manyi/script/spider/chaoxiang.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

# 超翔的需要利用android手机，打开小程序，然后拿到数据。我直接用的影刀连接android手机（必须调试模式，运行模拟点击的调试模式），然后再通过PC自动化进行操作
    
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 chaoxiang(Document):    
    devNo = StringField(default = '')
    phone = StringField(default = '')

    meta = {
        'collection': 'chaoxiang',
        '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)
        
# 二进制方式打开图片文件
# 获取access token
token = fetch_token()
# 拼接通用文字识别高精度url
#

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')
    return string.replace(' ','')
    
def back_to_search():
    string = get_zone_text(region=(782,183,228,27))
    if  u'启动设备' in string:
        pyautogui.click(x=1265, y=436)
        time.sleep(1)
    elif u'搜索' in string:
        return True
    elif u'通话' in string:
        pyautogui.click(x=1265, y=436)
        time.sleep(1)
        pyautogui.click(x=1265, y=436)
        time.sleep(1)
    elif u'首页' in string:
        pyautogui.click(x=1090, y=241)
        time.sleep(1)
    
    string = get_zone_text(region=(782,183,228,27))
    if u'搜索' in string:
        return True
    else:
        return False
        
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
#         
# string = get_text_from_baidu(None)

for ii in range(0,259889):
    jj = 259889 - ii
    if jj < 100000:
        break
    print jj

    shouji = pyautogui.getWindowsWithTitle(u'手机管理器')[0]
    if not shouji:
        break
    shouji.activate()
    time.sleep(3)
    
    if not back_to_search():
        print u'无法定位到搜索界面'
        break
    
    # 点击搜索框
    pyautogui.doubleClick(x=1066, y=249,interval=0.1)
    time.sleep(1)
     
    # 点击删除按钮，把可能的多余的删除掉
    pyautogui.click(x=1172, y=806,clicks=10,interval=0.1)
     
    time.sleep(0.1)
     
    # 输入设备ID号
    pyautogui.write("%s" % jj)
    time.sleep(0.1)
     
    # 点击搜索
    pyautogui.click(x=1170, y=868)
    time.sleep(1)
     
    # 检查是否有搜索结果
    string = get_zone_text(region=(828,316,332,100))
    print string
    if u'无' in string:
        print u'没有找到此设备',jj
        continue
    
    # 点击设备，多等下，因为广告比较慢
    pyautogui.click(x=1069, y=343)
    time.sleep(5)
    
    # 点击可能打开的广告，没有广告，多点击一次也无所谓
    pyautogui.click(x=1003,y=197)
    time.sleep(0.5)
     
    # 检查是否有联系商户，没有直接返回
    string = get_text_from_baidu(region=(1138,765,61,32))
    if not u'联系' in string:
        print u'没有找到联系方式按钮'
        result = back_to_search()
        if result:
            continue
        else:
            print u'，请人工干预'
            break
    
    # 点击联系方式
    pyautogui.click(x=1167,y=775)
    time.sleep(1)
    
    #解析电话
    string = get_zone_text(region=(813,431,331,46))
    try:
        newObj = chaoxiang(str(jj),string)
        newObj.save()
        print u'搞到一条信息!!!',string
    except Exception,e:
        continue
    
    result = back_to_search()
    if result:
        continue
    else:
        print u'无法返回到搜索页面，请人工干预'
        break
#     time.sleep(0.1)
# 
# 
# while True:
#     a= auto.GetFocusedControl()
#     time.sleep(2)
#     print a
#     print a.Name
#     time.sleep(2)


# while True:
#     pyautogui.moveTo(987,574)
#     file1 = pyautogui.screenshot(region=(766,220,412,575))
#     file1.save(u'Q:/友商信息/汽车桩/星星充电/站列表截图/%s.png' % int(time.time()*1000))
#     ii += 1
#     print ii
#     pyautogui.scroll(-400)
#     time.sleep(0.2)
    
print 'OK'