def analy_html(html_text='', url_parse={}):
arr_resume = []
dict_res = {}
soup = BeautifulSoup(html_text, "lxml")
for element in nb.clean_empty_array(soup.get_text('\n').split()):
resume = {}
if len(element) < 10:
continue
if nb.is_short_resume(element) or nb.is_job_history(element):
resume['text'] = element
if element != '':
resume['img_url_previous'] = urlUtils.absoluteUrl(
url_parse, find_img_url(soup, element))
resume['img_url_next'] = urlUtils.absoluteUrl(
url_parse, find_img_url(soup,
element,
previous_direction=False))
else:
continue
arr_resume.append(resume)
# 摘取照片 url
arr_resume = clean_image_url(arr_resume)
dict_res['resume'] = arr_resume
return dict_res
def analy_html(html_text=''):
arr_appoint = []
arr_resume = []
dict_res = {}
soup = BeautifulSoup(html_text, "lxml")
for element in nb.clean_empty_array(soup.get_text('\n').split()):
if len(element) < 10:
continue
if nb.is_job_appoint(element):
arr_appoint.append(element)
continue
dict_res['appoint'] = arr_appoint
return dict_res
def get_resume_project_history(lines=[]):
_lines = []
for line in lines:
res = NbUtils.is_career_project_history(line)
if (res):
_lines.append(line)
return _lines
def get_resume_kvtexts(lines=[]):
_lines = []
for line in lines:
res = NbUtils.is_career_resume_kv(line)
if (res):
_lines.append(line)
return _lines
def analy_html(html_text=''):
arr_reason = []
arr_resume = []
arr_result = []
dict_res = {}
soup = BeautifulSoup(html_text, "lxml")
for element in nb.clean_empty_array(soup.get_text('\n').split()):
if len(element) < 10:
continue
if nb.is_punish_reason(element):
arr_reason.append(element)
continue
if nb.is_punish_result(element):
arr_result.append(element)
continue
if nb.is_short_resume(element) or nb.is_job_history(element):
arr_resume.append(element)
continue
dict_res['reason'] = arr_reason
dict_res['result'] = arr_result
dict_res['resume'] = arr_resume
return dict_res