Python Examples of pytesseract.image_to_string (2023)

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 

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") 

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 

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 

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) 

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() 

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 presenttry: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 imageimg_text = pytesseract.image_to_string(img)text += f' . {img_text}'except KeyError:passlink = f'https://twitter.com/{screen_name}/status/{id}'try:self.tweet_callback(text, screen_name, link)except:pass 

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 

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} 

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 

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(' ', '') 

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(" ","")) 

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 

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") 

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') 

def jpg_to_txt(tesseractLoc, filename): # This is added so that python knows where the location of tesseract-OCR is pytesseract.pytesseract.tesseract_cmd = tesseractLoc # again using the function return value sourceImg = get_path_of_source(filename).with_suffix('.jpg') # Using pillow to open image img = Image.open(sourceImg) filenameOfImg = img.filename text = pytesseract.image_to_string(img) #calling the function which was defined above this function save_to_file_as_txt(filenameOfImg, text) 

def get_turns(): img = Image.open(screenshot_path) img_size = img.size gap = (img_size[0] - 1920) / 2 left = gap + 1280 right = left + 100 bottom = img_size[1] / 20 region = img.crop((left, 0, right, bottom)) text = image_to_string(region, config='--psm 7 -c tessedit_char_whitelist=/1234') print(text) return text 

def ocr(imgfile): print "[+] Running OCR on:", imgfile text = pytesseract.image_to_string(Image.open(imgpath + imgfile)) if debug: print "----------------------------" print "OCR Message:", text print "----------------------------" if text.find("YUKARIDAK") >= 0 or text.find("SANSLI KISI") >= 0 or text.find("SANSLI KiSi") >= 0 or text.find("KATILIM YAPAN") >= 0: # print "[!] Phishing tweet detected!\n"return 1 else:# print imgpath + imgfileos.remove(imgpath + imgfile)return 0 

def get_captcha(self): url = 'http://www.96369.net/Other/ValidateCode.aspx' response = self.do_request(url, method='GET', type='binary') img = Image.open(io.BytesIO(response)) img = img.convert('L') # 二值化 threshold = 160 table = [] for i in range(256): if i < threshold: table.append(0) else: table.append(1) # 由于都是数字 # 对于识别成字母的 采用该表进行修正 rep = {'O': '0', 'I': '1', 'L': '1', 'Z': '2', 'S': '8' } img = img.point(table, '1') img = img.convert('RGBA') rsp = pytesseract.image_to_string(img, config='-psm 6') try: answer = eval(rsp) return answer, self.get_cookies() except: return None, None 

def test02(): from PIL import Image import pytesseract """谷歌图片识别的包：tesseract""" # 使用pil加载一张图片到内存中，返回图片对象 img = Image.open('test.jpg') # 调用tesseract进行识别，返回一个data data = pytesseract.image_to_string(img) # 输出结果 print(data) 

def detect_yh_client_result(image_path): """封装了tesseract的识别，部署在阿里云上，服务端源码地址为： https://github.com/shidenggui/yh_verify_code_docker""" image = Image.open(image_path) code = pytesseract.image_to_string(image, config='-psm 7') return code.replace(' ', '') 

def test_tesseract(self): # Open pdf with Wand with wandimage(filename='/input/tests/data/test.pdf') as wand_image: img_buffer = np.asarray(bytearray(wand_image.make_blob(format='png')), dtype='uint8') bytesio = io.BytesIO(img_buffer) test_string = pytesseract.image_to_string(Image.open(bytesio)) self.assertTrue(type(test_string) == str) 

def image_ocr(self, path): import pytesseract from PIL import Image try: img = Image.open(path) text = pytesseract.image_to_string(img) except: text = '' return text 

def show_ocr_result(frame): start_time = time.time() text = pytesseract.image_to_string(frame, lang="eng", config="--psm 8") print(text) util.display_total_time(start_time) start_time = time.time() pytess_result = pytesseract.image_to_boxes(frame, lang="eng", config="--psm 8", output_type=pytesseract.Output.DICT) print(pytess_result) util.display_total_time(start_time) bbox_list = list() for i, _ in enumerate(pytess_result['bottom']): tl = (pytess_result['left'][i], pytess_result['bottom'][i]) br = (pytess_result['right'][i], pytess_result['top'][i]) bbox_list.append((tl, br)) util.show_frame(frame, bbox_list=bbox_list, wait_flag=True) start_time = time.time() pytess_data = pytesseract.image_to_data(frame, lang="eng", config="--psm 8", output_type=pytesseract.Output.DICT) print(pytess_data) util.display_total_time(start_time) bbox_list = list() for i, conf in enumerate(pytess_data['conf']): if int(conf) != -1: print("\tconf: {}".format(conf)) tl = (pytess_data['left'][i], pytess_data['top'][i]) br = (tl[0]+pytess_data['width'][i], tl[1]+pytess_data['height'][i]) bbox_list.append((tl, br)) util.show_frame(frame, bbox_list=bbox_list, wait_flag=True) 

def standard_test(self): fnum = self.start_fnum time_queue = list() disp_dict = dict() while fnum < self.stop_fnum: start_time = time.time() fnum += self.step_size frame = util.get_frame(self.capture, fnum, gray_flag=True) frame = frame[300:340, 80:220] # 300:340, 200:320 frame = self.param_filter(frame) if self.contour_flag: frame = self.contour_filter(frame) if self.ocr_flag: conf_text = "--psm 7" # Single test line mode. if self.ocr_mode_flag: # Single word mode. conf_text = "--psm 8" text = pytesseract.image_to_string(cv2.bitwise_not(frame), lang="eng", config=conf_text) disp_dict["OCR"] = text util.display_pa_fps(start_time, time_queue, disp_dict) cv2.imshow(self.window_name, frame) if cv2.waitKey(self.step_delay) & 0xFF == ord('q'): break # Apply filters to frame according to GUI parameters. 

def image_to_text(img, only_digits=False): text = pytesseract.image_to_string(img) text = re.sub('[\W]', '', text) text = text.strip() if only_digits: text = text.upper() for r in replace_table: text = text.replace(r, replace_table[r]) return text 

def solve_captcha(self, url, session): """Solve a Bluecoat CAPTCHA for the provided session.""" # Downloads CAPTCHA image and saves to current directory for OCR with tesseract # Returns CAPTCHA string or False if error occurred jpeg = 'captcha.jpg' headers = {'User-Agent': self.useragent} try: response = session.get(url=url, headers=headers, verify=False, stream=True) if response.status_code == 200: with open(jpeg, 'wb') as f: response.raw.decode_content = True shutil.copyfileobj(response.raw, f) else: click.secho('[!] Failed to download the Bluecoat CAPTCHA.', fg='red') return False # Perform basic OCR without additional image enhancement text = pytesseract.image_to_string(Image.open(jpeg)) text = text.replace(" ', '").replace("[', 'l").replace("'', '") # Remove CAPTCHA file try: os.remove(jpeg) except OSError: pass return text except Exception as error: click.secho('[!] Error processing the Bluecoat CAPTCHA.'.format(error), fg='red') return False 

def vcode(self): # 获取校验码 r = self._session.get('https://trade.gf.com.cn/yzm.jpgx') r.raise_for_status() # 通过内存保存图片，进行识别 img_buffer = BytesIO(r.content) img = Image.open(img_buffer) if hasattr(img, "width"): width, height = img.width, img.height else: width, height = img.size for x in range(width): for y in range(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(1): med_res = med_res.filter(ImageFilter.MedianFilter) # 通过tesseract-ocr的工具进行校验码识别 vcode = pytesseract.image_to_string(med_res) img.close() img_buffer.close() vcode = vcode.replace(' ', '') if self.code_rule.findall(vcode) != []: logger.debug('vcode is: %s' % vcode) return vcode else: raise VerifyCodeError('verify code error: %s' % vcode) 

def extract(model_name): print ("extract") if request.method == 'GET': return jsonify(error='Use POST method to send image.'), 400 #total_predictions = request.args.get('total') # Wait for the model to finish loading. image = request.files.get('image') thres = request.values.get("th") img = Image.open(image.stream).convert('RGB') #vis_objects(np.array(image_array), objects).save("c:\\temp\\data.png") s = "" for obj in ouputObjects: if (obj['prob'] > (int(thres)/100)): coordinates = obj['bbox'] print (coordinates) cropped = img.crop( ( coordinates[0], coordinates[1], coordinates[2], coordinates[3] ) ) file = "c:\\temp\\" +str(obj['prob']) +".jpg" cropped.save(file) print (file) print (image_to_string(Image.open(file))) s += image_to_string(Image.open(file)) print (s) return s 

def ocr_question_extract(im): # git@github.com:madmaze/pytesseract.git global pytesseract try: import pytesseract except: print "[ERROR] pytesseract not installed" return im = im.crop((127, 3, 260, 22)) im = pre_ocr_processing(im) # im.show() return pytesseract.image_to_string(im, lang='chi_sim').strip()