6Fi hddlZddlZddlZddlmZddlmZddlZddl Z ddl Z GddZ dS)N) extract_text)convert_from_pathc eZdZdZdZdZdS) PdfExtractorcBtjt|_dS)N)logging getLogger__name__logger)selfs BD:\xampp\htdocs\new-grp\engine\services\extractor\pdf_extractor.py__init__zPdfExtractor.__init__ s'11 cV tjtj|d}|jd|d} tj |}|D]}|| dz }| | r| |S|jdnA#t$r4}|jdt!|Yd}~nd}~wwxYw t#|}| r| |S|jdnA#t$r4}|jdt!|Yd}~nd}~wwxYw t%|}|D]}|t'j|d z }| |S#t$r4}|jd t!|Yd}~nd}~wwxYw| st+d |S#t$r0}|jd t!|d}~wwxYw)Nutf-8zExtracting text from PDF: textz.No text found with PyMuPDF, trying PDFMiner...zPyMuPDF extraction failed: z*No text found with PDFMiner, trying OCR...zPDFMiner extraction failed: eng)langzOCR extraction failed: z'No text could be extracted from the PDFzPDF extraction failed: )base64 b64decodeurllibparseunquotedecoder infofitzopenget_textclosestrip_detect_encoding Exceptionerrorstrrr pytesseractimage_to_string ValueError) r encoded_pathpdf_pathextracted_textdocpageeimagesimgs r rzPdfExtractor.extract_texts- ' (<(<\(J(JKKRRSZ[[H K  D(DD E E EN Ji))<s ^DKKMM22Fj)H N{{8,,33GH3MMMK    K  DCFFDD E E EKKKKKK s$AAA B(+BBBN)r __module__ __qualname__rrr"rr rr sB222...`     rr) r urllib.parserrpdfminer.high_levelr pdf2imagerr&r5rrr;rr r?s  ,,,,,,''''''>>>>>>>>>>r