manyi/script/spider/wanzhuangXiaochengxun.py

# -*- coding: utf-8 -*-
# !/usr/bin/env python

import os, sys,time,datetime
import urllib
import requests
from mongoengine import register_connection, PointField, DynamicDocument, StringField,Document
import simplejson as json
import simplejson as json
import base64
import sys
import json
import base64
import urllib2
from urllib import quote_plus
from urllib2 import urlopen
from urllib2 import Request
from urllib2 import URLError
from urllib import urlencode

# from django.db.models.fields import DateTimeField
# 
# 
# os.environ.setdefault("DJANGO_SETTINGS_MODULE", "configs.testing")
# 
# from script.base import init_env
# 
# init_env(interactive = False)

import pyautogui
import qrcode

IS_PY3 = sys.version_info.major == 3
if IS_PY3:
    from urllib.request import urlopen
    from urllib.request import Request
    from urllib.error import URLError
    from urllib.parse import urlencode
    from urllib.parse import quote_plus
else:
    import urllib2
    from urllib import quote_plus
    from urllib2 import urlopen
    from urllib2 import Request
    from urllib2 import URLError
    from urllib import urlencode

# 防止https证书校验不正确
import ssl
import pytesseract
from PIL import Image

# while True:
#     a = pyautogui.getWindowsWithTitle(u'图片查看')
#     time.sleep(1)
    
ssl._create_default_https_context = ssl._create_unverified_context

# 利用百度APP，直接解析截图中的地址，以及端口编号。
API_KEY = 'OVcN78LP40CBEwWk5REF2Hyu'
SECRET_KEY = 'a7luZBdbzjsfU9oE2GD3yPeTBgPty03t'
OCR_URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic"
TOKEN_URL = 'https://aip.baidubce.com/oauth/2.0/token'

register_connection(alias = 'spider',
                    name = 'spider',
                    host = '211.159.224.10',
                    port = 27119,
                    username = 'service',
                    password = 'oOzjoQcO5DyyiN97AY0NpzJ6vztjNpx5',
                    authentication_source = 'admin')

class wangzhuang(Document):    
    devNo = StringField(default = '')
    phone = StringField(default = '')

    meta = {
        'collection': 'wangzhuangXiaochengxu',
        'db_alias': 'spider',
        'unique_together': {'devNo'}
    }
    
def fetch_token():
    params = {'grant_type': 'client_credentials',
              'client_id': API_KEY,
              'client_secret': SECRET_KEY}
    post_data = urlencode(params)
    if (IS_PY3):
        post_data = post_data.encode('utf-8')
    req = Request(TOKEN_URL, post_data)
    try:
        f = urlopen(req, timeout=5)
        result_str = f.read()
    except URLError as err:
        print(err)
    
    if (IS_PY3):
        result_str = result_str.decode()
        
    result = json.loads(result_str)

    if ('access_token' in result.keys() and 'scope' in result.keys()):
        if not 'brain_all_scope' in result['scope'].split(' '):
            print ('please ensure has check the  ability')
            exit()
        return result['access_token']
    else:
        print ('please overwrite the correct API_KEY and SECRET_KEY')
        exit()
        
request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic" # accurate_basic

def read_file(image_path):
    f = None
    try:
        f = open(image_path, 'rb')
        return f.read()
    except:
        print('read image file fail')
        return None
    finally:
        if f:
            f.close()
            
def request(url, data):
    req = Request(url, data.encode('utf-8'))
    has_error = False
    try:
        f = urlopen(req)
        result_str = f.read()
        if (IS_PY3):
            result_str = result_str.decode()
        return result_str
    except  URLError as err:
        print(err)

def get_zone_text(region):
    file1 = pyautogui.screenshot(region=region)
    picPath = u'Q:/temp_chaoxiang/' + '%s.jpg' % int(time.time()*1000)
    file1.save(picPath)
    string = pytesseract.image_to_string(Image.open(picPath), lang='chi_sim')
    print picPath,string
    return string.replace(' ','')

def get_text_from_baidu(region):
    try:
        file1 = pyautogui.screenshot(region=region)
        picPath = u'Q:/temp_chaoxiang/' + '%s.jpg' % int(time.time()*1000)
        file1.save(picPath)
        
        f = open(picPath, 'rb')
        img = base64.b64encode(f.read())
        if f:
            f.close()
        # 调用文字识别服务
        params = {"image":img}
        request_url1 = request_url + "?access_token=" + token
        headers = {'content-type': 'application/x-www-form-urlencoded'}
        response = requests.post(request_url1, data=params, headers=headers)
 
        # 解析返回结果
        result_json = response.json()
         
        for words_result in result_json["words_result"]:
            text = words_result["words"]
            return text
        return ''
    except Exception,e:
        print u"解析图片报错了！！！！",e
        
# 二进制方式打开图片文件
# 获取access token
token = fetch_token()
        
def back_to_message():
    stringTitle = get_zone_text(region=(886,180,170,35))
    stringLeft = get_zone_text(region=(782,183,228,27))
    if  u'陈军' in stringTitle:
        return True
    
    elif u'充电支付' in stringLeft:
        pyautogui.click(x=1167, y=198) # 直接点击关闭按钮
        time.sleep(1)
        
    elif u'通话' in stringLeft:
        pyautogui.click(x=1265, y=436)
        time.sleep(1)
        pyautogui.click(x=1265, y=436)
        time.sleep(1)
    
    stringTitle = get_zone_text(region=(886,180,170,35))
    if u'陈军' in stringTitle:
        return True
    else:
        return False

# 从30万启动开始
for ii in range(0,300000):
    jj = 300000 - ii
    print jj
    qrStr = 'https://www.ctiot.info/d/18%06d' % jj
    img =qrcode.make(qrStr)
    filePath = "Q:/temp/%s" % jj
    img.save(filePath)
    time.sleep(0.2)
        
    weixin = pyautogui.getWindowsWithTitle(u'微信')[0]
    if not weixin:
        break
    weixin.activate()
    time.sleep(3)
     
    # 点击文件按钮
    pyautogui.click(x=761, y=777)
    time.sleep(0.2)
        
    # 输入二维码文件名称
    pyautogui.click(x=1083, y=928)
    pyautogui.write("%s" % jj)
    time.sleep(0.2)
        
    # 选择该文件,传到编辑框
    with pyautogui.hold('alt'):
        pyautogui.press('o')
    time.sleep(0.1)
     
    # 发消息
    with pyautogui.hold('alt'):
        pyautogui.press('s')
    time.sleep(0.1)
    
    # --------------------------------- 手机这边识别二维码-------------------------
    shouji = pyautogui.getWindowsWithTitle(u'手机管理器')[0]
    if not shouji:
        break
    shouji.activate()
    time.sleep(3)
    
    if not back_to_message():
        print u'无法定位到消息接受窗口'
        break
    
    # 点击图片
    pyautogui.click(x=1067, y=782)
    time.sleep(1)
    
    # 点击图片的二维码识别按钮
    pyautogui.click(x=1025, y=864)
    time.sleep(3)
    
    string = get_zone_text(region=(782,183,228,27))
    if u'充电支付' not in string:
        print u'没有启动小程序，需要等等吧'
        time.sleep(1800)
        
    string = get_zone_text(region=(847,568,82,30))
    if u'消' in string:
        pyautogui.click(x=847, y=568)
        time.sleep(0.2)
    
#     devNo = get_text_from_baidu(region=(855,278,68,21))
#     if devNo and devNo != '18%06d' % jj:
#         print u'设备编号错误，可能是二维码没有发过来',devNo,jj
#         break
    
    string = get_text_from_baidu(region=(1122,262,72,40))
    if not u'电话' in string :
        continue 
    
    # 点击联系方式
    pyautogui.click(x=1154, y=278)
    time.sleep(1)
    
    #解析电话
    string = get_zone_text(region=(813,431,331,46))
    if not string:
        continue
    try:
        newObj = wangzhuang(str(jj),string)
        newObj.save()
        print u'搞到一条信息!!!',string
    except Exception,e:
        continue
    
print 'OK'