extracted_text
        ):
            if empty_pages == len(extracted_text):
                raise InvalidFileError(
                    f"PDF contains {empty_pages} empty pages with no extractable text. "
                    "This may be a scanned PDF that requires OCR."
                )

        result = "\n".join(extracted_text)
        return result

    except fitz.FileDataError as e:
        raise InvalidFileError(f"Invalid or corrupted PDF file: {e}")
    except fitz.EmptyFileError:
        raise InvalidFileError("PDF file is empty")
    except Exception as e:
        if isinstance(e, (ExtractionError, InvalidFileError)):
            raise
        raise ExtractionError(f"PDF extraction failed: {e}")
extract_async async 
extract_async(file_path, config=None)
Source code in textxtract/handlers/pdf.py 
73
74
75
76
77
78
async def extract_async(
    self, file_path: Path, config: Optional[dict] = None
) -> str:
    import asyncio

    return await asyncio.to_thread(self.extract, file_path, config)