def construct_jd_raw(item):
jd_raw = JdRaw()
jd_raw.jdId = item.jdId
jd_raw.jdFrom = item.jdFrom
jd_raw.jdUrl = item.jdUrl
jd_raw.pubDate = DtString(item.pubDate, getFlag(item.pubDate))
# 公司信息
jd_inc = JdIncRaw()
jd_inc.incName = DtString(item.incName, getFlag(item.incName))
jd_inc.incType = DtString(item.incType, getFlag(item.incType))
jd_inc.incIntro = DtString(item.incIntro, getFlag(item.incIntro))
jd_inc.incIndustry = DtString(item.incIndustry, getFlag(item.incIndustry))
jd_inc.incScale = DtString(item.incScale, getFlag(item.incScale))
jd_inc.incUrl = DtString() # 量化不需要
# 职位信息
job_info = JdJobRaw()
job_info.jobPosition = DtString(item.jobPosition, getFlag(item.jobPosition))
job_info.jobSalary = DtString(item.jobSalary, getFlag(item.jobSalary))
job_info.jobWorkLoc = DtString(item.jobWorkLoc, getFlag(item.jobWorkLoc))
job_info.jobDiploma = DtString(item.jobDiploma, getFlag(item.jobDiploma))
job_info.jobWorkAge = DtString(item.jobWorkAge, getFlag(item.jobWorkAge))
job_info.jobDescription = DtString() #量化不需要
job_info.jobCate = DtString(item.jobCate, getFlag(item.jobCate))
job_info.jobType = DtString() #量化不需要
job_info.jobWelfare = DtString() #量化不需要
jd_raw.jdJob = job_info
jd_raw.jdInc = jd_inc
remedyInfo = JdRemedyRaw()
remedyInfo.age = DtString()
remedyInfo.cert = [DtString()]
remedyInfo.diploma = DtString()
remedyInfo.endTime = DtString()
remedyInfo.gender = DtString()
remedyInfo.incName = DtString()
remedyInfo.incTags = [DtString()]
remedyInfo.jdId = ""
remedyInfo.jobPosition = DtString()
remedyInfo.jobTags = [DtString()]
remedyInfo.jobWelfare = DtString()
remedyInfo.major = DtString()
remedyInfo.pubTime = DtString()
remedyInfo.salary = DtString()
remedyInfo.skills = [DtString()]
remedyInfo.workDemand = DtString()
remedyInfo.workLoc = DtString()
remedyInfo.workDuty = DtString()
remedyInfo.workExp = DtString()
jd_raw.remedyInfo = remedyInfo
return jd_raw
def parse(content):
# check(content)
doc = html.fromstring(content)
jdRaw = JdRaw(jdFrom="jd_zhilian")
jdRaw.jdUrl = ""
jdRaw.jdInc = jdinc.parse(doc)
jdRaw.jdJob = jdjob.parse(doc)
pub_date = doc.xpath("//ul[@class='terminal-ul clearfix']/li[3]/strong")
if pub_date:
jdRaw.pubDate = DtString(pub_date[0].text_content(), DataFlag(hasValue=True).toByte())
return jdRaw
def parse(content):
doc = html.fromstring(content)
jdRaw = JdRaw(jdFrom="jd_lagou")
jdRaw.jdInc = jdinc.parse(doc)
jdRaw.jdJob = jdjob.parse(doc)
return jdRaw