本文将介绍这一细微差别。
我像往常一样开始硒,然后首先单击带有table斯坦共和国选举结果的所需表格所在的链接,然后崩溃
如您所知,细微差别在于,每次单击链接后,都会显示一个验证码。
通过分析站点的结构,发现链接数达到了约3万个。
我别无选择,只能在互联网上找到识别验证码的方法。找到一个服务
+验证码会像一个人一样被100%
识别-平均识别时间为9秒,这很长,因为我们有大约3万个不同的链接,我们需要关注并识别验证码。
我立即放弃了这个想法。经过几次尝试获取验证码后,我注意到它并没有太大变化,绿色背景上的所有黑色数字均相同。
而且,由于我一直想用手触摸“视觉计算机”,因此我决定有机会亲自尝试每个人最喜欢的MNIST问题。
已经是17:00了,我开始寻找经过预训练的模型以识别数字。在此验证码上检查了它们之后,准确性令我不满意-好的,是时候收集图片并训练您的神经网络了。
首先,您需要收集培训样本。
我打开Chrome网络驱动程序,并在文件夹中显示1000个验证码。
from selenium import webdriver
i = 1000
driver = webdriver.Chrome('/Users/aleksejkudrasov/Downloads/chromedriver')
while i>0:
driver.get('http://www.vybory.izbirkom.ru/region/izbirkom?action=show&vrn=4274007421995®ion=27&prver=0&pronetvd=0')
time.sleep(0.5)
with open(str(i)+'.png', 'wb') as file:
file.write(driver.find_element_by_xpath('//*[@id="captchaImg"]').screenshot_as_png)
i = i - 1
由于我们只有两种颜色,因此我将验证码转换为bw:
from operator import itemgetter, attrgetter
from PIL import Image
import glob
list_img = glob.glob('path/*.png')
for img in list_img:
im = Image.open(img)
im = im.convert("P")
im2 = Image.new("P",im.size,255)
im = im.convert("P")
temp = {}
#
for x in range(im.size[1]):
for y in range(im.size[0]):
pix = im.getpixel((y,x))
temp[pix] = pix
if pix != 0:
im2.putpixel((y,x),0)
im2.save(img)
现在我们需要将验证码切成数字并将其转换为10 * 10的单个大小。
首先,我们将验证码切成数字,然后,由于验证码沿OY轴移动,因此我们需要裁剪所有不必要的内容并将图像旋转90°。
def crop(im2):
inletter = False
foundletter = False
start = 0
end = 0
count = 0
letters = []
name_slise=0
for y in range(im2.size[0]):
for x in range(im2.size[1]):
pix = im2.getpixel((y,x))
if pix != 255:
inletter = True
# OX
if foundletter == False and inletter == True:
foundletter = True
start = y
# OX
if foundletter == True and inletter == False:
foundletter = False
end = y
letters.append((start,end))
inletter = False
for letter in letters:
#
im3 = im2.crop(( letter[0] , 0, letter[1],im2.size[1] ))
# 90°
im3 = im3.transpose(Image.ROTATE_90)
letters1 = []
#
for y in range(im3.size[0]): # slice across
for x in range(im3.size[1]): # slice down
pix = im3.getpixel((y,x))
if pix != 255:
inletter = True
if foundletter == False and inletter == True:
foundletter = True
start = y
if foundletter == True and inletter == False:
foundletter = False
end = y
letters1.append((start,end))
inletter=False
for letter in letters1:
#
im4 = im3.crop(( letter[0] , 0, letter[1],im3.size[1] ))
#
im4 = im4.transpose(Image.ROTATE_270)
resized_img = im4.resize((10, 10), Image.ANTIALIAS)
resized_img.save(path+name_slise+'.png')
name_slise+=1
我想:“已经到了18:00,是时候解决这个问题了。”我想着,把文件夹中的数字和数字一路散开了。
我们声明一个简单的模型,该模型接受我们图片的扩展矩阵作为输入。
为此,请创建100个神经元的输入层,因为图片的大小为10 * 10。作为输出层,有10个神经元,每个神经元对应于0到9的数字。
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, Activation, BatchNormalization, AveragePooling2D
from tensorflow.keras.optimizers import SGD, RMSprop, Adam
def mnist_make_model(image_w: int, image_h: int):
# Neural network model
model = Sequential()
model.add(Dense(image_w*image_h, activation='relu', input_shape=(image_h*image_h)))
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy'])
return model
我们将数据分为训练集和测试集:
list_folder = ['0','1','2','3','4','5','6','7','8','9']
X_Digit = []
y_digit = []
for folder in list_folder:
for name in glob.glob('path'+folder+'/*.png'):
im2 = Image.open(name)
X_Digit.append(np.array(im2))
y_digit.append(folder)
我们将其分为训练和测试集:
from sklearn.model_selection import train_test_split
X_Digit = np.array(X_Digit)
y_digit = np.array(y_digit)
X_train, X_test, y_train, y_test = train_test_split(X_Digit, y_digit, test_size=0.15, random_state=42)
train_data = X_train.reshape(X_train.shape[0], 10*10) # 100
test_data = X_test.reshape(X_test.shape[0], 10*10) # 100
# 10
num_classes = 10
train_labels_cat = keras.utils.to_categorical(y_train, num_classes)
test_labels_cat = keras.utils.to_categorical(y_test, num_classes)
我们训练模型。
凭经验选择时期数和“批量”大小的参数:
model = mnist_make_model(10,10)
model.fit(train_data, train_labels_cat, epochs=20, batch_size=32, verbose=1, validation_data=(test_data, test_labels_cat))
我们保存权重:
model.save_weights("model.h5")
在第11个时代,精度非常好:精度= 1.0000。满意的是,我将于19:00回家休息,明天我仍然需要编写一个解析器来从CEC网站上收集信息。
第二天早上。
问题仍然很小,它仍然需要浏览CEC网站上的所有页面并获取数据:
加载经过训练的模型的权重:
model = mnist_make_model(10,10)
model.load_weights('model.h5')
我们编写一个函数来保存验证码:
def get_captcha(driver):
with open('snt.png', 'wb') as file:
file.write(driver.find_element_by_xpath('//*[@id="captchaImg"]').screenshot_as_png)
im2 = Image.open('path/snt.png')
return im2
让我们编写一个验证码预测功能:
def crop_predict(im):
list_cap = []
im = im.convert("P")
im2 = Image.new("P",im.size,255)
im = im.convert("P")
temp = {}
for x in range(im.size[1]):
for y in range(im.size[0]):
pix = im.getpixel((y,x))
temp[pix] = pix
if pix != 0:
im2.putpixel((y,x),0)
inletter = False
foundletter=False
start = 0
end = 0
count = 0
letters = []
for y in range(im2.size[0]):
for x in range(im2.size[1]):
pix = im2.getpixel((y,x))
if pix != 255:
inletter = True
if foundletter == False and inletter == True:
foundletter = True
start = y
if foundletter == True and inletter == False:
foundletter = False
end = y
letters.append((start,end))
inletter=False
for letter in letters:
im3 = im2.crop(( letter[0] , 0, letter[1],im2.size[1] ))
im3 = im3.transpose(Image.ROTATE_90)
letters1 = []
for y in range(im3.size[0]):
for x in range(im3.size[1]):
pix = im3.getpixel((y,x))
if pix != 255:
inletter = True
if foundletter == False and inletter == True:
foundletter = True
start = y
if foundletter == True and inletter == False:
foundletter = False
end = y
letters1.append((start,end))
inletter=False
for letter in letters1:
im4 = im3.crop(( letter[0] , 0, letter[1],im3.size[1] ))
im4 = im4.transpose(Image.ROTATE_270)
resized_img = im4.resize((10, 10), Image.ANTIALIAS)
img_arr = np.array(resized_img)/255
img_arr = img_arr.reshape((1, 10*10))
list_cap.append(model.predict_classes([img_arr])[0])
return ''.join([str(elem) for elem in list_cap])
添加一个下载表格的功能:
def get_table(driver):
html = driver.page_source #
soup = BeautifulSoup(html, 'html.parser') # " "
table_result = [] #
tbody = soup.find_all('tbody') #
list_tr = tbody[1].find_all('tr') #
ful_name = list_tr[0].text #
for table in list_tr[3].find_all('table'): #
if len(table.find_all('tr'))>5: #
for tr in table.find_all('tr'): #
snt_tr = []#
for td in tr.find_all('td'):
snt_tr.append(td.text.strip())#
table_result.append(snt_tr)#
return (ful_name, pd.DataFrame(table_result, columns = ['index', 'name','count']))
我们收集了9月13日的所有链接:
df_table = []
driver.get('http://www.vybory.izbirkom.ru')
driver.find_element_by_xpath('/html/body/table[2]/tbody/tr[2]/td/center/table/tbody/tr[2]/td/div/table/tbody/tr[3]/td[3]').click()
html = driver.page_source
soup = BeautifulSoup(html, 'html.parser')
list_a = soup.find_all('table')[1].find_all('a')
for a in list_a:
name = a.text
link = a['href']
df_table.append([name,link])
df_table = pd.DataFrame(df_table, columns = ['name','link'])
在13:00之前,我将遍历所有页面完成编写代码:
result_df = []
for index, line in df_table.iterrows():#
driver.get(line['link'])#
time.sleep(0.6)
try:#
captcha = crop(get_captcha(driver))
driver.find_element_by_xpath('//*[@id="captcha"]').send_keys(captcha)
driver.find_element_by_xpath('//*[@id="send"]').click()
time.sleep(0.6)
true_cap(driver)
except NoSuchElementException:#
pass
html = driver.page_source
soup = BeautifulSoup(html, 'html.parser')
if soup.find('select') is None:#
time.sleep(0.6)
html = driver.page_source
soup = BeautifulSoup(html, 'html.parser')
for i in range(len(soup.find_all('tr'))):#
if '\n \n' == soup.find_all('tr')[i].text:# ,
rez_link = soup.find_all('tr')[i+1].find('a')['href']
driver.get(rez_link)
time.sleep(0.6)
try:
captcha = crop(get_captcha(driver))
driver.find_element_by_xpath('//*[@id="captcha"]').send_keys(captcha)
driver.find_element_by_xpath('//*[@id="send"]').click()
time.sleep(0.6)
true_cap(driver)
except NoSuchElementException:
pass
ful_name , table = get_table(driver)#
head_name = line['name']
child_name = ''
result_df.append([line['name'],line['link'],rez_link,head_name,child_name,ful_name,table])
else:# ,
options = soup.find('select').find_all('option')
for option in options:
if option.text == '---':#
continue
else:
link = option['value']
head_name = option.text
driver.get(link)
try:
time.sleep(0.6)
captcha = crop(get_captcha(driver))
driver.find_element_by_xpath('//*[@id="captcha"]').send_keys(captcha)
driver.find_element_by_xpath('//*[@id="send"]').click()
time.sleep(0.6)
true_cap(driver)
except NoSuchElementException:
pass
html2 = driver.page_source
second_soup = BeautifulSoup(html2, 'html.parser')
for i in range(len(second_soup.find_all('tr'))):
if '\n \n' == second_soup.find_all('tr')[i].text:
rez_link = second_soup.find_all('tr')[i+1].find('a')['href']
driver.get(rez_link)
try:
time.sleep(0.6)
captcha = crop(get_captcha(driver))
driver.find_element_by_xpath('//*[@id="captcha"]').send_keys(captcha)
driver.find_element_by_xpath('//*[@id="send"]').click()
time.sleep(0.6)
true_cap(driver)
except NoSuchElementException:
pass
ful_name , table = get_table(driver)
child_name = ''
result_df.append([line['name'],line['link'],rez_link,head_name,child_name,ful_name,table])
if second_soup.find('select') is None:
continue
else:
options_2 = second_soup.find('select').find_all('option')
for option_2 in options_2:
if option_2.text == '---':
continue
else:
link_2 = option_2['value']
child_name = option_2.text
driver.get(link_2)
try:
time.sleep(0.6)
captcha = crop(get_captcha(driver))
driver.find_element_by_xpath('//*[@id="captcha"]').send_keys(captcha)
driver.find_element_by_xpath('//*[@id="send"]').click()
time.sleep(0.6)
true_cap(driver)
except NoSuchElementException:
pass
html3 = driver.page_source
thrid_soup = BeautifulSoup(html3, 'html.parser')
for i in range(len(thrid_soup.find_all('tr'))):
if '\n \n' == thrid_soup.find_all('tr')[i].text:
rez_link = thrid_soup.find_all('tr')[i+1].find('a')['href']
driver.get(rez_link)
try:
time.sleep(0.6)
captcha = crop(get_captcha(driver))
driver.find_element_by_xpath('//*[@id="captcha"]').send_keys(captcha)
driver.find_element_by_xpath('//*[@id="send"]').click()
time.sleep(0.6)
true_cap(driver)
except NoSuchElementException:
pass
ful_name , table = get_table(driver)
result_df.append([line['name'],line['link'],rez_link,head_name,child_name,ful_name,table])
然后是改变我生活的推文