Python pytesseract.image_to_string方法代码示例

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def full_OCR(self):
        bounded = self.img.copy()
        res = np.zeros_like(self.gray_img)

        string = image_to_string(Image.open(self.image_file))
        if string == u'':
            return bounded, res

        boxes = image_to_boxes(Image.open(self.image_file))
        boxes = [map(int, i) for i in [b.split(" ")[1:-1] for b in boxes.split("\n")]]

        for box in boxes:
            b = (int(box[0]), int(self.h - box[1]), int(box[2]), int(self.h - box[3]))
            cv2.rectangle(bounded, (b[0], b[1]), (b[2], b[3]), (0, 255, 0), 2)
            cv2.rectangle(res, (b[0], b[1]), (b[2], b[3]), 255, -1)

        return bounded, res 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def autocaptcha(path):
    """Auto identify captcha in path.

    Use pytesseract to identify captcha.

    Args:
        path: string, image path.

    Returns:
        string, OCR identified code.
    """
    im = Image.open(path)

    im = im.convert('L')
    im = ImageEnhance.Contrast(im)
    im = im.enhance(3)
    img2 = Image.new('RGB', (150, 60), (255, 255, 255))
    img2.paste(im.copy(), (25, 10))

    # TODO: add auto environment detect
    return pytesseract.image_to_string(img2) 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def create_session(self):
        """
        create a session by solving captcha challenge
        """
        self.session['timestamp'] = int(time.time() * 1000)
        url = "http://www.indianrail.gov.in/enquiry/captchaDraw.png?{}".format(self.session['timestamp'])
        r = requests.get(url)
        self.session['cookies'] = r.cookies
        try:
            f = BytesIO(r.content)
        except OSError:
            return None
        im = Image.open(f)
        text = pytesseract.image_to_string(im, lang = 'eng')
        try:
            self.session['captcha'] = eval(text.split("=")[0])
        except:
            self.create_session() 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def handle_tweet(self, tweet_json):
		screen_name = tweet_json["user"]["screen_name"]
		id = tweet_json["id_str"]
		text = tweet_json["text"].replace("\\", "")

		# Get media if present
		try:
			urls = [x["media_url"].replace("\\", "") for x in tweet_json["entities"]["media"] if x["type"] == "photo"]
			for url in urls:
				response = requests.get(url)
				img = Image.open(io.BytesIO(response.content))
				# Extract text from image
				img_text = pytesseract.image_to_string(img)
				text += f' . {img_text}'
		except KeyError:
			pass

		link = f'https://twitter.com/{screen_name}/status/{id}'

		try:
			self.tweet_callback(text, screen_name, link)
		except:
			pass 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def extracttext(imgpath, preprocess):
    if imgpath.startswith('http://') or imgpath.startswith('https://') or imgpath.startswith('ftp://'):
        image = url_to_image(imgpath)
    else:
        image = cv2.imread(imgpath)

    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    if preprocess == "thresh":
        gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
    elif preprocess == "blur":
        gray = cv2.medianBlur(gray, 3)

    filename = "{}.png".format(os.getpid())
    cv2.imwrite(filename, gray)
    text = pytesseract.image_to_string(Image.open(filename))

    os.remove(filename)
    return {"text": text} 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def vcode(self):

        r = self._session.get(
            'https://jy.yongjinbao.com.cn/winner_gj/gjzq/user/extraCode.jsp',
            params={'randomStamp': random.random()}
        )
        r.raise_for_status()

        # 通过内存保存数据
        img_buffer = BytesIO(r.content)
        img = Image.open(img_buffer)
        code = pytesseract.image_to_string(img)
        img.close()
        img_buffer.close()

        if self.code_rule.findall(code) == []:
            raise VerifyCodeError('Wrong verify code: %s' % code)
        else:
            logger.debug('Verify Code is: %s' % code)
            return code 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def get_battle_id(img_path: str):
    img = Image.open(img_path)
    region = img.crop((1286, 15, 1378, 62))
    THRESHOLD = 200
    BINARY_TABLE = [0 if i < THRESHOLD else 1 for i in range(256)]
    text = image_to_string(
        region.convert('L').point(BINARY_TABLE, '1'), config='--psm 7 --oem 3 -c tessedit_char_whitelist=/1234')
    print(text)
    try:
        x = int(text[0])
    except IndexError:
        print("Failed to recognize battle id.")
        return 0
    except ValueError:
        print("Failed to recognize battle id.")
        return 0
    else:
        return x 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def detect_gf_result(image_path):
    from PIL import ImageFilter, Image
    import pytesseract
    img = Image.open(image_path)
    for x in range(img.width):
        for y in range(img.height):
            if img.getpixel((x, y)) < (100, 100, 100):
                img.putpixel((x, y), (256, 256, 256))
    gray = img.convert('L')
    two = gray.point(lambda x: 0 if 68 < x < 90 else 256)
    min_res = two.filter(ImageFilter.MinFilter)
    med_res = min_res.filter(ImageFilter.MedianFilter)
    for _ in range(2):
        med_res = med_res.filter(ImageFilter.MedianFilter)
    res = pytesseract.image_to_string(med_res, config='-psm 6')
    return res.replace(' ', '') 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def deobfuscator(dict_of_dicts):
    #====Work backwards====
    #Build graph from dict_of_dicts:
    graph_from_dict = nx.DiGraph(dict_of_dicts)

    #Get adjacency matrix of graph
    graph_array = nx.to_numpy_array(graph_from_dict)

    #Change 1's to 255's to save as an image
    graph_array[graph_array == 1] = 255
    image_from_array = Image.fromarray(graph_array).convert("L")
    #We can send the array directly to OCR, but I like to see the image.
    image_from_array.save("obfuscated.png")

    #Run OCR on our image
    return pytesseract.image_to_string("obfuscated.png") 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def getImgFromScreenCapture(ques, ans_one, ans_two, ans_thr):
    question = os.system("screencapture -R {} ./question_screenshot.png".format(ques))
    answer_one = os.system("screencapture -R {} ./answers_one.png".format(ans_one))
    answer_two = os.system("screencapture -R {} ./answers_two.png".format(ans_two))
    answer_thr = os.system("screencapture -R {} ./answers_thr.png".format(ans_thr))

    question_img = Image.open("./question_screenshot.png")
    answer_one_img = Image.open("./answers_one.png")
    answer_two_img = Image.open("./answers_two.png")
    answer_thr_img = Image.open("./answers_thr.png")

    question_enh = getImageFromImageEnhanceForQuestion(question_img)
    ans_one_enh  = getImageFromImageEnhance(answer_one_img)
    ans_two_enh  = getImageFromImageEnhance(answer_two_img)
    ans_thr_enh  = getImageFromImageEnhance(answer_thr_img)

    #使用简体中文解析图片
    print('OCR  ' + datetime.datetime.now().strftime('%H:%M:%S'))
    question_text = pytesseract.image_to_string(question_enh, lang='chi_sim')
    question = question_text
    answers = ['','','']
    return question, answers 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def get_name(img):
        #    cv2.imshow("method3", img)
        #    cv2.waitKey()
        print('name')
        _, _, red = cv2.split(img) #split 会自动将UMat转换回Mat
        red = cv2.UMat(red)
        red = hist_equal(red)
        red = cv2.adaptiveThreshold(red, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 151, 50)
        #    red = cv2.medianBlur(red, 3)
        red = img_resize(red, 150)
        img = img_resize(img, 150)
        # showimg(red)
        # cv2.imwrite('name.png', red)
        #    img2 = Image.open('address.png')
        # img = Image.fromarray(cv2.UMat.get(red).astype('uint8'))
        #return get_result_vary_length(red, 'chi_sim', img, '-psm 7')
        return get_result_vary_length(red, 'chi_sim', img, '--psm 7')
        # return punc_filter(pytesseract.image_to_string(img, lang='chi_sim', config='-psm 13').replace(" ","")) 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def captcha_recognize(img_path):
    import pytesseract

    im = Image.open(img_path).convert("L")
    # 1. threshold the image
    threshold = 200
    table = []
    for i in range(256):
        if i < threshold:
            table.append(0)
        else:
            table.append(1)

    out = im.point(table, "1")
    # 2. recognize with tesseract
    num = pytesseract.image_to_string(out)
    return num 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def ocr_get_port(self, data):
        """
        用ocr提取图片中的端口
        :param data: 返回的图片二进制流结果
        :return:
        """

        f = open('port.png', 'wb')
        f.write(data)
        f.close()

        pytesseract.pytesseract.tesseract_cmd = 'C://Program Files//Tesseract-OCR//tesseract.exe'
        port = pytesseract.image_to_string(Image.open('port.png'),
                                           config='--psm 10 --oem 3 -c tessedit_char_whitelist=0123456789')

        # 删除图片
        os.remove('port.png')

        return port 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def ocr_image(orig_image_arr):
  otsu_thresh_image = PIL.Image.fromarray(process_image(orig_image_arr))
  return image_to_string(otsu_thresh_image, lang="letsgodigital", config="-psm 100 -c tessedit_char_whitelist=.0123456789") 

# 需要导入模块: import pytesseract [as 别名]
# 或者: from pytesseract import image_to_string [as 别名]
def image_ocr(image_path):
    """
    识别图像中的英文
    :return:
    """
    # 英文：lang='eng'
    # 中文：lang='chi_sim'
    return pytesseract.image_to_string(Image.open(image_path), lang='eng')