class Cdata(GQDataHelper):
edulevel = [["005","博士后"],["010","博士"],["020","MBA/EMBA"],["030","硕士"],["040","本科"]]
# edulevel.extend([["050","大专"],["060","中专"],["070","中技"],["080","高中"],["090","初中"]])
sex = GQDataHelper.qlist('男', '女')
userStatus=[[0,"在职，看看新机会"],[1,"离职，正在找工作"],[2,"在职，急寻新工作"],[3,"在职，暂无跳槽打算"]]
agedata = [['0-25'], ['26-30'], ['31-32'], ['33-35'], ['36-40'], ['41-45'], ['46-55'], ['56-999']]
# workyear = GQDataHelper.qlist('0-2', '3-5', '6-8', '9-999')
workyear = GQDataHelper.qlist('5-10', '11-999')
yearSalary = GQDataHelper.qlist('30-80','81-999')
cst_template = {"keys":"","keysRelation":"","company_name":"","company_name_scope":"0","industrys":"","jobtitles"
:"","dqs":"","wantdqs":"","edulevellow":"","edulevelhigh":"","edulevel_tz":"","school_kind"
:"","agelow":"","agehigh":"","workyearslow":"","workyearshigh":"", "yearSalarylow": "", "yearSalaryhigh":"", "sex":"","userStatus":"","search_level"
:"2"}
pd_template = {
"agehigh" : "",
"search_level" : "1",
"jobtitles" : "",
"company_name" : "",
"keys" : "",
"workyearslow" : "",
"search_scope" : "",
"dqs" : "",
"conditionCount" : "",
"company_name_scope" : "0",
"wantdqs" : "",
"edulevellow" : "",
"industrys" : "",
"cs_createtime" : "",
"sex" : "",
"edulevelhigh" : "",
"agelow" : "",
"workyearshigh" : "",
"so_translate_flag" : "1",
"cstContent" : {},
"userStatus" : "",
"cs_id" : "",
"yearSalarylow":"",
"yearSalaryhigh":"",
}
headers = {'DNT':1, 'Referer':'http://lpt.liepin.com/resume/soResumeNew/' }
accounts = [{'u':'hr20065124', 'p':'zhaopin123'}]
# tempfile = spider.racer.TempFileNames()
# lt_accounts = [{'u':'*****@*****.**', 'p':'zhaopin123'}]
# lt_accounts = [{'u':'*****@*****.**', 'p':'zhaopin123'}]
lt_accounts = [{'u':'*****@*****.**', 'p':'zhaopin123'}]
def init_conditions(self):
GQDataHelper.add(self, 'nc', nc)
GQDataHelper.add(self, 'nc2', nc)
GQDataHelper.add(self, 'dqs', dqs)
GQDataHelper.add(self, 'compscale', compscale)
def init_conditions(self):
GQDataHelper.add(self, 'companyType', companyType)
GQDataHelper.add(self, 'degreeType', degreeType)
GQDataHelper.add(self, 'experienceType', experienceType)
GQDataHelper.add(self, 'industry', industry)
GQDataHelper.add(self, 'jobType', jobType)
GQDataHelper.add(self, 'payType', payType)
GQDataHelper.add(self, 'cityKw', cityKw)
self.bs2 = FileSaver("failed_urls.txt")
#!/usr/bin/env python
# -*- coding:utf8 -*-
import os
import sys
import spider
from spider.savebin import FileSaver
from spider.genquery import GenQueries, GQDataHelper
import re
import copy
#来源网站
domain = GQDataHelper.qlist("百城招聘", "英才网联", "厦门人才网", "卓博人才网", "智通人才网", "拉勾网",
"猎聘网", "中国医疗人才网", "36人才", "云南招聘网", "中国人才热线",
"河南九博人才网", "中国汽车人才网", "海峡人才网", "江西人才人事网", "百才招聘",
"中国美容人才热线", "河北搜才网")
#公司性质
companyType = GQDataHelper.qlist("其他性质", "民营企业", "外资", "合资", "国企", "事业单位",
"国家机关")
#xue历要求
degreeType = GQDataHelper.qlist("初中", "高中", "中技", "中专", "大专", "本科", "硕士", "博士",
"不限学历")
#工作经验
experienceType = GQDataHelper.qlist("应届毕业生", "0-2年", "3-5年", "6-7年", "8-10年",
"不限经验")
#行业类型
industry = GQDataHelper.qlist("快速消费品(食品、饮料、化妆品)", "贸易/进出口", "互联网/电子商务",
"电子技术/半导体/集成电路", "专业服务(咨询、人力资源、财会)", "计算机软件",
"新能源", "批发/零售", "服装/纺织/皮革", "汽车及零配件", "金融/投资/证券",
"外包服务", "制药/生物工程", "房地产", "交通/运输/物流", "教育/培训/院校",
"机械/设备/重工", "家具/家电/玩具/礼品", "中介服务", "通信/电信/网络设备")
def init_conditions(self):
#ALL=3277369
GQDataHelper.add(self, 'companyType', companyType) #0 0
GQDataHelper.add(
self, 'degreeType',
degreeType) #13 0.000003966596376544722306215748059
GQDataHelper.add(self, 'jobType',
jobType) #2329 0.0007106309969978967885520367099
GQDataHelper.add(self, 'domain',
domain) #0.01408784246034669669827704161
GQDataHelper.add(
self, 'experienceType',
experienceType) #13031 0.003976055183288790490176724073
GQDataHelper.add(self, 'payType',
payType) #20364 0.006213520662458209618752114882
class Cdata(GQDataHelper):
edulevel = [
["005", "博士后"],
["010", "博士"],
["020", "MBA/EMBA"],
["030", "硕士"],
["040", "本科"],
["050", "大专"],
["060", "中专"],
["070", "中技"],
["080", "高中"],
["090", "初中"],
]
sex = GQDataHelper.qlist('男', '女')
userStatus = [[0, "在职，看看新机会"], [1, "离职，正在找工作"], [2, "在职，急寻新工作"],
[3, "在职，暂无跳槽打算"]]
agedata = [['0-25'], ['26-30'], ['31-35'], ['36-40'], ['41-45'], ['46-55'],
['56-999']]
workyear = GQDataHelper.qlist('0-2', '3-5', '5-8', '9-999')
cst_template = {
"keys": "",
"keysRelation": "",
"company_name": "",
"company_name_scope": "0",
"industrys": "",
"jobtitles": "",
"dqs": "",
"wantdqs": "",
"edulevellow": "",
"edulevelhigh": "",
"edulevel_tz": "",
"school_kind": "",
"agelow": "",
"agehigh": "",
"workyearslow": "",
"workyearshigh": "",
"sex": "",
"userStatus": "",
"search_level": "2"
}
pd_template = {
"agehigh": "",
"search_level": "2",
"jobtitles": "",
"company_name": "",
"keys": "",
"workyearslow": "",
"search_scope": "",
"dqs": "",
"conditionCount": "",
"company_name_scope": "0",
"wantdqs": "",
"edulevellow": "",
"industrys": "",
"cs_createtime": "",
"sex": "",
"edulevelhigh": "",
"agelow": "",
"workyearshigh": "",
"so_translate_flag": "1",
"cstContent": {},
"userStatus": "",
"cs_id": ""
}
headers = {
'DNT': 1,
'Referer': 'http://lpt.liepin.com/resume/soResumeNew/'
}
accounts = [{'u': '深圳市晶伯川科技有限公司', 'p': 'zhaopin123'}]
tempfile = spider.racer.TempFileNames()
try:
lpcvstore = LPCVStore()
except:
print '===== using fake store ======'
lpcvstore = FakeCVStore()
def init_conditions(self):
GQDataHelper.add(self, 'jl', jl)
GQDataHelper.add(self, 'cs', cs)
GQDataHelper.add(self, 'ct', ct)
GQDataHelper.add(self, 'el', el)
#GQDataHelper.add(self, 'we', we) #不能正交切分。....
GQDataHelper.add(self, 'in', in_)
GQDataHelper.add(self, 'salary', salary)
GQDataHelper.add(self, 'bj', bj)
GQDataHelper.add(self, 'et', et)
self.bs2 = FileSaver("failed_urls.txt")