def read_captcha():
"""
Use a free api provided by @ocr.space to recognize the captcha.
"""
# Upload the captcha picture to be identified.
result = ocr_space_file('captcha.png')
# Use json.loads to load the result and retrieve the parsed text.
result = loads(result)
parsed_text = result['ParsedResults'][0]['ParsedText']
# Keep the letters and delete all other chars.
parsed_text = parsed_text.strip()
parsed_text = parsed_text.replace(' ', '').replace('\n', '').replace('\r', '')
print('Try to recognize the captcha: ' + parsed_text)
return parsed_text
backup_folder = "backup"
os.makedirs(backup_folder, exist_ok=True)
for folder in dirs:
folder_name = folder
print(folder)
files = os.listdir(path + "/" + folder)
sheet = wb.get_sheet_by_name(sheet_languages[folder])
i = 2
for file in files:
print(file)
file_name = path + "/" + folder + "/" + file
test_file = ocr_space_file(file_name, overlay=True, language=folder)
json_obj = json.loads(test_file)
print(json_obj)
actual_result = ""
actual_result = json_obj["ParsedResults"][0]["ParsedText"].strip(
).replace("\r\n", "")
print('Actual: ' + actual_result)
expected_result = sheet.cell(row=i, column=1).value
sheet['B' + str(i)] = actual_result
print('Expected: ' + expected_result)
if expected_result == actual_result:
sheet.cell(row=i, column=3).value = 'Pass'
from ocr import ocr_space_file
import json
import openpyxl
import os
import shutil
import datetime
path = "input"
dirs = os.listdir(path)
wb = openpyxl.load_workbook('example.xlsx')
sheet = wb.get_sheet_by_name('Sheet1')
i = 2
for file in dirs:
file_name = file
test_file = ocr_space_file(filename=path + "/" + file_name, language='jpn')
json_obj = json.loads(test_file)
print(json_obj)
actual_result = ""
actual_result = json_obj["ParsedResults"][0]["ParsedText"].strip().replace(
"\r\n", "")
print('Actual: ' + actual_result)
expected_result = sheet.cell(row=i, column=1).value
sheet['B' + str(i)] = actual_result
print('Expected: ' + expected_result)
if expected_result == actual_result:
sheet.cell(row=i, column=3).value = 'Pass'
backup_folder = "backup"
os.makedirs(backup_folder, exist_ok=True)
for folder in dirs:
folder_name = folder
print(folder)
files = os.listdir(path + "/" + folder)
sheet = wb.get_sheet_by_name(sheet_languages[folder])
i = 2
for file in files:
print(file)
file_name = path + "/" + folder + "/" + file
test_file = ocr_space_file(file_name, language=folder)
json_obj = json.loads(test_file)
#print(json_obj)
actual_result = ""
actual_result = json_obj["ParsedResults"][0]["ParsedText"].strip(
).replace("\r\n", "")
print('Actual: ' + actual_result)
expected_result = sheet.cell(row=i, column=1).value
sheet['B' + str(i)] = actual_result
#print('Expected: ' + expected_result)
from ocr import ocr_space_file
import json
import openpyxl
import os
import shutil
import datetime
now = datetime.datetime.now()
file_name = '2.jpg'
test_file = ocr_space_file(filename=file_name, language='jpn')
json_obj = json.loads(test_file)
actual_result = ""
for key in json_obj["ParsedResults"][0]["TextOverlay"]["Lines"]:
actual_result += key["Words"][0]["WordText"]
actual_result = json_obj["ParsedResults"][0]["ParsedText"]
print('Actual: ' + actual_result)
wb = openpyxl.load_workbook('example.xlsx')
sheet = wb.get_sheet_by_name('Sheet1')
expected_result = sheet.cell(row=2, column=1).value
sheet['B2'] = actual_result
#print (sheet.cell(row=2, column=2).value)
if expected_result == actual_result:
sheet.cell(row=2, column=3).value = 'Pass'
from ocr import ocr_space_file
import json
test_file = ocr_space_file(filename='example_image.png', language='pol')
json_obj = json.loads(test_file)
#print (json_obj["ParsedResults"][0]["TextOverlay"]["Lines"])
s = ""
for key in json_obj["ParsedResults"][0]["TextOverlay"]["Lines"]:
s += key["Words"][0]["WordText"]
print(s)
#test_url = ocr_space_url(url='http://i.imgur.com/31d5L5y.jpg')