from img2table.ocr import PaddleOCR
ocr = PaddleOCR(lang="en",                 kw={"kwarg": kw_value, ...})

from img2table.ocr import EasyOCR
ocr = EasyOCR(lang=["en"],               kw={"kwarg": kw_value, ...})

from img2table.ocr import DocTR
ocr = DocTR(detect_language=False,             kw={"kwarg": kw_value, ...})

from img2table.ocr import RapidOCR
ocr = RapidOCR(params={"Rec.langtype": ..., "kwarg": kwvalue, ...})

from img2table.ocr import SuryaOCR
ocr = SuryaOCR(langs=["en"])

from img2table.ocr import VisionOCR
ocr = VisionOCR(apikey="apikey", timeout=15)

from img2table.ocr import TextractOCR
ocr = TextractOCR(awsaccesskey_id="*",                   awssecretaccess_key="*",                   aws_sessi,                   region="eu-west-1")

from img2table.ocr import AzureOCR
ocr = AzureOCR(endpoint="abc.azure.com",                subscripti)

Table extraction

Multiple tables can be extracted at once from a PDF page/ an image using the extract_tables method of a document.

from img2table.ocr import TesseractOCR
from img2table.document import Image
Instantiation of OCR
ocr = TesseractOCR()
Instantiation of document, either an image or a PDF
doc = Image(src)
Table extraction
extractedtables = doc.extracttables(ocr=ocr,
                                      implicit_rows=False,
                                      implicit_columns=False,
                                      borderless_tables=False,
                                      min_confidence=50,
                                      max_workers=1)

Parameters

ocr : OCRInstance, optional, default None

OCR instance used to parse document text. If None, cells content will not be extracted

implicit_rows : bool, optional, default False

Boolean indicating if implicit rows should be identified - check related example

implicit_columns : bool, optional, default False

Boolean indicating if implicit columns should be identified - check related example

borderless_tables : bool, optional, default False

Boolean indicating if borderless tables are extracted on top of bordered tables.

min_confidence : int, optional, default 50

Minimum confidence level from OCR in order to process text, from 0 (worst) to 99 (best)

max_workers : int, optional, default 1

Number of concurrent workers used for table extraction. Mainly useful for multi-page PDFs.

Method return

The ExtractedTable class is used to model extracted tables from documents.

Attributes

bbox : BBox

Table bounding box, with absolute coordinates and normalized coordinates available via bbox.relative

title : str

Extracted title of the table

content : OrderedDict

Dict with row indexes as keys and list of TableCell objects as values

df : pd.DataFrame

Pandas DataFrame representation of the table

html : str

HTML representation of the table

In order to access bounding boxes at the cell level, you can use the following code snippet :

for id_row, row in enumerate(table.content.values()):
    for id_col, cell in enumerate(row):
        x1 = cell.bbox.x1
        y1 = cell.bbox.y1
        x2 = cell.bbox.x2
        y2 = cell.bbox.y2
        value = cell.value

Normalized coordinates (in percentage of image height / width) are also available on the same object:

relative_bbox = cell.bbox.relative
x1 = relative_bbox.x1
y1 = relative_bbox.y1
x2 = relative_bbox.x2
y2 = relative_bbox.y2

Images

extract_tables method from the Image class returns a list of ExtractedTable objects.

output = [ExtractedTable(...), ExtractedTable(...), ...]

PDF

extract_tables method from the PDF class returns an OrderedDict object with page indexes as keys and lists of ExtractedTable objects.

output = {
    0: [ExtractedTable(...), ...],
    1: [],
    ...
    last_page: [ExtractedTable(...), ...]
}

Excel export

Tables extracted from a document can be exported to a xlsx file. The resulting file is composed of one worksheet per extracted table.
Method arguments are mostly common with the extract_tables method.

from img2table.ocr import TesseractOCR
from img2table.document import Image
Instantiation of OCR
ocr = TesseractOCR()
Instantiation of document, either an image or a PDF
doc = Image(src)
Extraction of tables and creation of a xlsx file containing tables
doc.to_xlsx(dest=dest,
            ocr=ocr,
            implicit_rows=False,
            implicit_columns=False,
            borderless_tables=False,
            min_confidence=50,
            max_workers=1)

Parameters

dest : str, pathlib.Path or io.BytesIO, required

Destination for xlsx file

ocr : OCRInstance, optional, default None

OCR instance used to parse document text. If None, cells content will not be extracted

implicit_rows : bool, optional, default False

Boolean indicating if implicit rows should be identified - check related example

implicit_columns : bool, optional, default False

Boolean indicating if implicit columns should be identified - check related example

borderless_tables : bool, optional, default False

Boolean indicating if borderless tables are extracted.

min_confidence : int, optional, default 50

Minimum confidence level from OCR in order to process text, from 0 (worst) to 99 (best)

max_workers : int, optional, default 1

Number of concurrent workers used for table extraction. Mainly useful for multi-page PDFs.

Returns

If a io.BytesIO buffer is passed as dest arg, it is returned containing xlsx data

Examples

Several Jupyter notebooks with examples are available :

• Basic usage: generic library usage, including examples with images, PDF and OCRs
• Borderless tables: specific examples dedicated to the extraction of borderless tables
• Implicit content: illustrated effect of the parameter implicitrows/implicitcolumns of the extract_tables method

FYI / Caveats

• For a high-level description of the implemented bordered and borderless table detection algorithms, see the table detection algorithms documentation.
• For table extraction, results are highly dependent on OCR quality. By design, tables where no OCR data can be found are not returned.
• The library is tailored for usage on documents with white/light background. Effectiveness can not be guaranteed on other type of documents.
• Table detection using only OpenCV processing can have some limitations. If the library fails to detect tables, you may check CNN / LLM based solutions.