def _get_inc_intro(doc):
els = doc.xpath("//div[@class='tCompany_text_gsjs']")
for el in els:
r = etree.tounicode(el, pretty_print=True)
r = HtmlFind.remove_tag(r)
return r
return ''
def parse(self):
top_info = self._doc.xpath("//div[@class='cn']")
if not top_info:
raise Exception("find top_info exception")
position = top_info[0].xpath("h1/@title")[0]
self.result.jobPosition = self.replace_pattern('\(.*?\)', '', position)
self.result.jobWorkLoc = top_info[0].xpath("span[@class='lname']")[0].text_content()
self.result.incName = top_info[0].xpath("p[@class='cname']/a/@title")[0]
self.result.incUrl = top_info[0].xpath("p[@class='cname']/a/@href")[0]
self.result.jobSalary = top_info[0].xpath("strong")[0].text_content()
inc_info_part1 = top_info[0].xpath("p[@class='msg ltype']")
if inc_info_part1:
incType, incScale, incIndustry = inc_info_part1[0].text_content().split('|')
self.result.incType = HtmlFind.remove_tag(incType, 1)
self.result.incScale = HtmlFind.remove_tag(incScale, 1)
self.result.incIndustry = HtmlFind.remove_tag(incIndustry, 1)
###########################################################################
###########################################################################
mid_info = self._doc.xpath("//div[@class='jtag inbox']")
if not mid_info:
raise Exception("find mid_info exception")
mid_elems = mid_info[0].xpath("div[@class='t1']/span[@class='sp4']")
mid_field_list = ['jobWorkAge', 'jobPersonNumber']
i = 0
for mid_elem in mid_elems:
if i >=2 :
break
setattr(self.result, mid_field_list[i], mid_elem.text_content())
i += 1
jobWelfare = ''
mid_elems_2 = mid_info[0].xpath("p[@class='t2']/span")
for el in mid_elems_2:
jobWelfare += el.text_content() + ' '
self.result.jobWelfare = jobWelfare
jobDesc = self._doc.xpath("//div[@class='bmsg job_msg inbox']")
if not jobDesc:
raise Exception("get jobdesc exception")
jobDescription = HtmlFind.remove_tag(html.tostring(jobDesc[0], encoding='utf-8'), 1)
index = jobDescription.find('关键字：')
if index != -1:
jobDescription = jobDescription[:index]
self.result.jobDescription = jobDescription
index = jobDescription.find('职能类别：')
if index != -1:
jobCate = jobDescription[index:]
self.result.jobCate = self.replace_pattern('职能类别：', '', jobCate)
inc_intro = self._doc.xpath('//div[@class="tmsg inbox"]')
if inc_intro:
raw_content = html.tostring(inc_intro[0], encoding='utf-8')
raw_content = HtmlFind.remove_tag(raw_content, 1)
self.result.incIntro = raw_content
self.myprint()
def _set_job_others(ret, doc):
els = doc.xpath('//div[@class="tCompany_basic_job"]/dl[@class="lineDl"]')
for dl in els:
dts = dl.xpath("dt")
dds = dl.xpath("dd")
for i in range(0, len(dts)):
key = dts[i].text_content().strip()
value = dds[i].text_content().strip()
if isinstance(key, unicode):
key = key.encode("utf8")
if "发布日期：" == key:
ret.pubDate = value
if "工作地点：" == key:
ret.jobWorkLoc = value
if "招聘人数：" == key:
ret.jobPersonNumber = value
if "工作年限：" == key:
ret.jobWorkAge = value
if "学历要求：" == key:
ret.jobDiploma = value
if "薪资范围：" == key:
ret.jobSalary = value
if "薪酬福利：" == key:
els = dds[i].xpath('span')
job_welfare_list = []
for el in els:
job_welfare_list.append(el.text_content().strip())
ret.jobWelfare = ",".join(job_welfare_list)
if "职能类别：" == key:
job_cate_list = []
els = dds[i].xpath('a')
for el in els:
job_cate_list.append(el.text_content().strip())
ret.jobCate = ",".join(job_cate_list)
if "职位标签：" == key:
job_tags_list = []
els = dds[i].xpath('a')
for el in els:
job_tags_list.append(el.text_content().strip())
ret.jobTags = ",".join(job_tags_list)
# job描述
els = doc.xpath("//div[@class='tCompany_text']/ul")
r = ""
for el in els:
r += etree.tounicode(el, pretty_print=True)
r = HtmlFind.remove_tag(r)
ret.jobDescription = r
# job职位
a = doc.xpath("//li[@class='tCompany_job_name']")
if a:
ret.jobPosition = a[0].text_content().strip()
else:
ret.jobPosition = ''
