def DoResumePayDown(companyid, siteid, syncid, fromsitecode, ownpay, taskid):
try:
if ownpay == 'T':
handler = SiteConfig.GetTaskHandler(companyid, siteid, taskid)
else:
# 获取公用账号企业ID
common_companyid = 0
handler = SiteConfig.GetTaskHandler(common_companyid, siteid,
taskid)
# 账号未验证通过
if handler.bind.check_status == 10:
raise CompanyAccountInvalidError(companyid, siteid, u'账号登录失败')
try:
handler.resume_searcher_down(fromsitecode, syncid, companyid)
# 任务状态回写
task = ResSyncDistribute.queryWithId(syncid)
if HANDLE_STATUS.SUCCESS == handler.status:
task.sync_status = 2010
logger.info(u'<{}>下载付费简历<{}>成功!'.format(
handler.name, fromsitecode, handler.message))
else:
task.sync_status = 10
task.error_message = handler.message
logger.error(u'<{}>下载付费简历<{}>失败,原因:{}'.format(
handler.name, fromsitecode, handler.message))
task.save()
except BaseException as e:
raise UnHandleRuntimeError(e)
except BaseError as e:
task = DBTask.queryWithId(syncid)
task.sync_status = 10
task.fail_num += 1
task.log_info = e.message
task.save()
def get(self):
ret = {'status': 1, 'message': ''}
try:
company_id = str2int(self.get_argument('company_id', ''))
site_id = str2int(self.get_argument('site_id', ''))
if not (company_id and site_id):
raise InvalidParamError(u'提交参数错误!')
try:
handler = SiteConfig.GetTaskHandler(company_id, site_id, None)
try:
# 开始登陆
handler.login()
# 反馈结果
if handler.status == HANDLE_STATUS.SUCCESS:
ret['status'] = 100
# 增加201轮询指令
DBTask.newSchedule(company_id, site_id)
else:
ret['message'] = handler.message
except BaseException as e:
raise UnHandleRuntimeError(e)
logger.error(u'Web服务请求异常,原因:{}'.format(e))
except BaseError as e:
ret['message'] = e.message
finally:
logger.debug(ret)
self.write(json.dumps(ret))
def str2datetime(instr, format='%Y-%m-%d %H:%M:%S'):
if instr:
try:
return datetime.strptime(instr.replace('/', '-'), format)
except BaseException as e:
logger.error(u'时间格式化异常,message:<{}>'.format(e))
return datetime.today()
else:
return datetime.today()
def encryptBindPasswd(salt, original):
enkey = b'{0}-renSHIyi.com'.format(salt)
enkey = enkey[0:8]
try:
iv = Random.new().read(DES.block_size)
generator = DES.new(enkey, DES.MODE_ECB, iv)
s = generator.encrypt(pad_it(original))
return b64encode(generator.encrypt(pad_it(original)))
except BaseException as e:
logger.error(u'数据加密失败,原始串:{},原因:{}'.format(original, e))
return ''
def _getHyperLink(itemname):
response = None
try:
response = http_opener.open(baikurl.format(quote(itemname)))
if response.code == 302:
return response.headers.get('Location')
except BaseException as e:
logger.error(u'<{}>百科超链接查询失败,原因:{}'.format(itemname, str(e)))
finally:
if response:
response.close()
def decryptBindPasswd(salt, ciphering):
enkey = b'{0}-renSHIyi.com'.format(salt)
enkey = enkey[0:8]
try:
passwdcrypt = b64decode(ciphering)
iv = Random.new().read(DES.block_size)
generator = DES.new(enkey, DES.MODE_ECB, iv)
return generator.decrypt(passwdcrypt).rstrip('\x00')
except BaseException as e:
logger.error(u'数据解密失败,加密串:{},原因:{}'.format(ciphering, e))
return ''
def GetRedis(Self, redisName):
pool = Self.__GetPool(redisName)
redisCli = redis.StrictRedis(connection_pool=pool)
try:
if redisCli.ping():
return redisCli
else:
error_msg = u'redis服务器({})ping失败'.format(redisName)
logger.error(error_msg)
raise BaseException(error_msg)
except redis.exceptions.ConnectionError as e:
error_msg = u' redis服务器({})连接失败,原因:{}'.format(redisName, str(e))
raise BaseException(error_msg)
def _doResumeParseByFile(b64content, ext):
try:
soapCli = SudsClient(Conf.YGYS['soapuri'],
timeout=Conf.YGYS['timeout'])
except BaseException as e:
logger.error(u'无法连接简历解析SOAP服务,uri:<{}>,e:<{}>'.format(
Conf.YGYS['soapuri'], e))
return
try:
return soapCli.service.TransResumeByJsonStringForFileBase64(
Conf.YGYS['username'], Conf.YGYS['password'], b64content, ext)
except BaseException as e:
logger.error(u'简历文件解析失败,原因:{}'.format(e))
def post(self):
ret = {'status': 1, 'message': ''}
try:
site_id = str2int(self.get_argument('site_id', ''))
member_name = self.get_argument('member_name', '')
login_name = self.get_argument('login_name', '')
login_pswd = self.get_argument('login_pswd', '')
# 中文解码
member_name = unquote(member_name.encode('gbk'))
login_name = unquote(login_name.encode('gbk'))
#
session = self.get_argument('sessionid', '')
try:
if not session:
raise InvalidParamError(u'非法的请求!')
if not (site_id and login_name and login_pswd):
raise InvalidParamError(u'非法的请求!')
messages = decryptBindPasswd('zpb', session).split(':')
if len(messages) != 2:
raise InvalidParamError(u'非法的请求!')
companyid = messages[0]
handler = SiteConfig.GetTaskHandler(0, site_id, None)
# 登录密码解密
password = decryptBindPasswd(login_name, login_pswd)
if not password:
raise InvalidParamError(u'登录账号或密码错误!')
try:
# 开始登陆
(res,
message) = handler.innerlogin(member_name, login_name,
password)
# 反馈结果
if res:
if Bind.newAndSave(companyid, site_id, member_name,
login_name, login_pswd):
ret['status'] = 0
ret['message'] = u'账号绑定成功!'
else:
ret['status'] = 0
ret['message'] = u'账号已绑定!'
DBTask.newSchedule(companyid, site_id)
else:
ret['message'] = message
except BaseException as e:
raise UnHandleRuntimeError(e)
logger.error(u'Web服务请求异常,原因:{}'.format(e))
except BaseError as e:
ret['message'] = e.message
finally:
logger.debug(ret)
self.write(json.dumps(ret))
def DownResume(checkstatservice, **kwargs):
data = kwargs.copy()
taskid = data['taskid']
companyid = data['companyid']
siteid = data['siteid']
username = data['username']
resumeid = data['resumeid']
postdate = data['postdate']
# 强制刷新简历(用於付费简历下载)
force = data.get('force', False)
#
sitename = SiteConfig.getSiteNameById(siteid)
importkey = Conf.RESUME_IMPORT_HKEY % taskid
try:
try:
# 简历更新度验证(投递日期)
if not force:
if not ResumeBase.isNew(companyid, siteid, resumeid, postdate):
# 未更新的简历将会被忽略
logger.debug(u'<{}>简历<{}, {}>重复下载!'.format(
sitename, username, resumeid))
ResumeRedisCli.hincrby(importkey, 'ignore')
return
try:
handler = SiteConfig.GetTaskHandler(companyid, siteid, taskid)
logger.info(u'正在下载<{}>简历<{}, {}>'.format(
sitename, username, resumeid))
handler.resume_down(data)
if handler.status == HANDLE_STATUS.SUCCESS:
logger.info(handler.message)
dtc. async ('zpb.service.resumeservice.ParseResume',
checkstatservice, **data),
elif handler.status == HANDLE_STATUS.AGAIN:
logger.info(u'<{}>简历<{}, {}>需要重新下载'.format(
sitename, username, resumeid))
data['retry'] = data.get('retry', 0) + 1
dtc. async ('zpb.service.resumeservice.DownResume',
checkstatservice, **data),
else:
ResumeRedisCli.hincrby(importkey, 'failure')
logger.error(handler.message)
except BaseError as e:
pass
except BaseException as e:
dtc. async ('zpb.service.resumeservice.DownResume',
checkstatservice, **data),
logger.error(u'<{}>简历<{}, {}>下载异常,原因:{}'.format(
sitename, username, resumeid, e))
finally:
dtc. async (checkstatservice, taskid)
def Do20(companyid, siteid, syncid, taskid, **kwargs):
task = DBTask.queryWithId(syncid)
try:
handler = SiteConfig.GetTaskHandler(companyid, siteid, taskid)
# 账号已解除绑定
if handler.bind.is_valid != 'T':
DBTask.newSchedule(companyid, siteid, False)
raise CompanyAccountUnBindError(companyid, siteid, u'账号已解除绑定')
# 账号未验证通过
if handler.bind.check_status == 10:
raise CompanyAccountInvalidError(companyid, siteid, u'账号登录失败')
try:
handler.position_import()
if HANDLE_STATUS.SUCCESS == handler.status:
task.sync_status = 2000
task.succ_num += 1
task.log_info = handler.message
# 账号绑定
handler.bind.check_status = 50
handler.bind.login_result = '登录成功'
handler.bind.last_succ_time = datetime.today()
handler.bind.save()
# 下发其它异步任务
infouid = md5(taskid + 'info')
dtc. async ('zpb.service.handleservice.DoInfo',
*(companyid, siteid, infouid),
uid=infouid)
resuid = md5(taskid + '201')
dtc. async ('zpb.service.handleservice.Do201',
*(companyid, siteid, syncid, resuid),
uid=resuid)
logger.info(handler.message)
elif HANDLE_STATUS.AGAIN == handler.status:
task.sync_status = 11
task.fail_num += 1
task.log_info = handler.message
logger.error(handler.message)
else:
task.sync_status = 10
task.fail_num += 1
task.log_info = handler.message
logger.error(handler.message)
except BaseException as e:
raise UnHandleRuntimeError(e)
except BaseError as e:
task.sync_status = 10
task.fail_num += 1
task.log_info = e.message
task.save()
def execute(self, dbname, command):
conn = None
cur = None
res = None
try:
conn = self.getConn(dbname)
cur = conn.cursor()
cur.execute(command)
res = cur._cursor.rowcount
conn.commit()
except Exception, e:
logger.error(u'execute error:%s,cause:%s' % (command, str(e)))
if conn:
conn.rollback()
traceback.print_exc()
def testConn(self, dbname):
conn = None
cur = None
res = False
msg = ""
try:
conn = self.getConn(dbname)
cur = conn.cursor()
cur.execute("select 1")
res = cur.fetchall()
res = True
except Exception, e:
logger.error(u'testConn error:' + str(e))
traceback.print_exc()
msg = e
def guard(self):
logger.info('{} guarding Application at {}'.format(
current_process().name, self.pid))
self.start_event.set()
logger.info('Application-{} running.'.format(self.parent_pid))
cycle = 0.5 # guard loop sleep in seconds
# guard loop. Runs at least once
while not self.stop_event.is_set():
# Check dispatcher
if not self.dispatcher.is_alive():
self.dispatcher = self.spawn_dispatcher()
logger.error(
'reincarnated dispatcher {} after sudden death'.format(
self.dispatcher.name))
sleep(cycle)
self.stop()
def download_email(pop, emailconf, mid, uidl, taskid):
logger.info(u'[*] 正在下载邮箱<{}>第<{}>封邮件'.format(emailconf.email_user, mid))
try:
typ, data, octets = pop.retr(mid)
msg = email.message_from_string('\n'.join(data))
except error_proto as e:
logger.error(u'[*] 邮箱<{}>中的第<{}>封邮件下载失败,原因:{}'.format(
emailconf.email_user, mid, e))
return
# Parse and save email content/attachments
try:
parse_email(emailconf, msg, mid, taskid)
setkey = MAIL_SET_KEY % emailconf.email_user
MailRedisCli.sadd(setkey, uidl)
except BaseException as e:
logger.error(u'[*] 邮箱<{}>中的第<{}>封邮件解析失败,原因:{}'.format(
emailconf.email_user, mid, e))
def call(self, data=None):
try:
if data is not None:
if isinstance(data, dict):
self.add_data(urlencode(data))
elif isinstance(data, basestring):
self.add_data(data)
ret = urllib2.urlopen(self)
response = XResponse(ret, self)
response.status = HTTP_STATUS.SUCCESS
return response
except Exception, e:
msg = 'Http Request call error：{}\n{}\n'.format(self.url, format_exc(e))
logger.error(msg)
response = XResponse(None, self)
response.status = HTTP_STATUS.FAILURE
response.msg = msg
return response
def mutiExecute(self, dbname, commandList):
conn = None
cur = None
res = []
flag = True
sql = ''
try:
conn = self.getConn(dbname)
cur = conn.cursor()
for sql in commandList:
cur.execute(sql)
num = cur._cursor.rowcount
res.append(num)
conn.commit()
except Exception, e:
logger.error(u'execute error:%s,cause:%s' % (sql, str(e)))
if conn:
conn.rollback()
traceback.print_exc()
def dispatcher(event):
def _async_task(tasks):
# 分发异步任务
for task in tasks:
taskname = task.get('name', False)
if taskname:
logger.debug(u'dispatcher task named <{}>'.format(taskname))
args = task.get('args', ())
kwargs = task.get('kwargs', {})
kwargs['uid'] = task['id']
dtc. async (task['func'], *args, **kwargs)
#
name = current_process().name
pid = current_process().pid
logger.info('{} dispatch tasks at {}'.format(name, pid))
while not event.is_set():
try:
# 任务指令中心
task_set = DBTask.queryPending() or []
_async_task(task_set)
# 手动简历解析
task_set = ImpLocalFile.queryPending() or []
_async_task(task_set)
# 付费简历下载
task_set = ResSyncDistribute.queryPending() or []
_async_task(task_set)
# 邮件搜索定时任务
task_set = EmailConf.queryPending() or []
_async_task(task_set)
# 简历搜索定时任务
task_set = ResumeSearcher.queryPending() or []
_async_task(task_set)
# 关键词百科超链接
task_set = HyperLink.queryPending() or []
_async_task(task_set)
#
sleep(2)
except BaseException as e:
logger.error(e)
break
logger.info('{} stopped dispatch tasks'.format(name))
def PackPositionDown(grab, job):
try:
if grab.siteid == 1:
wyjob.pack_position(grab, job)
elif grab.siteid == 2:
rd2.pack_position(grab, job)
elif grab.siteid == 3:
lag.pack_position(grab, job)
elif grab.siteid == 4:
cjol.pack_position(grab, job)
elif grab.siteid == 5:
wuba.pack_position(grab, job)
elif grab.siteid == 6:
ganj.pack_position(grab, job)
elif grab.siteid == 7:
liep.pack_position(grab, job)
return True
except BaseException as e:
logger.error(u'<{}>下载职位<{}>失败,原因:<{}>'.format(SiteConfig.getSiteNameById(grab.siteid), grab.jobid, e))
return True
def pack_position(self, grab, job):
job.company_id = grab.companyid
job.from_site_id = grab.siteid
job.from_site_code = grab.jobid
job.job_name = grab.jobtitle
job.job_mode = 1 if grab.worktype == u'全职' else 2
job.job_status = 10
job.is_valid = 'T' if grab.status == 10 else 'F'
job.start_date = datetime.date(grab.datepublish)
job.publish_date = grab.datepublish
if grab.positiontype2:
job.job_type_level_3 = dict_info('LAG:JobType', grab.positiontype2)
job.job_type_level_2 = int(job.job_type_level_3[0: -2])
job.job_type_level_1 = dict_info('SubJobType', job.job_type_level_2)
elif grab.positiontype:
job.job_type_level_3 = dict_info('LAG:JobType', grab.positiontype)
job.job_type_level_2 = int(job.job_type_level_3[0: -2])
job.job_type_level_1 = dict_info('SubJobType', job.job_type_level_2)
# 模糊匹配城市
citykey = blur_key('Common:City', grab.workarea)
if citykey:
cityjson = dict_info('Common:City', citykey)
cityinfo = json.loads(cityjson)
job.location_city_id = cityinfo['cityid']
job.location_province_id = cityinfo['provinceid']
else:
job.location_province_id = 4241
logger.error(u'拉勾职位工作城市{0}没有模糊匹配结果!'.format(grab.workarea))
job.location_detail = ''
# 薪资范围
avgsalary = int(round(grab.salarymin * 1000.00 + grab.salarymax * 1000.00) / 2)
if avgsalary > 0:
job.salary_id = getSalaryIdBySalaryValue(avgsalary)
job.recruit_num = 0
# -1=学历不限
job.lmt_edu_id = dict_info('LAG:Degree', grab.education, '0')
job.lmt_work = dict_info('LAG:WorkYear', grab.workexperience, '371006')
job.lmt_sex_ids = '391012'
job.receiver_emails = grab.emails.replace(',', ';')
job.work_responsibility = clearHtmlTag(grab.jobdesc.lstrip("'").rstrip("'"))
job.last_sync_time = datetime.today()
def callReConn(self, dbname):
ret = False
if DB_CONFIG.has_key(dbname):
if self.__DbManagerDict.has_key(dbname):
try:
print "%s: now try to reconnect Database(%s)!" % (
datetime.datetime.now(), dbname)
#_dbManager ＝ self.__DbManagerDict[dbname]
_dbManager = TQDbManager(dbname)
self.__DbManagerDict[dbname] = _dbManager
print u"%s reconnect database(%s) success!" % (
datetime.datetime.now(), dbname)
ret = True
except Exception, e:
logger.error(u'callReConn error:' + dbname + ' cause:' +
str(e))
traceback.print_exc()
print u"%s reconnect database(%s) failed!" % (
datetime.datetime.now(), dbname)
finally:
return ret
def Do201(companyid, siteid, syncid, taskid, **kwargs):
task = DBTask.queryWithId(syncid)
try:
handler = SiteConfig.GetTaskHandler(companyid, siteid, taskid)
# 账号已解除绑定
if handler.bind.is_valid != 'T':
DBTask.newSchedule(companyid, siteid, False)
raise CompanyAccountUnBindError(companyid, siteid, u'账号已解除绑定')
# 账号未验证通过
if handler.bind.check_status == 10:
raise CompanyAccountInvalidError(companyid, siteid, u'账号登录失败')
try:
handler.resume_import(syncid)
except BaseException as e:
raise UnHandleRuntimeError(e)
if HANDLE_STATUS.SUCCESS == handler.status:
task.succ_num += 1
task.log_info = handler.message
task.sync_status = 20
#
dtc. async ('zpb.service.handleservice.DoInfo',
*(companyid, siteid, taskid))
logger.info(handler.message)
else:
task.fail_num += 1
task.log_info = handler.message
if HANDLE_STATUS.AGAIN == handler.status:
task.sync_status = 11
else:
task.sync_status = 10
logger.error(handler.message)
except BaseError as e:
task.sync_status = 10
task.fail_num += 1
task.log_info = e.message
task.save()
def pop3(host, port, username, password, usessl):
try:
conn = poplib.POP3_SSL(host) if usessl else poplib.POP3(host)
if debug_mode:
conn.set_debuglevel(2)
conn.user(username)
conn.pass_(password)
logger.info(u'[+] 邮箱<{}> 登录成功'.format(username))
return conn, ''
except error_proto:
error_message = u'登录账号或密码错误'
logger.error(u'[+] 邮箱<{}> 登录失败,原因:'.format(username, error_message))
return None, error_message
except socket.gaierror:
error_message = u'非法POP3服务器名'
logger.error(u'[+] 邮箱<{}> 登录失败,原因:<{}>为{}'.format(
username, host, error_message))
return None, error_message
except BaseException as e:
# 可能网络异常,可以再次执行
logger.error(u'[+] 邮箱<{}> 登录失败,原因:{}'.format(username, str(e)))
return None, None
def post(self):
ret = {'status': 1, 'message': ''}
try:
# 提取post参数中name=file的文件元数据
if self.request.files.has_key('file'):
#
try:
soapCli = SudsClient(Conf.YGYS['soapuri'],
timeout=Conf.YGYS['timeout'])
except BaseException as e:
logger.error(e)
ret['message'] = u'无法连接简历解析WebService服务'
return
#
try:
sitecode = self.get_argument('sitefromcode', '0')
maildate = self.get_argument('maildate', '')
filedata = self.request.files['file'][0]
filename = filedata['filename']
logger.info(u'解析简历文件<{}>'.format(filename))
# 文件扩展名
ext = os.path.splitext(filename)[-1]
if not ext: ext = '.text'
res = soapCli.service.TransResumeByJsonStringForFileBase64(
Conf.YGYS['username'], Conf.YGYS['password'],
base64.b64encode(filedata['body']), ext)
if res:
js = json.loads(res)
if js['Type'] == 0:
ret['message'] = js['Name']
elif not js['Name']:
ret['message'] = u'非完整简历'
else:
js['companyid'] = 0
js['jobid'] = 0
js['source'] = 0
js['apply_job_id'] = 0
js['siteid'] = sitecode
js['apply_time'] = maildate
js['websiteresumeid'] = js['WebSiteResumeID']
js['matching'] = 0
(res, message, new) = AssembelResumeByJson(js)
if res:
data = ResumeBase.queryAndExportByResumeCode(
message)
ret['status'] = 0
ret['count'] = 1
ret['message'] = u'简历文件解析成功!'
ret['res_resume_base'] = data
else:
ret['message'] = message
else:
ret['message'] = u'解析结果空白!'
except BaseException as e:
logger.error(e)
ret['message'] = u'简历解析内部服务错误!'
else:
ret['message'] = u'未上传需要解析的简历文件!'
finally:
if ret['status'] == 1:
logger.error(ret['message'])
self.write(json.dumps(ret))
def AssembelResumeByJson(js):
"""
: params json js
: return (bool, str, bool)->(处理状态,错误原因或简历ID,是否新简历)
"""
# 噪声过滤
if js['Sex'] == '' and js['Age'] == '':
if js['LastUpdate'] == '199001':
return (False, u'非法的简历!', False)
if js['siteid'] == 0:
return (False, u'非法的简历!', False)
#
session = DBInstance.session
try:
# 强制刷新简历(用於付费简历下载)
force = js.get('force', False)
(ret, rm) = ResumeBase.queryAndCreate(session, js['companyid'], js['siteid'], js['websiteresumeid'], js['apply_time'])
if not ret and not force:
return (True, rm.resume_code, False)
# 填充简历
rm.apply_job_status = 0
rm.apply_job_id = 0
# 简历关联的职位ID,用最新的覆盖
if js['jobid']:
rm.from_site_jobcode = js['jobid']
if not rm.from_site_jobcode:
rm.from_site_jobcode = ''
# 来源可能制定本系统关联职位ID(imp_local_file)
if js['apply_job_id']:
rm.apply_job_id = js['apply_job_id']
rm.apply_job_status = 1
else:
# 依据招聘平台职位ID查找本系统职位ID
if rm.from_site_jobcode:
jobid = JobSyncDistribute.queryJobIdByThirdJobCode(rm.company_id, rm.from_site_id, rm.from_site_jobcode)
if jobid:
rm.apply_job_status = 1
rm.apply_job_id = jobid
# 判定简历投递时间
if rm.apply_job_status == 1:
if rm.apply_time <= dateAdd(day=-7):
rm.pre_apply_job_id = rm.apply_job_id
rm.apply_job_id = 0
rm.apply_job_status = 0
#
rm.resume_type = js['Type']
rm.resume_grade = js['ResumeGrade']
rm.married_status = js['Married']
rm.id_no = js['IDNO']
rm.get_encouragement = js['Encouragement'].replace('\r\n', '<br />')
rm.join_team = js['Team'].replace('\r\n', '<br />')
rm.volunteer_info = js['Volunteer']
rm.graduate_year = str2int(js['Graduatetime'][0: 4])
rm.graduate_month = str2int(js['Graduatetime'][5: 7])
rm.begin_work_year = str2int(js['Beginworktime'][0: 4])
rm.begin_work_month = str2int(js['Beginworktime'][5: 7])
rm.last_update = js['LastUpdate']
rm.third_score = js['Score']
rm.certificate_name = js['Certificate'].replace('\r\n', '<br />')
rm.person_memo = js['Personal'].replace('\r\n', '<br />')
rm.lesson_name = js['Lesson']
rm.computer_level = js['Computer']
rm.english_level = js['English']
rm.graduate_school = js['School']
rm.school_rankings = js['SchoolRankings']
rm.addr_postcode = js['PostCode']
rm.speciality_name = js['Speciality']
rm.contact_addr = js['Address']
rm.native_place = js['Jiguan']
rm.national_name = js['National']
rm.nationality_name = js['Nationality']
rm.birth_day = js['Birth']
# 来源于简历搜索器(简历解析服务器返回结果有噪声)
if js['source'] == 9:
if rm.source is None or rm.source == 9:
rm.person_name = ''
rm.family_name = ''
else:
rm.person_name = js['Name']
rm.family_name = js['FamilyName']
#
rm.person_href = js['Href']
rm.hope_title = js['Title']
rm.hope_title2 = js['Title2']
rm.title_standard = js['TitleStandard']
rm.aim_institution = js['AimInstitution']
rm.person_age = str2int(js['Age'])
rm.person_sex = js['Sex']
rm.body_high = js['High']
rm.body_weight = js['Weight']
if js['Mobile']:
rm.mobile_no = js['Mobile']
if rm.mobile_no is None:
rm.mobile_no = ''
if js['Phone']:
rm.other_phone = js['Phone']
if rm.other_phone is None:
rm.other_phone = ''
rm.fax_no = js['Fax']
if js['Email']:
rm.email_addr = js['Email']
if rm.email_addr is None:
rm.email_addr = ''
if rm.email_addr == '*****@*****.**':
rm.email_addr = ''
rm.now_location = js['NowLocation']
rm.hope_location = js['Forwardlocation']
rm.high_education = js['Education']
if rm.high_education == u'大專':
rm.high_education = u'大专'
rm.high_edu_id = getEduHighId(rm.high_education)
rm.advance_degree = js['AdvancedDegree']
rm.exp_name = ''
rm.now_vocation = js['Vocation']
rm.hope_vocation = js['ForwardVocation']
rm.vocation_standard = js['VocationStandard']
rm.now_salary = js['Salary']
rm.hope_salary = js['AimSalary']
rm.political_name = js['Political']
rm.start_from = js['StartFrom']
rm.apply_switch = js['Switch']
rm.qq_no = js['QQ']
rm.student_type = js['StudentType']
rm.photo_url = js['PhotoUrl']
rm.apply_letter = js['AppLetter']
rm.last_company = js['LastCompany']
rm.last_title = js['LastTitle']
rm.overseas_work = js['OverseasWork']
rm.job_hope_frequency = js['JobHoppingFrequency']
rm.integrity_ratio = js['Integrity']
rm.work_type = js['WorkType']
rm.birth_date = getBirthDay(js['Birth'])
rm.work_years = str2int(js['Experience'])
rm.source = js.get('source', 0)
rm.matching_degree = js.get('matching', 0)
rm.is_valid = 'T'
rm.modify_user = '******'
rm.modify_time = datetime.today()
session.add(rm)
# 简历扩展
rext = ResumeExtend()
rext.resume_code = rm.resume_code
rext.org_resume = fmtHtml(js['Original'])
rext.edu_detail_full = js['EducationDetail'].replace('\r\n', '<br />')
rext.exp_detail_full = js['ExperienceDetail'].replace('\r\n', '<br />')
rext.train_detail_full = js['Training'].replace('\r\n', '<br />')
rext.proj_detail_full = js['Project'].replace('\r\n', '<br />')
rext.skill_detail_full = js['Skill'].replace('\r\n', '<br />')
rext.is_valid = 'T'
rext.create_user = '******'
rext.create_time = datetime.today()
session.add(rext)
#
if js['EducationInfo']:
for (idx, item) in enumerate(js['EducationInfo']):
redu = ResumeEdu()
redu.resume_code = rm.resume_code
redu.start_date = item['StartDate']
redu.end_date = item['EndDate']
redu.school_name = item['School']
redu.major_name = item['Speciality']
redu.adv_degree = item['AdvancedDegree']
redu.diplomas_name = item['Education']
redu.depart_name = item['Department']
redu.edu_summary = item['Summary'].replace('\r\n', '<br />')
redu.is_studii = item['IsStudii']
redu.is_valid = 'T'
session.add(redu)
# 异步增加百科超链接
dtc.async('zpb.business.model.hyperlink.AppendSchoolLink', redu.school_name)
#
if js['ExperienceInfo']:
for (idx, item) in enumerate(js['ExperienceInfo']):
rexp = ResumeExp()
rexp.resume_code = rm.resume_code
rexp.start_date = item['StartDate']
rexp.end_date = item['EndDate']
rexp.periods_of_time = item['PeriodsOfTime']
# 最近工作的时间长度写入resume_base表
if idx == 0:
rm.periods_of_time = rexp.periods_of_time
rexp.company_name = item['Company']
rexp.work_location = item['Location']
rexp.vocation_name = item['Vocation']
rexp.company_scale = item['Size']
rexp.company_type = item['Type']
rexp.depart_name = item['Department']
rexp.work_title = item['Title']
rexp.salary_name = item['Salary']
rexp.work_summary = item['Summary'].replace('\r\n', '<br />')
rexp.leader_name = item['Leader']
rexp.underling_num = str2int(item['UnderlingNumber'])
rexp.leaving_reason = item['ReasonOfLeaving']
rexp.is_valid = 'T'
session.add(rexp)
# 异步增加百科超链接
dtc.async('zpb.business.model.hyperlink.AppendCompanyLink', rexp.company_name)
#
if js['TrainingInfo']:
for item in js['TrainingInfo']:
rtra = ResumeTrain()
rtra.resume_code = rm.resume_code
rtra.start_date = item['StartDate']
rtra.end_date = item['EndDate']
rtra.train_institution = item['TrainingInstitution']
rtra.train_location = item['TrainingLocation']
rtra.train_course = item['TrainingCourse'].replace('\r\n', '<br />')
rtra.train_certificate = item['Certificate']
rtra.train_desc = item['DescriptionInDetails'].replace('\r\n', '<br />')
rtra.is_valid = 'T'
session.add(rtra)
#
if js['ProjectInfo']:
for item in js['ProjectInfo']:
rpro = ResumeProject()
rpro.resume_code = rm.resume_code
rpro.start_date = item['StartDate']
rpro.end_date = item['EndDate']
rpro.project_name = item['ProjectName']
rpro.work_title = item['Title']
rpro.proj_desc = item['ProjectDescription'].replace('\r\n', '<br />')
rpro.work_responsibility = item['Responsibilities'].replace('\r\n', '<br />')
rpro.is_valid = 'T'
session.add(rpro)
#
if js['LanguagesSkills']:
for item in js['LanguagesSkills']:
rlan = ResumeLang()
rlan.resume_code = rm.resume_code
rlan.lang_name = item['Languages']
rlan.listen_speak = item['ListeningSpeakingSkills']
rlan.write_read = item['ReadingWritingSkills']
rlan.lang_score = item['Score']
rlan.lang_skill = item['Skills']
rlan.is_valid = 'T'
session.add(rlan)
#
if js['ITSkills']:
for item in js['ITSkills']:
rit = ResumeIT()
rit.resume_code = rm.resume_code
rit.skill_name = item['SkillType']
rit.use_time = item['TimeOfUse']
rit.competency_level = item['CompetencyLevel']
rit.is_valid = 'T'
session.add(rit)
#
if js['GradeOfEnglish']:
item = js['GradeOfEnglish']
if item['NameOfCertificate']:
reng = ResumeEnglish()
reng.resume_code = rm.resume_code
reng.certificate_name = item['NameOfCertificate']
reng.certificate_score = item['Score']
reng.rec_date = item['ReceivingDate']
reng.is_valid = 'T'
session.add(reng)
session.commit()
resume_code = rm.resume_code
return (True, resume_code, True)
except BaseException as e:
session.rollback()
logger.error(u'简历解析失败,原因:{}'.format(e))
return (False, u'简历解析失败!', False)
finally:
session.close()
def __init__(self, company, siteid, message):
super(InvalidParamError, self).__init__(company, siteid, message)
self.code = 20010
logger.error(self)
def ParseResume(checkstatservice, **kwargs):
data = kwargs.copy()
taskid = data['taskid']
companyid = data['companyid']
siteid = data['siteid']
jobid = data['jobid']
source = data.get('source', 0)
username = data['username']
resumeid = data['resumeid']
postdate = data['postdate']
# 强制刷新简历(用於付费简历下载)
force = data.get('force', False)
# 简历与职位匹配度
matching = data.get('matching', 0)
#
sitename = SiteConfig.getSiteNameById(siteid)
importkey = Conf.RESUME_IMPORT_HKEY % taskid
try:
try:
# 开始解析
logger.info(u'正在解析<{}>简历<{}>, <{}>'.format(sitename, username,
resumeid))
filepath = data['filepath']
if os.path.isfile(filepath):
# 用於文件备份
# basename = os.path.basename(filepath)
# dirname = os.path.dirname(filepath)
ext = os.path.splitext(filepath)[-1]
ret = _doResumeParseByFile(
base64.b64encode(open(filepath, 'rb').read()), ext)
if ret:
js = json.loads(ret)
if js['Type'] == 0:
ResumeRedisCli.hincrby(importkey, 'failure')
logger.error(u'<{}>简历<{}, {}>解析失败,原因:{}'.format(
sitename, username, resumeid, js['Name']))
return
if not js['Name']:
ResumeRedisCli.hincrby(importkey, 'failure')
logger.error(
u'<{}>简历<{}, {}>解析失败,原因:文件不是一份完整的简历!'.format(
sitename, username, resumeid))
return
#
js['companyid'] = companyid
js['siteid'] = siteid
if siteid == 4:
if resumeid:
js['websiteresumeid'] = resumeid
elif js['WebSiteResumeID']:
js['websiteresumeid'] = js[
'WebSiteResumeID'].replace('J', '')
else:
js['websiteresumeid'] = ''
else:
js['websiteresumeid'] = resumeid if resumeid else js[
'WebSiteResumeID']
js['jobid'] = jobid
js['source'] = source
js['force'] = force
js['matching'] = matching
js['apply_job_id'] = 0
js['apply_time'] = postdate
(res, message, new) = AssembelResumeByJson(js)
if res:
logger.info(u'<{}>简历<{}, {}>解析成功!'.format(
sitename, username, resumeid))
# 简历存储
imphistoryid = ResumeRedisCli.hget(
importkey, 'imphistoryid')
# 简历刷新,不必新增
if new:
ResumeRedisCli.hincrby(importkey, 'success')
# 保存简历历史详细记录
if ImpHistoryResume.newAndSave(
imphistoryid, companyid, message):
ImpHistory.incSuccessByHistoryId(imphistoryid)
else:
logger.error(u'<{}>简历<{}, {}>历史详情保存异常!'.format(
sitename, username, resumeid))
else:
ResumeRedisCli.hincrby(importkey, 'ignore')
else:
ResumeRedisCli.hincrby(importkey, 'failure')
logger.error(u'<{}>简历<{}, {}>解析失败,原因:{}'.format(
sitename, username, resumeid, message))
else:
ResumeRedisCli.hincrby(importkey, 'failure')
message = u'简历服务器解析简历返回结果异常,<{}><{}, {}>'.format(
sitename, username, resumeid)
logger.error(message)
else:
ResumeRedisCli.hincrby(importkey, 'failure')
message = u'简历解析失败,磁盘文件<{}>不存在'.format(sitename, username,
resumeid)
logger.error(message)
except BaseException as e:
dtc. async ('zpb.service.resumeservice.ParseResume',
checkstatservice, **data),
logger.error(u'简历解析服务异常,message:{}'.format(e))
finally:
dtc. async (checkstatservice, taskid)
#_dbManager ＝ self.__DbManagerDict[dbname]
_dbManager = TQDbManager(dbname)
self.__DbManagerDict[dbname] = _dbManager
print u"%s reconnect database(%s) success!" % (
datetime.datetime.now(), dbname)
ret = True
except Exception, e:
logger.error(u'callReConn error:' + dbname + ' cause:' +
str(e))
traceback.print_exc()
print u"%s reconnect database(%s) failed!" % (
datetime.datetime.now(), dbname)
finally:
return ret
else:
logger.error(u'未约定的数据库连接名称(%s)' % dbname)
return ret
@classmethod
def testConn(self, dbname):
conn = None
cur = None
res = False
msg = ""
try:
conn = self.getConn(dbname)
cur = conn.cursor()
cur.execute("select 1")
res = cur.fetchall()
res = True
except Exception, e:
def ParseLocalResume(companyid, taskid, importid):
row = ImpLocalFile.queryByImportId(importid)
if row:
sitename = SiteConfig.getSiteNameById(row.from_site_id)
logger.info(u'开始解析<{}>的本地简历'.format(sitename))
row.proc_status = 10
imp = ImpHistory.new(row.company_id, row.from_site_id, row.import_id,
row.input_type)
if row.input_type == 1:
imp.src_memo = row.user_file_name
if not imp.save():
return
# 异常信息提示
log_msg = u''
try:
if row.input_type == 1:
log_msg = u'简历文件<{}>解析'.format(row.user_file_name)
# 数据库存储类型为hex编码,此处进行解码
content = base64.b64encode(row.file_content)
ext = os.path.splitext(row.user_file_name)[-1]
ret = _doResumeParseByFile(content, ext)
else:
log_msg = u'简历文本解析'
content = row.input_content
ret = _doResumeParseByString(content)
if ret:
js = json.loads(ret)
if js['Type'] > 0 and js['Name']:
js['companyid'] = row.company_id
js['siteid'] = row.from_site_id
if js['WebSiteResumeID']:
js['websiteresumeid'] = js['WebSiteResumeID']
else:
js['websiteresumeid'] = 'Local{0}'.format(
row.import_id)
js['jobid'] = ''
js['source'] = 0
js['apply_job_id'] = row.apply_job_id
js['apply_time'] = datetime2str(datetime.today())
(res, message, new) = AssembelResumeByJson(js)
if res:
row.resume_code = message
row.proc_status = 20
# 保存简历历史详细记录
if ImpHistoryResume.newAndSave(imp.history_id,
row.company_id,
message):
# 保存简历历史记录
imp.succ_num = 1
imp.proc_status = 1
message = u'{}成功'.format(log_msg)
logger.info(message)
else:
message = u'数据存储失败'
logger.error('{}失败,{}'.format(log_msg, message))
imp.fail_num = 1
imp.proc_status = 2
imp.fail_reason = message
else:
logger.error('{}失败,{}'.format(log_msg, message))
imp.fail_num = 1
imp.proc_status = 2
imp.fail_reason = message
else:
message = u'简历内容为空'
logger.error('{}失败,{}'.format(log_msg, message))
imp.fail_num = 1
imp.proc_status = 2
imp.fail_reason = message
else:
message = u'解析结果为空'
logger.error('{}失败,{}'.format(log_msg, message))
imp.fail_num = 1
imp.proc_status = 2
imp.fail_reason = message
except BaseException as e:
message = u'{}异常,原因:{}'.format(log_msg, e)
logger.error(message)
imp.fail_num = 1
imp.proc_status = 2
imp.fail_reason = u'内部服务错误!'
# 历史结果存储
row.save()
imp.end_time = datetime.today()
imp.save()
def Do101(companyid, siteid, syncid, taskid, **kwargs):
task = DBTask.queryWithId(syncid)
try:
jobid = kwargs.pop('jobid', None)
if not jobid:
raise InvalidParamError(companyid, siteid, u'未指定发布职位编号')
handler = SiteConfig.GetTaskHandler(companyid, siteid, taskid)
# 账号已解除绑定
if handler.bind.is_valid != 'T':
DBTask.newSchedule(companyid, siteid, False)
raise CompanyAccountUnBindError(companyid, siteid, u'账号已解除绑定')
# 账号未验证通过
if handler.bind.check_status == 10:
raise CompanyAccountInvalidError(companyid, siteid, u'账号登录失败')
# step 1
dist = JobSyncDistribute.queryByJobIdAndCompanyIdWithSiteId(
jobid, companyid, siteid)
if not dist:
raise JobNotDistributeError(companyid, siteid, u'未找到职位同步记录')
try:
if not dist.third_job_code:
handler.position_add(jobid)
else:
handler.position_modify(jobid, dist.third_job_code,
dist.last_sync_time)
# step 2
if HANDLE_STATUS.SUCCESS == handler.status:
if hasattr(handler, 'thirdjobcode'):
dist.third_job_code = handler.thirdjobcode
dist.sync_succ_num += 1
dist.sync_status = 20
dist.error_message = ''
dist.last_sync_time = datetime.today()
#
BaseJob.updateSyncTimeByJobId(jobid)
#
dtc. async ('zpb.service.handleservice.DoInfo',
*(companyid, siteid, taskid))
else:
dist.sync_fail_num += 1
dist.sync_status = 10
dist.error_message = handler.message
dist.save()
# step 3
jmm = JobMemo(jobid)
if HANDLE_STATUS.SUCCESS == handler.status:
jmm.memo_content = u'[{}]发布成功'.format(handler.name)
else:
jmm.memo_content = u'[{}]发布失败,{}'.format(
handler.name, handler.message)
jmm.save()
# step 4
if HANDLE_STATUS.SUCCESS == handler.status:
task.succ_num += 1
task.log_info = handler.message
task.sync_status = 20
logger.info(handler.message)
else:
task.fail_num += 1
task.log_info = handler.message
if HANDLE_STATUS.AGAIN == handler.status:
task.sync_status = 11
else:
task.sync_status = 10
logger.error(handler.message)
except BaseException as e:
raise UnHandleRuntimeError(e)
except BaseError as e:
task.sync_status = 10
task.fail_num += 1
task.log_info = e.message
task.save()
