Python pyocr.get_available_tools方法代码示例

# 需要导入模块: import pyocr [as 别名]
# 或者: from pyocr import get_available_tools [as 别名]
def __init__(self, ocr_language):
        tools = pyocr.get_available_tools()
        if len(tools) == 0:
            print("No OCR tool found")
            sys.exit(1)
        self.tool = tools[0]
        print("OCR tool: %s" % self.tool)

        try:
            langs = self.tool.get_available_languages()
            self.lang = langs[0]
            if ocr_language in langs:
                self.lang = ocr_language
            print("OCR selected language: %s (available: %s)" % (self.lang.upper(), ", ".join(langs)))
        except Exception as e:
            print("{}".format(e)) 

# 需要导入模块: import pyocr [as 别名]
# 或者: from pyocr import get_available_tools [as 别名]
def __init__(self, path):
        
        ocr_language = 'eng'
        
        path = path

        #if call(['which', 'tesseract']): #Run the command described by args
        #    print("tesseract-ocr missing") #No tesseract installed
        
        tools = pyocr.get_available_tools()
        if len(tools) == 0:
            print("No OCR tool found")
            sys.exit(1)
        self.tool = tools[0]
        print("OCR tool: %s" % self.tool)

        try:
            langs = self.tool.get_available_languages()
            self.lang = langs[0]
            if ocr_language in langs:
                self.lang = ocr_language
            print("OCR selected language: %s (available: %s)" % (self.lang.upper(), ", ".join(langs)))
        except Exception as e:
            print("{}".format(e)) 

# 需要导入模块: import pyocr [as 别名]
# 或者: from pyocr import get_available_tools [as 别名]
def check_required_software():
        logger = logging.getLogger(__name__)
        tools = pyocr.get_available_tools()
        if len(tools) == 0:
            raise PyOCRIntegrationNoOCRFound('No OCR tool has been found on '
                                             'this system. Make sure it\'s on')
        elif len(tools) == 1:
            logger.info("I've found only one ocr tool [%s]. This is not exactly "
                        "an error but you should get better results if you have "
                        "both Tesseract and Cuneiform installed"
                        % tools[0].get_name())
        else:
            logger.info("I've found all required software. We're good to go =)") 

# 需要导入模块: import pyocr [as 别名]
# 或者: from pyocr import get_available_tools [as 别名]
def initialize(self):
		''' Initialize Tesseract and load it up for speed '''
		tools = pyocr.get_available_tools()
		if len(tools) == 0:
			print("No tools found, do you have Tesseract installed?")
			sys.exit(1)
		self.tool = tools[0]
		self.langs = self.tool.get_available_languages() 

# 需要导入模块: import pyocr [as 别名]
# 或者: from pyocr import get_available_tools [as 别名]
def get_default_ocr_lang():
    # Try to guess based on the system locale what would be
    # the best OCR language

    ocr_tools = pyocr.get_available_tools()
    if len(ocr_tools) == 0:
        return DEFAULT_OCR_LANG
    ocr_langs = ocr_tools[0].get_available_languages()

    lang = find_language()
    if hasattr(lang, 'iso639_3_code') and lang.iso639_3_code in ocr_langs:
        return lang.iso639_3_code
    if hasattr(lang, 'terminology') and lang.terminology in ocr_langs:
        return lang.terminology
    return DEFAULT_OCR_LANG 

# 需要导入模块: import pyocr [as 别名]
# 或者: from pyocr import get_available_tools [as 别名]
def image_to_string(self, filename):
        tools = pyocr.get_available_tools()
        if len(tools) == 0:
            raise PyOCRIntegrationNoOCRFound('No OCR tool has been found on '
                                             'this system. Make sure it\'s on'
                                             'PATH variable of your system')

        filename_split, fileextension_split = os.path.splitext(filename)

        grayscale_filename = filename_split + '_gray' + fileextension_split
        with WandImage(filename=filename) as img:
            img.type = 'grayscale'
            img.save(filename=grayscale_filename)

        adaptive_thresh_filename = filename_split + '_adt' + fileextension_split
        ScikitImageIntegration.adaptive_threshold(grayscale_filename, adaptive_thresh_filename)

        processes = []
        for tool in tools:
            if tool.get_name() == "Tesseract":

                thread_t = self._OCRProcessingThread(tool, self.lang, filename)
                thread_t.start()
                processes.append(thread_t)

            else:
                thread_c_raw = self._OCRProcessingThread(tool, self.lang,
                                                         filename)
                thread_c_raw.start()
                processes.append(thread_c_raw)

                thread_c_gs = self._OCRProcessingThread(tool, self.lang,
                                                        grayscale_filename)
                thread_c_gs.start()
                processes.append(thread_c_gs)

                thread_c_prd = self._OCRProcessingThread(tool, self.lang,
                                                         adaptive_thresh_filename)
                thread_c_prd.start()
                processes.append(thread_c_prd)

        # Wait this all threads finish processing
        result = []
        threads_running = True
        while threads_running:
            found_thread_alive = False
            for p in processes:
                if p.is_alive():
                    found_thread_alive = True

            if not found_thread_alive:
                threads_running = False
                for p in processes:
                    result.append(p.return_value)

        # Removing generated files
        self._cleanup(grayscale_filename)
        self._cleanup(adaptive_thresh_filename)

        return result