def IdentifyVerifyCode(imgPath,getPublicSetting=True, base64_str = None):
import base64
import os
import Public.SettingReader as SettingReader
encoded_string=""
if base64_str is None :
with open(imgPath, "rb") as image_file:
encoded_string = base64.b64encode(image_file.read())
else:
encoded_string = base64_str
import requests
req=requests.session()
header={
'content-type': 'raw;text/plain;charset=UTF-8;application/json'
}
req.headers.update(header)
data="{'pic':"+str(encoded_string).lstrip('b')+", 'lang':'"+SettingReader.getPublicSetting("Identify","lang")+"'}"
if (getPublicSetting):
IdentifyServer=SettingReader.getPublicSetting("Identify","server")
else:
IdentifyServer=SettingReader.getSetting("Identify","server")
res=req.post(IdentifyServer,data=data)
import json
result=json.loads(res.text)
status=result["status"]
if status != "-1":
VerifyCode=result["result"].replace('\\','').replace('\n','').replace('|','')
imgName=VerifyCode+"_"+result["serialNubmer"]+".png"
os.rename(imgPath,os.path.join(os.getcwd(),"tempFolder",imgName))
return imgName
raise Exception("驗證碼取得失敗")
def __init__(self, secName=None,publicSetting=False):
if secName is None:
secName="connect"
if publicSetting:
self.server = SettingReader.getPublicSetting(secName,"server")
self.database = SettingReader.getPublicSetting(secName,"database")
self.username = SettingReader.getPublicSetting(secName,"username")
self.password = SettingReader.getPublicSetting(secName,"password")
self.driver=SettingReader.getPublicSetting(secName,"driver")
self.dbcon=None
else:
self.server = SettingReader.getSetting(secName,"server")
self.database = SettingReader.getSetting(secName,"database")
self.username = SettingReader.getSetting(secName,"username")
self.password = SettingReader.getSetting(secName,"password")
self.driver=SettingReader.getSetting(secName,"driver")
self.dbcon=None
def getWebDriver(WebDriverType,
incognito=True,
headless=False,
loadPic=True,
DataFolderName=""):
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import os
from Public import SettingReader
#filepath=os.getcwd()
opts = Options()
if incognito:
opts.add_argument("--incognito") # 使用無痕模式
if not headless:
opts.add_argument("--headless") #無介面模式
if DataFolderName == "":
DataFolderName = createID()
DataFolder = os.path.join(getSysTempFolder(), "PyJob", DataFolderName)
opts.add_argument("user-data-dir=" + DataFolder) #變更資料儲存位置
#禁止載入圖片模式
if not loadPic:
prefs = {"profile.managed_default_content_settings.images": 2}
opts.add_experimental_option("prefs", prefs)
opts.add_argument("--disable-gpu") #取消硬體加速 (規避google bug)
opts.add_argument("--disable-extensions") #關閉擴充功能
opts.add_argument("--no-sandbox") #取消沙盒模式
WebDriverType = WebDriverType.lower()
driver = None
if WebDriverType == "chrome":
driverPath = SettingReader.getPublicSetting(
"WebDriver", "chrome"
) + "/chromedriver" #os.path.join(filepath,"Program","chromedriver.exe")
driver = webdriver.Chrome(executable_path=driverPath,
chrome_options=opts)
return driver
jobURL = str(jsondata["jobURL"])
jobAREA = str(jsondata["jobAREA"])
companyInfo = jsondata["companyInfo"]
try:
companyName = PublicFun.SQLFilter(str(companyInfo["companyName"]))
except Exception as ex:
companyInfo = PublicFun.StringToJson(companyInfo, Default=False)
companyName = PublicFun.SQLFilter(str(companyInfo["companyName"]))
ScanDate = str(jsondata["ScanDate"])
DBConnect = SQLConnect.DBConnect(publicSetting=True)
DBConnect.ConnectDB()
CompanyGUID = BIASDataIO.CheckCompanyMappingList(
DBConnect, companyName)
requestHost = SettingReader.getSetting("global", "requestHost")
req = RequestsHandler.getNewRequests(jobURL, requestHost)
res = req.get(jobURL)
res.encoding = 'utf8'
JobSoup = bs(res.text, "html.parser")
objJob = Engine.Query(DBConnect, JOB.JOBAAA(),
"JOBAAA009 = '" + jobURL.strip() + "'")
if (objJob.GUID == ""):
objJob.GUID = PublicFun.createID()
objJob.D_INSERTUSER = "******"
else:
objJob.D_MODIFYUSER = "******"
objJob.JOBAAA001 = CompanyGUID
objJob.JOBAAA002 = "104"
objJob.JOBAAA003 = jobName.strip()
objJob.JOBAAA005 = jobAREA.strip()
return version.strip()
def write_json(file_path, data):
with open(file_path, "w") as f:
json.dump(data, f, indent=2)
def read_json(file_path):
with open(file_path, "r") as f:
data = json.load(f)
return data
CHROME_DRIVER_BASE_URL = "https://chromedriver.storage.googleapis.com"
CHROME_DRIVER_FOLDER = SettingReader.getPublicSetting(
"WebDriver", "chrome") #r"E:\chromeDriver"
CHROME_DRIVER_MAPPING_FILE = r"{}\mapping.json".format(CHROME_DRIVER_FOLDER)
CHROME_DRIVER_EXE = r"{}\chromedriver.exe".format(CHROME_DRIVER_FOLDER)
CHROME_DRIVER_ZIP = r"{}\chromedriver_win32.zip".format(CHROME_DRIVER_FOLDER)
def get_chrome_driver_major_version():
chrome_browser_path = r"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe"
chrome_ver = get_file_version(chrome_browser_path)
chrome_major_ver = chrome_ver.split(".")[0]
return chrome_major_ver
def get_latest_driver_version(browser_ver):
latest_api = "{}/LATEST_RELEASE_{}".format(CHROME_DRIVER_BASE_URL,
browser_ver)
JobID = sys.argv[1]
data = sys.argv[2]
jsondata = PublicFun.StringToJson(data)
DBConnect = SQLConnect.DBConnect(publicSetting=True)
DBConnect.ConnectDB()
sql = ""
if "Update" in jsondata:
sql = (
"select GUID,JOBAAA009 from JOBAAA with(nolock) where JOBAAA029 != 'Y'"
)
elif "Insert" in jsondata:
sql = (
"select GUID,JOBAAA009 from JOBAAA with(nolock) where JOBAAA029 != 'Y'"
)
else:
raise Exception("無動作指令")
CatchListPath = SettingReader.getSetting("excutePath", "CatchList")
rows = DBConnect.GetDataTable(sql)
for row in rows:
tmpQueue = QueueIO.setParameter("CompanyGUID", row.GUID)
tmpQueue = QueueIO.setParameter("JOBAAA009", row.JOBAAA009,
tmpQueue)
QueueIO.addQueue("UpdateJobEndRecruit", "Excute", CatchListPath,
"UpdateJobEndRecruit.py", tmpQueue)
DBConnect.close()
except Exception as ex:
print(ex)
Soup = bs(Chromedriver.page_source, "html.parser")
pageSize=len(Soup.select("select.b-clear-border.js-paging-select.gtm-paging-top option"))
if pageSize==0:
pageSize=len(Soup.select("select.page-select.js-paging-select.gtm-paging-top option"))
PublicFun.closeWebDriver(JobID,Chromedriver)
return pageSize
if __name__ == '__main__':
jsondata=""
try:
JobID=sys.argv[1]
data=sys.argv[2]
jsondata = PublicFun.StringToJson(data)
if "UpdateJobCategory" in jsondata and str(jsondata["UpdateJobCategory"])=="True":
UpdateJobCategoryQueue=QueueIO.setParameter("","")
UpdateJobCategoryPath=SettingReader.getSetting("excutePath","UpdateJobCategory")
QueueIO.addQueue("Update104JobCategory","Excute",UpdateJobCategoryPath,"UpdateJobCategory.py",UpdateJobCategoryQueue)
requestHost=SettingReader.getSetting("global","requestHost")
CatchListPath=SettingReader.getSetting("excutePath","CatchList")
SearchURL=SettingReader.getSetting("global","searchURL")
if "condition" in jsondata:
jsondata=jsondata["condition"]
if "jobcats" in jsondata:
for jobcat in jsondata["jobcats"]:
condition="&jobcat="+jobcat
JobWebSite=SearchURL+condition
pageSize=getPageSize(JobWebSite+"&page=1")
for n in range(pageSize):
CatchListQueue=QueueIO.setParameter("URL",JobWebSite+"&page="+str(n+1))
today = datetime.datetime.now()
ScanDate = today + datetime.timedelta(days=StandardDate)
result = str(ScanDate.year).zfill(4) + "/" + str(
ScanDate.month).zfill(2) + "/" + str(ScanDate.day).zfill(2)
return result
if __name__ == '__main__':
jsondata = ""
try:
JobID = sys.argv[1]
data = sys.argv[2]
jsondata = PublicFun.StringToJson(data)
ListURL = str(jsondata["URL"])
CatchCompanyPath = SettingReader.getSetting("excutePath",
"CatchCompany")
CatchJobPath = SettingReader.getSetting("excutePath", "CatchJob")
DateStandard = int(SettingReader.getSetting("global", "DateStandard"))
requestHost = SettingReader.getSetting("global", "requestHost")
req = RequestsHandler.getNewRequests(ListURL, requestHost)
res = req.get(ListURL)
res.encoding = 'utf8'
Soup = bs(res.text, "html.parser")
JobContent = Soup.find("div", id="js-job-content")
if JobContent is not None:
JobContent = JobContent.select("article.js-job-item ul")
ScanDate = getDataDate(DateStandard)
for tempContent in JobContent:
if tempContent.attrs is not None and len(