def login():
url='https://www.douban.com/accounts/login'
formdata = {
"source": "None",
"form_email": "15817161961",
"redir":"https://www.douban.com",
"form_password": "******",
"captcha-solution": "brother", # 验证码
"captcha-id": "LaWfXy8orhmAw5XhjVtF2hQs:en", # 验证码图片id
"remember": "on"
}
response = post_http(url, formdata)
res_tr = r'<img id="captcha_image" src="(.*?)" alt="captcha" class="captcha_image"/>'
img_link = re.findall(res_tr, str(response), re.S | re.M)[0]
print img_link
#response = get_file('https://www.douban.com')
#print response
#res_tr = r'<img id="captcha_image" src="(.*?)" alt="captcha" class="captcha_image"'
#img_link = re.findall(res_tr, str(response), re.S | re.M)[0]
#print img_link
save_file("../../../../img", "captcha.jpg", get_file(img_link))
print tesserocr.file_to_text("/home/howell/PycharmProjects/luckwine-spider/img/captcha.jpg")
print Image.open('/home/howell/PycharmProjects/luckwine-spider/img/captcha.jpg')
print pytesseract.image_to_string(Image.open('/home/howell/PycharmProjects/luckwine-spider/img/captcha.jpg'))
def write_json_to_file():
file_path = './images/images_pdf1/'
f = open('out.json', 'w+')
write_array = []
pageID = 1
for i in range(2, 60):
file = file_path + "image (" + str(i) + ").jpg"
text = tess.file_to_text(file,
lang='eng',
psm=tess.PSM.AUTO,
path='tessdata-master/')
array = []
jsn = {}
try:
array = parse_file(text)
except Exception as inst:
pass
finally:
jsn['page_id'] = str(pageID)
pageID += 1
jsn['page_name'] = getPageName(text)
jsn['page_info'] = array
write_array.append(jsn)
f.write(json.dumps(write_array))
f.close()
def generate_text_from_file(self, tessDataPath='tessdata-master/'):
text = tess.file_to_text(self.imagePath,
lang='eng',
psm=tess.PSM.AUTO,
path=tessDataPath)
self.text = text
return text
def test_image_file(self):
"""Test SetImageFile and GetUTF8Text."""
self._api.SetImageFile(self._image_file)
text = self._api.GetUTF8Text()
self.assertIn("quick", text)
text2 = tesserocr.file_to_text(self._image_file)
self.assertEqual(text, text2)
def test_image_file(self):
"""Test SetImageFile and GetUTF8Text."""
self._api.Init()
self._api.SetImageFile(self._image_file)
text = self._api.GetUTF8Text()
self.assertIn('quick', text)
text2 = tesserocr.file_to_text(self._image_file)
self.assertEqual(text, text2)
def ocr_remote_link():
url = "https://raw.githubusercontent.com/Python3WebSpider/CrackImageCode/master/code2.jpg"
resp = requests.get(url)
if codes.ok == resp.status_code:
file_name = 'pic/' + str(md5(resp.content).hexdigest()) + '.jpg'
with open(file_name, 'wb') as f:
f.write(resp.content)
print(tesserocr.file_to_text(file_name))
def same_old_solve():
"""
识别率依旧很低, 不提了...
"""
for i in range(10001):
picture_path = "cap1/im{}.png".format(i)
picture = Image.open(picture_path)
result1 = tesserocr.image_to_text(picture.convert('L'), lang='eng')
result2 = tesserocr.file_to_text(picture_path, psm=tesserocr.PSM.AUTO)
print(result1)
print(result2)
def predict(file_name):
predictions = recognize_keras(file_name)
tesser_res = tesserocr.file_to_text(file_name)
keras_text = []
# coords = []
for idx, prediction in enumerate(predictions):
for word, array in prediction:
keras_text.append(word)
# coords.append(array.tolist())
response = ' '.join(keras_text) + ' ' + ' '.join(tesser_res.split())
os.remove(file_name)
return response
def batch_rec(img_path):
# Recognize all the text that present in the path folder, and store the result in a txt time which
# has the same name with the image
if not os.path.exists(img_path):
return
dirs = os.listdir(img_path)
for img in dirs:
print("predicting " + img)
try:
content = tesserocr.file_to_text(img_path + img)
except Exception:
print("skip", img)
continue
# content = tesserocr.file_to_text(img_path+img)
name, _ = img.split(".")
with open(img_path + name + '_rec.txt', 'w') as file:
file.write(content)
def code_tests_ocr(images, version):
if version is 1:
print("CODE EXAMPLE 1\n")
with PyTessBaseAPI() as api:
for img in images:
api.SetImageFile(img)
print('------------------------------------------------------')
print(img.capitalize())
print()
print(api.GetUTF8Text())
print(api.AllWordConfidences())
print()
elif version is 2:
print("CODE EXAMPLE 2\n")
for img in images:
print('------------------------------------------------------')
print(img.capitalize())
print()
print(tesserocr.file_to_text(img))
print()
else:
print('WRONG CODE VERSION ERROR')
# 测试 tesserocr 是否安装成功
import tesserocr
print(tesserocr.file_to_text('../image/OCRTest.png'))
def checkCaptcha(img):
r = tesserocr.file_to_text('./rawCaptcha/0B7D.png')
print('r=', r)
import tesserocr as tc
from PIL import Image
'''
通过添加字体库支持新的语言和字体
C:\\Users\\admin\\AppData\\Local\\Programs\\Python\\Python37-32\\/tessdata/'
'''
class OcrTools:
def __init__(self):
demo = ''
print(tc.tesseract_version()) # print tesseract-ocr version
print(tc.get_languages()) # prints tessdata path and list of available languages
filename = 'data/news.png'
en_filename = 'data/testp.png'
image = Image.open(filename)
#print(tc.image_to_text(image)) # print ocr text from image
# or
#标准中文图片
print('---------------------标准中文图片---------------------')
print(tc.file_to_text(filename,lang='chi_sim'))
#标准英文图片
print('---------------------标准英文图片---------------------')
print(tc.file_to_text(en_filename))
import tesserocr
from PIL import Image
image = Image.open('./images/code.jpg')
r = tesserocr.image_to_text(image)
print(r)
print(tesserocr.file_to_text('./images/code.jpg'))
print(tesserocr.file_to_text('./images/image.png'))
img = image.convert('L')
# img.show()
threshold = 110
table = []
for i in range(256):
if i< threshold:
table.append(0)
else :
table.append(1)
image = img.point(table, '1')
# image.show()
res = tesserocr.image_to_text(image)
print(res)
import tesserocr
for i in range(1, 6):
str = 'code{}.jpg'.format(i)
#这次使用的是file_to_text()方法
result = tesserocr.file_to_text(str).strip()
print(result)
# from selenium import webdriver
# driver = webdriver.Edge('msedgedriver.exe')
# driver = webdriver.PhantomJS()
# driver.get('https://www.baidu.com')
# print(driver.current_url)
import tesserocr
from PIL import Image
image=Image.open('1.png')
print(tesserocr.image_to_text(image))
print(tesserocr.file_to_text('1.png'))
import os
import time
import pytesseract
from PIL import Image
startTime = time.time()
filePath = input('Enter file path (e.g. \'C:/sampleImages/\'): ')
files = os.listdir(filePath)
for file in files:
if file.endswith('jpg'):
print(file)
fileName = file[:file.rindex('.')]
imageFile = os.path.join(filePath, file)
#first OCR method
text = tesserocr.file_to_text(imageFile)
##second OCR method
#text = pytesseract.image_to_string(Image.open(imageFile))
f=(open(filePath+fileName+'.txt', 'w'))
f.write(text)
print('text file created')
else:
print(file, ' - skipped')
elapsedTime = time.time() - startTime
m, s = divmod(elapsedTime, 60)
h, m = divmod(m, 60)
print('Total script run time: ','%d:%02d:%02d' % (h, m, s))
import tesserocr
from PIL import Image
result = tesserocr.file_to_text('Code.jpg')
print(result)
def ocr_redirect():
# 识别概率不高，容易受到线条、模糊化干扰
print(tesserocr.file_to_text("pic/code.jpg"))
image = Image.open("pic/code2.jpg")
print(tesserocr.image_to_text(image))
def get_text(filepath):
return tesserocr.file_to_text(filepath, lang='sqi')
import tesserocr
from PIL import Image
import pytesseract
if __name__ == '__main__':
image = Image.open('C:/Users/lijiafei/Desktop/verifycode/verfycode.jpg')
# print(tesserocr.image_to_text(image)) # print ocr text from image
# or
print(
tesserocr.file_to_text(
'C:/Users/lijiafei/Desktop/verifycode/verfycode.jpg'))
print(pytesseract.image_to_string(image), 1)
# -*- coding: UTF-8 -*-
import tesserocr
from PIL import Image
image = Image.open("/Users/gaxiong/Downloads/image.png")
print(tesserocr.image_to_text(image))
print(tesserocr.file_to_text("/Users/gaxiong/Downloads/image.png"))
import tesserocr
from PIL import Image
image = Image.open('test.jpeg')
result = tesserocr.image_to_text(image)
print(result)
print(tesserocr.file_to_text('test.jpeg'))
import tesserocr
from PIL import Image
# 获取 tesserocr 版本信息
print(tesserocr.tesseract_version())
print(tesserocr.get_languages())
image = Image.open('CheckCode.jpg')
print(tesserocr.image_to_text(image))
# print ocr text from image
print(tesserocr.file_to_text('CheckCode.jpg'))
cv2.imwrite(filename, img)
return img, filename
'''
'''
plt.figure('licencePlate') #图名
plt.imshow(image_gray,cmap='gray') #cmap即colormap，颜色映射
plt.axis('on') #关闭网格线
plt.show()
'''
#image_gray.save('jin2.jpg')
#box=(70,65,590,190)
#region = image_black_white.crop(box)
#region.show()
#region.save('cutoff.jpg')
#print(tesserocr.image_to_text('cutoff.jpg'))
print(tesserocr.file_to_text('bchuan.test.exp0.jpg'))
class languages:
CHS = 'chi_sim'
CHT = 'chi_tra'
ENG = 'eng'
NA = 'num'
def img_to_str(image_path, lang):
return pytesseract.image_to_string(Image.open(image_path), lang)
def save(text):
fs = open("../OCR/gg_ocr.txt", 'w+', encoding='utf-8') # 遍历后的图片提取文字，保存到txt
print api.AllWordConfidences()
# api is automatically finalized when used in a with-statement (context manager).
# otherwise api.End() should be explicitly called when it's no longer needed.
#Basic Usage
import tesserocr
from PIL import Image
print tesserocr.tesseract_version() # print tesseract-ocr version
print tesserocr.get_languages(
) # prints tessdata path and list of available languages
image = Image.open('sample.jpg')
print tesserocr.image_to_text(image) # print ocr text from image
# or
print tesserocr.file_to_text('sample.jpg')
#Advanced API
from PIL import Image
from tesserocr import PyTessBaseAPI
image = Image.open('/usr/src/tesseract/testing/phototest.tif')
with PyTessBaseAPI() as api:
api.SetImage(image)
boxes = api.GetComponentImages(RIL.TEXTLINE, True)
print 'Found {} textline image components.'.format(len(boxes))
for i, (im, box, _, _) in enumerate(boxes):
# im is a PIL image object
# box is a dict with x, y, w and h keys
api.SetRectangle(box['x'], box['y'], box['w'], box['h'])
ocrResult = api.GetUTF8Text()
# File : test_for_packages.py
# IDE : PyCharm
import tesserocr
from PIL import Image
from selenium import webdriver
from bs4 import BeautifulSoup
# Part 1: test selenium
# prepare the option for the chrome driver
options = webdriver.ChromeOptions()
options.add_argument('headless')
# start chrome browser
browser = webdriver.Chrome(chrome_options=options)
browser.get('https://www.baidu.com')
print(browser.current_url)
browser.quit()
# Part 2: test beautifulsoup4
soup = BeautifulSoup('<p>Hello<p>', 'lxml')
print(soup.p.string)
# Part 3: test tesserocr
# method one: use image_to_text
image = Image.open('chapter_1/python3webspider.png')
print(tesserocr.image_to_text(image))
# method two: use file_to_text
print(tesserocr.file_to_text('chapter_1/python3webspider.png'))
from selenium import webdriver
import tesserocr
from PIL import Image
if __name__ == "__main__":
#api = tesserocr.PyTessBaseAPI(path=r'C:\Program Files (x86)\Tesseract-OCR\tessdata')
#browser = webdriver.Chrome()
#browser = webdriver.Firefox()
#browser = webdriver.PhantomJS(executable_path=r'E:\phantomjs\bin\phantomjs.exe')
#browser.get('https:www.baidu.com')
#print(browser.current_url)
image = Image.open('image.png')
print(tesserocr.image_to_text(image))
print(tesserocr.file_to_text('image.png'))
import tesserocr
from PIL import Image
image = Image.open('image.png')
print(tesserocr.file_to_text(image))
#coding:utf-8
'''
图片验证码
'''
import tesserocr
from PIL import Image
image = Image.open('D:\\exercise\\code.jpg') #先打开图片
result = tesserocr.image_to_text(image) #imge_to_text()将图片转化为文字
print(result)
print(tesserocr.file_to_text('D:\\exercise\\code.jpg')) #file_to_text也行，但不稳定
image2 = Image.open('D:\\exercise\\code2.jpg')
result = tesserocr.image_to_text(image2)
print(result)
image2 = image2.convert('L') # 使用convert()方法传入L，将图片灰度处理
image2 = image2.convert('1') # 使用convert()方法传入1，将图片二值处理
image2.show()
image = image.convert('L')
threshold = 127 # 二值化的阈值
table = []
# 这个没懂，怀疑是添加rgb的的参数？
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
print('table>>>>>', table)
import tesserocr
from PIL import Image
image = Image.open('code.jpg')
result = tesserocr.image_to_text(image)
print(result)
# tesserocr另一个简单的方法，将图片文件转为字符串
print(tesserocr.file_to_text('code.jpg'))
import tesserocr
from PIL import Image
image = Image.open('images/template.png')
print(tesserocr.image_to_text(image, lang='chi_sim'))
print(tesserocr.file_to_text('images/test.jpg'))
#灰度与二值化处理
image = Image.open('images/CheckCode.jpg')
image = image.convert('L')
threshold = 127 #阈值
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
image = image.point(table, '1')
image.show()
print(tesserocr.image_to_text(image))
import tesserocr
print(tesserocr.file_to_text('code.jpg'))
