数据包括切割好的验证文字信息和验证图片块
word_patch_message{
"number":2930,
"shape": (25,175,3),
"Deduplication":true
}
image_patch_message{
"number":23593,
"shape" :(67,67,3),
"Deduplication":true
}
数据下载地址
================================================
Sorry 服务器欠费已停用,现给出爬虫代码及切图代写
================================================
1、爬取验证图片
#coding:u8
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
import requests
import base64
import re
import time
import os
import _thread
def getImage(name):
login_url="https://kyfw.12306.cn/otn/resources/login.html"
driver = webdriver.Chrome()
driver.get(login_url)
count=0
while 1:
count+=1
if not os.path.exists(name):
os.mkdir(name)
driver.find_element_by_class_name("login-hd-account").click()
try:
time.sleep(2)
img_element =WebDriverWait(driver, 100).until(
EC.presence_of_element_located((By.ID, "J-loginImg"))
)
base64_str=img_element.get_attribute("src").split(",")[-1]
imgdata=base64.b64decode(base64_str)
pname=os.path.join("verify",name+str(count)+".jpg")
print(pname)
with open(pname,'wb') as file:
file.write(imgdata)
except Exception as e:
print(u"网络开小差,请稍后尝试")
driver.refresh()
print("start")
try:
_thread.start_new_thread(getImage,("THREAD-1",))
_thread.start_new_thread(getImage,("THREAD-2",))
_thread.start_new_thread(getImage,("THREAD-3",))
_thread.start_new_thread(getImage,("THREAD-4",))
except Exception as e:
print("启动失败")
while 1:
pass
爬虫开了4个线程,将验证图片放入4个文件夹中,请自行归并到一个文件夹下,供切图使用
2、切图
#coding:u8
import cv2
import os
if not os.path.exists("12306_dataset_obj"):
os.mkdir("12306_dataset_obj")
if not os.path.exists("12306_dataset_word"):
os.mkdir("12306_dataset_word")
for batch,file_name in enumerate(os.listdir("verify")):
print(u"处理第{:>9}张图".format(batch+1))
im=cv2.imread("verify/{}".format(file_name),1)
patch=[
im[0:25,120:290],
im[41:108,5:72],
im[41:108,77:144],
im[41:108,149:216],
im[41:108,221:288],
im[113:180,5:72],
im[113:180,77:144],
im[113:180,149:216],
im[113:180,221:288]
]
for i,item in enumerate(patch):
if i is not 0:
cv2.imwrite("12306_dataset_obj/{}.jpg".format(batch*8+i),item)
else:
cv2.imwrite("12306_dataset_word/{}.jpg".format(batch+1),item)