python爬虫--模拟12306登录
Posted corei5
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了python爬虫--模拟12306登录相关的知识,希望对你有一定的参考价值。
模拟12306登录
超级鹰:
#!/usr/bin/env python
# coding:utf-8
import requests
from hashlib import md5
class Chaojiying_Client(object):
def __init__(self, username, password, soft_id):
self.username = username
password = password.encode('utf8')
self.password = md5(password).hexdigest()
self.soft_id = soft_id
self.base_params = {
'user': self.username,
'pass2': self.password,
'softid': self.soft_id,
}
self.headers = {
'Connection': 'Keep-Alive',
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
}
def PostPic(self, im, codetype):
"""
im: 图片字节
codetype: 题目类型 参考 http://www.chaojiying.com/price.html
"""
params = {
'codetype': codetype,
}
params.update(self.base_params)
files = {'userfile': ('ccc.jpg', im)}
r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
return r.json()
def ReportError(self, im_id):
"""
im_id:报错题目的图片ID
"""
params = {
'id': im_id,
}
params.update(self.base_params)
r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
return r.json()
def codecjy():
chaojiying = Chaojiying_Client('tjtj', 'tangjian219', '902590')#用户中心>>软件ID 生成一个替换 96001 用户名 密码 软件id
im = open('./code.png', 'rb').read()#本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
code=chaojiying.PostPic(im,9004)['pic_str']#1902 验证码类型 官方网站>>价格体系 3.4+版 print 后要加()
return code
爬虫程序:
from selenium import webdriver
from selenium.webdriver import ActionChains
from time import sleep
from PIL import Image #安装PIL或者是Pillow
from CJY import Chaojiying_Client
#封装一个识别验证码的函数
def transformCode(imgPath,imgType):
chaojiying = Chaojiying_Client('超级鹰用户名', '超级鹰密码', '899370')
im = open(imgPath, 'rb').read()
return chaojiying.PostPic(im, imgType)['pic_str']
bro = webdriver.Chrome(executable_path='./chromedriver.exe')
bro.get('https://kyfw.12306.cn/otn/login/init')
sleep(2)
#将当前浏览器页面进行图片保存
bro.save_screenshot('./main.png')
#将验证码的局部区域进行裁剪
#捕获标签在页面中的位置信息
img_tag = bro.find_element_by_xpath('//*[@id="loginForm"]/div/ul[2]/li[4]/div/div/div[3]/img')
location = img_tag.location#标签的起始位置坐标(左下角坐标)
size = img_tag.size#标签的尺寸
#裁剪范围对应的矩形区域
rangle = (int(location['x']),int(location['y']),int(location['x']+size['width']),int(location['y']+size['height']))
#使用Image工具进行指定区域的裁剪
i = Image.open('./main.png')
frame = i.crop(rangle)#crop就是根据指定的裁剪范围进行图片的截取
frame.save('code.png')
#调用打码平台进行验证码的识别
result = transformCode('./code.png',9004)
print(result) #x1,y1|x2,y2|x3,y3
#x1,y1|x2,y2|x3,y3 ==>[[x1,y1],[x2,y2],[x3,y3]]
all_list = []#[[x1,y1],[x2,y2],[x3,y3]] 验证码中图片中的点击内容的坐标
if '|' in result:
list_1 = result.split('|')
count_1 = len(list_1)
for i in range(count_1):
xy_list = []
x = int(list_1[i].split(',')[0])
y = int(list_1[i].split(',')[1])
xy_list.append(x)
xy_list.append(y)
all_list.append(xy_list)
else:
x = int(result.split(',')[0])
y = int(result.split(',')[1])
xy_list = []
xy_list.append(x)
xy_list.append(y)
all_list.append(xy_list)
for point in all_list:
x = point[0]
y = point[1]
ActionChains(bro).move_to_element_with_offset(img_tag,x,y).click().perform()
sleep(1)
bro.find_element_by_id('username').send_keys('xxxxxx') #12306用户名
sleep(1)
bro.find_element_by_id('password').send_keys('xxxx') #密码
sleep(1)
bro.find_element_by_id('loginSub').click() #点击事件,登录
sleep(10)
print(bro.page_source)
bro.quit()
以上是关于python爬虫--模拟12306登录的主要内容,如果未能解决你的问题,请参考以下文章