def _get_job_desc(doc):
for pt in job_desc_patterns:
ps = doc.xpath(pt)
r = ""
for p in ps:
r += etree.tounicode(p, pretty_print=True)
r = content_format(r)
removed_special_token_content = re.sub(ur'岗位要求|岗位职责|工作描述|职位描述| ', '', r)
if len(removed_special_token_content) < 10:
continue
return DtString(r, DataFlag(hasValue=True).toByte())
els = doc.xpath(job_desc_pattern_other)
r = ""
for el in els:
r += etree.tounicode(el, pretty_print=True)
r = content_format(r)
return DtString(r, DataFlag(hasValue=True).toByte())
return DtString()
def fetch_content_by_patterns(doc, patterns):
for pat in patterns:
els = doc.xpath(pat)
r = ""
for el in els:
r += el.text_content()
r += '\n'
r = content_format(r)
if len(r) < 10:
continue
return r
return ""
def _get_inc_intro(doc):
for pat in company_patterns:
els = doc.xpath(pat)
r = ""
for el in els:
r += el.text_content()
r += '\n'
r = content_format(r)
if len(r)>10:
return DtString(r, DataFlag(hasValue=True).toByte())
return DtString()
