├── .gitignore ├── PDFSyncAPI.zip ├── README.md ├── misc ├── CreateLayer.md ├── UseProvidedLayer.md ├── boto3-layer.zip └── samples │ ├── analyze-document-forms │ ├── employmentapp.png │ └── forms-parser.py │ ├── analyze-document-tables │ ├── draw-table.py │ ├── employmentapp.png │ └── exportcsv.py │ ├── detect-document-text │ ├── call_analyze_doc.py │ ├── call_comprehend.py │ ├── call_detect_text.py │ ├── call_translate.py │ ├── reading_order.py │ ├── simple-document-pdf.pdf │ ├── simple_text_document.jpg │ └── two_column_sample.jpg │ ├── simple-document-pdf.pdf │ └── simple_text_document.json ├── src ├── helper.py ├── og.py ├── ta.py ├── tdp.py ├── temp-response.json ├── textractor.py ├── trp.py └── trptest.py └── zip └── textractor.zip /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | -------------------------------------------------------------------------------- /PDFSyncAPI.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/PDFSyncAPI.zip -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/README.md -------------------------------------------------------------------------------- /misc/CreateLayer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/CreateLayer.md -------------------------------------------------------------------------------- /misc/UseProvidedLayer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/UseProvidedLayer.md -------------------------------------------------------------------------------- /misc/boto3-layer.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/boto3-layer.zip -------------------------------------------------------------------------------- /misc/samples/analyze-document-forms/employmentapp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/analyze-document-forms/employmentapp.png -------------------------------------------------------------------------------- /misc/samples/analyze-document-forms/forms-parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/analyze-document-forms/forms-parser.py -------------------------------------------------------------------------------- /misc/samples/analyze-document-tables/draw-table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/analyze-document-tables/draw-table.py -------------------------------------------------------------------------------- /misc/samples/analyze-document-tables/employmentapp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/analyze-document-tables/employmentapp.png -------------------------------------------------------------------------------- /misc/samples/analyze-document-tables/exportcsv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/analyze-document-tables/exportcsv.py -------------------------------------------------------------------------------- /misc/samples/detect-document-text/call_analyze_doc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/call_analyze_doc.py -------------------------------------------------------------------------------- /misc/samples/detect-document-text/call_comprehend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/call_comprehend.py -------------------------------------------------------------------------------- /misc/samples/detect-document-text/call_detect_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/call_detect_text.py -------------------------------------------------------------------------------- /misc/samples/detect-document-text/call_translate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/call_translate.py -------------------------------------------------------------------------------- /misc/samples/detect-document-text/reading_order.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/reading_order.py -------------------------------------------------------------------------------- /misc/samples/detect-document-text/simple-document-pdf.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/simple-document-pdf.pdf -------------------------------------------------------------------------------- /misc/samples/detect-document-text/simple_text_document.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/simple_text_document.jpg -------------------------------------------------------------------------------- /misc/samples/detect-document-text/two_column_sample.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/detect-document-text/two_column_sample.jpg -------------------------------------------------------------------------------- /misc/samples/simple-document-pdf.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/simple-document-pdf.pdf -------------------------------------------------------------------------------- /misc/samples/simple_text_document.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/misc/samples/simple_text_document.json -------------------------------------------------------------------------------- /src/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/helper.py -------------------------------------------------------------------------------- /src/og.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/og.py -------------------------------------------------------------------------------- /src/ta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/ta.py -------------------------------------------------------------------------------- /src/tdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/tdp.py -------------------------------------------------------------------------------- /src/temp-response.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/temp-response.json -------------------------------------------------------------------------------- /src/textractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/textractor.py -------------------------------------------------------------------------------- /src/trp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/trp.py -------------------------------------------------------------------------------- /src/trptest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/src/trptest.py -------------------------------------------------------------------------------- /zip/textractor.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darwaishx/textractor/HEAD/zip/textractor.zip --------------------------------------------------------------------------------