class JDHandler(object):
def __init__(self):
# 初始化四个网站的解析器
self.jd_parser = JdParser()
def analyzeHtml(self,htmlContent=None,jdFrom=None):
"""
jd_html: 输入的html源码,
jd_from:[lagou,51job,zhilian,liepin]中的一个
"""
result = dict()
result_inc = dict()
result_job = dict()
if not jdFrom:
raise ValueError("jdFrom invalid")
try:
result = self.jd_parser.parser(htmlContent,jdFrom=jdFrom,detail=True) # detail=False 为基础解析，True为详尽解析
except Exception as e:
raise NamedError(e.message)
result_inc = result["jdInc"]
result_job = result["jdJob"]
# jdId 和 jdUrl 需要处理时填充
# result["jdId"] = "None"
# result["jdUrl"] = "None"
result["jdInc"] = JdIncRaw(**result_inc)
result["jdJob"] = JdJobRaw(**result_job)
result = JdRaw(**result)
return result
class JDHandler(object):
def __init__(self):
# 初始化四个网站的解析器
self.jd_parser = JdParser()
def analyzeHtml(self, htmlContent=None, jdFrom=None):
"""
jd_html: 输入的html源码,
jd_from:[lagou,51job,zhilian,liepin]中的一个
"""
result = dict()
result_inc = dict()
result_job = dict()
if not jdFrom:
raise ValueError("jdFrom invalid")
try:
result = self.jd_parser.parser(
htmlContent, jdFrom=jdFrom,
detail=True) # detail=False 为基础解析，True为详尽解析
except Exception as e:
raise NamedError(e.message)
result_inc = result["jdInc"]
result_job = result["jdJob"]
# jdId 和 jdUrl 需要处理时填充
# result["jdId"] = "None"
# result["jdUrl"] = "None"
result["jdInc"] = JdIncRaw(**result_inc)
result["jdJob"] = JdJobRaw(**result_job)
result = JdRaw(**result)
return result
