def handler(tag):
tds = tag.find_all(name='td')
if not tds:
print("len(tds) == 0")
return None
employee = Employee()
if len(tds) < 4:
print("len(tds) = %d" % (len(tds)))
return None
name_tag = tds[0]
employee.name = name_tag.get_text()
employee.name = employee.name.strip()
if employee.name == u'姓名':
return None
ass = name_tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
employee.title = tds[2].get_text().strip()
employee.departments = tds[3].get_text().strip()
return employee
def handler(tag):
tds = tag.find_all(name='td')
if not tds:
print("len(tds) == 0")
return None
employee = Employee()
if len(tds) < 5:
print("len(tds) = %d"%(len(tds)))
return None
name_tag = None
name_tag_idx = 0
if len(tds) == 5:
name_tag_idx = 0
name_tag = tds[name_tag_idx]
elif len(tds) > 5:
name_tag_idx = 1
name_tag = tds[name_tag_idx]
employee.name = name_tag.get_text()
employee.name = employee.name.strip()
if employee.name == u'姓名':
return None
ass = name_tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
employee.title = tds[name_tag_idx+1].get_text().strip()
employee.email = tds[name_tag_idx+2].get_text().strip()
employee.tel = tds[name_tag_idx+3].get_text().strip()
return employee
def handler(tag):
tds = tag.find_all("td")
if not tds or len(tds) != 4:
return None
employee = Employee()
ass = tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
employee.name = tds[0].get_text().strip()
employee.name = ''.join(employee.name.split())
title = tds[1].get_text()
if title and len(title) != 0:
employee.title = ''.join(title.split())
email = tds[3].get_text()
if email and len(email) != 0:
employee.email = ''.join(email.split())
tel = tds[2].get_text()
if tel and len(tel) != 0:
employee.tel = ''.join(tel.split())
return employee
def handler(tag):
tds = tag.find_all(name='td')
if not tds:
print("len(tds) == 0")
return None
employee = Employee()
if len(tds) < 4:
print("len(tds) = %d"%(len(tds)))
return None
name_tag = tds[0]
employee.name = name_tag.get_text()
employee.name = employee.name.strip()
if employee.name == u'姓名':
return None
ass = name_tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
employee.title = tds[2].get_text().strip()
employee.departments = tds[3].get_text().strip()
return employee
def handler(tag):
tds = tag.find_all(name='td')
if not tds:
print("len(tds) == 0")
return None
employee = Employee()
if len(tds) < 5:
print("len(tds) = %d" % (len(tds)))
return None
name_tag = None
name_tag_idx = 0
if len(tds) == 5:
name_tag_idx = 0
name_tag = tds[name_tag_idx]
elif len(tds) > 5:
name_tag_idx = 1
name_tag = tds[name_tag_idx]
employee.name = name_tag.get_text()
employee.name = employee.name.strip()
if employee.name == u'姓名':
return None
ass = name_tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
employee.title = tds[name_tag_idx + 1].get_text().strip()
employee.email = tds[name_tag_idx + 2].get_text().strip()
employee.tel = tds[name_tag_idx + 3].get_text().strip()
return employee
def handler(tag):
employee = Employee()
name_divs = tag.find_all("div",class_="teacher-title")
if name_divs and len(name_divs) != 0:
employee.name = name_divs[0].get_text()
employee.name = ''.join(employee.name.split())
# 使用纯文本方式处理
lines = tag.stripped_strings
# text=div.get_text(strip=True)
parser = ProfileParser(lines=lines,employee=employee)
return parser.parse()
def handler(tag):
employee = Employee()
name_divs = tag.find_all("div", class_="teacher-title")
if name_divs and len(name_divs) != 0:
employee.name = name_divs[0].get_text()
employee.name = ''.join(employee.name.split())
# 使用纯文本方式处理
lines = tag.stripped_strings
# text=div.get_text(strip=True)
parser = ProfileParser(lines=lines, employee=employee)
return parser.parse()
def handler(tag):
employee = Employee()
ass = tag.find_all('a',class_="orangea")
if ass and len(ass) != 0:
employee.name = ass[0].get_text()
employee.name = ''.join(employee.name.split())
employee.profile = ass[0]['href']
ass = tag.find_all('a',class_="black01")
if ass and len(ass) != 0:
lines = ass[0].stripped_strings
parser = ProfileParser(lines=lines,employee=employee)
employee = parser.parse()
return employee
def handler(tag):
employee = Employee()
ass = tag.find_all('a', class_="orangea")
if ass and len(ass) != 0:
employee.name = ass[0].get_text()
employee.name = ''.join(employee.name.split())
employee.profile = ass[0]['href']
ass = tag.find_all('a', class_="black01")
if ass and len(ass) != 0:
lines = ass[0].stripped_strings
parser = ProfileParser(lines=lines, employee=employee)
employee = parser.parse()
return employee
def handler(tag):
ass = tag.find_all(name='a')
if not ass:
return None
employee = Employee()
if len(ass) >= 2:
employee.email = ass[1].string
if employee.email:
employee.email = ''.join(employee.email.split())
if len(ass) >= 1:
employee.name = ass[0].string
if not employee.name:
return None
employee.name = employee.name.strip()
employee.url = ass[0]['href']
return employee
def handler(tag):
employee = Employee(url=tag['href'])
# 刘全勇： 硕士生导师
string = ''.join(tag.string.split())
string_splits = string.split(u'：')
if len(string_splits) == 1:
employee.name = string_splits[0]
elif len(string_splits) == 2:
employee.name = string_splits[0]
employee.title = string_splits[1]
else:
return None
print("name:"+employee.name )
return employee
def handler(tag):
employee = Employee(url=tag['href'])
# 刘全勇： 硕士生导师
string = ''.join(tag.get_text().split())
string_splits = string.split(u'：')
if len(string_splits) == 1:
employee.name = string_splits[0]
elif len(string_splits) == 2:
employee.name = string_splits[0]
employee.title = string_splits[1]
else:
return None
print("name:"+employee.name )
return employee
def handler(tag):
tds = tag.find_all(name='td')
if not tds or len(tds) != 5:
return None
name = tds[0].get_text()
if not name or len(name) == 0:
return None
employee = Employee()
employee.name = ''.join(name.split())
if employee.name == u'姓名':
return None
ass = tag.find_all('a')
if ass:
employee.url = ass[0]['href']
title = tds[3].get_text()
if title and len(title) != 0:
title = ''.join(title.split())
title = title.replace(',','，')
employee.title = title
print title
research = tds[4].get_text()
if research and len(research) != 0:
employee.research = research.strip()
employee.research = employee.research.replace(',','，')
return employee
def handler(tag):
tds = tag.find_all(name='td')
if not tds or len(tds) != 5:
return None
name = tds[0].get_text()
if not name or len(name) == 0:
return None
employee = Employee()
employee.name = ''.join(name.split())
if employee.name == u'姓名':
return None
ass = tag.find_all('a')
if ass:
employee.url = ass[0]['href']
title = tds[3].get_text()
if title and len(title) != 0:
title = ''.join(title.split())
title = title.replace(',', '，')
employee.title = title
print title
research = tds[4].get_text()
if research and len(research) != 0:
employee.research = research.strip()
employee.research = employee.research.replace(',', '，')
return employee
def handler(tag):
ass = tag.find_all(name='a')
if not ass:
return None
employee = Employee()
if len(ass) >= 2:
employee.email = ass[1].string
if employee.email:
employee.email = ''.join(employee.email.split())
if len(ass) >= 1:
employee.name = ass[0].string
if not employee.name:
return None
employee.name = employee.name.strip()
employee.url = ass[0]['href']
return employee
def profile_handler(doc,name,url,path):
# employee可用属性(url, name, email, tel, title, profile, research, departments,fax,addr):
symbols = {
u'Email：' :'email',
u'邮箱：' :'email',
u'电子邮件：' :'email',
u'电子邮箱：' :'email',
u'电话：' :'tel',
u'联系电话：' :'tel',
u'Tel：' :'tel',
u'办公电话：' :'tel',
u'传真：' :'fax',
u'URL：' :'url',
u'职称：' :'title'
}
employee = None
# 太乱了，只保存名称和个人主页，个人简历文件另存当前目录
soup = BeautifulSoup(doc, Config.SOUP_PARSER)
divs = soup.find_all(id="s2_right_con",limit=1)
filename = path+name+".html"
if not divs or len(divs) == 0:
return Employee(name=name,url=url)
div =divs[0]
with open(filename,'wb') as fp:
content = div.prettify()
fp.write(content)
fp.close()
employee = Employee()
# parse name
name_h4 = div.h4
if name_h4:
employee.name = name_h4.string.strip(' \t\n\r')
else:
print name_h4
for tag in div.children:
if not tag.string:
continue
text = tag.string.strip(' \t\n\r')
if len(text) == 0:
continue
for symbol,name in symbols.items():
idx = text.find(symbol)
if idx != -1:
idx += len(symbol)
value = text[idx:]
if hasattr(employee, name):
setattr(employee, name, value)
symbols
# print (name + ":" + value)
else:
print ("no attr %s in employee" % name)
break
return employee
def profile_handler(doc, name, url, path):
# employee可用属性(url, name, email, tel, title, profile, research, departments,fax,addr):
symbols = {
u'Email：': 'email',
u'邮箱：': 'email',
u'电子邮件：': 'email',
u'电子邮箱：': 'email',
u'电话：': 'tel',
u'联系电话：': 'tel',
u'Tel：': 'tel',
u'办公电话：': 'tel',
u'传真：': 'fax',
u'URL：': 'url',
u'职称：': 'title'
}
employee = None
# 太乱了，只保存名称和个人主页，个人简历文件另存当前目录
soup = BeautifulSoup(doc, Config.SOUP_PARSER)
divs = soup.find_all(id="s2_right_con", limit=1)
filename = path + name + ".html"
if not divs or len(divs) == 0:
return Employee(name=name, url=url)
div = divs[0]
with open(filename, 'wb') as fp:
content = div.prettify()
fp.write(content)
fp.close()
employee = Employee()
# parse name
name_h4 = div.h4
if name_h4:
employee.name = name_h4.string.strip(' \t\n\r')
else:
print name_h4
for tag in div.children:
if not tag.string:
continue
text = tag.string.strip(' \t\n\r')
if len(text) == 0:
continue
for symbol, name in symbols.items():
idx = text.find(symbol)
if idx != -1:
idx += len(symbol)
value = text[idx:]
if hasattr(employee, name):
setattr(employee, name, value)
symbols
# print (name + ":" + value)
else:
print("no attr %s in employee" % name)
break
return employee
def handler(tag):
employee = Employee()
lines = tag.stripped_strings
ass = tag.find_all(name="a", attrs={"class": "dt_text_tit"})
if not ass or len(ass) == 0:
# first line is the name
for count, line in enumerate(lines):
employee.name = line
break
else:
employee.name = ass[0].string
employee.profile = ass[0]["href"]
employee.url = employee.profile
parser = ProfileParser(lines=lines, employee=employee)
employee = parser.parse()
return employee
def handler(tag):
employee = Employee()
lines = tag.stripped_strings
ass = tag.find_all(name="a", attrs={"class": "dt_text_tit"})
if not ass or len(ass) == 0:
# first line is the name
for count, line in enumerate(lines):
employee.name = line
break
else:
employee.name = ass[0].string
employee.profile = ass[0]['href']
employee.url = employee.profile
parser = ProfileParser(lines=lines, employee=employee)
employee = parser.parse()
return employee
def handler(tag):
name_spans = tag.find_all(class_="handle")
if not name_spans or len(name_spans) == 0:
return None
# js <span class="handle" onclick="toCardDetailAction('10c07e70-3fb6-42af-aa26-bfab26b6ce0406');" style="color:#2084D2;font-size: 16px;">艾明晶</span>
employee = Employee()
employee.name = name_spans[0].get_text()
employee.name = ''.join(employee.name.split())
card_id = name_spans[0]['onclick'][len('toCardDetailAction(\''):-3]
employee.url = 'http://scse.buaa.edu.cn/buaa-css-web/toCardDetailAction.action?firstSelId=CARD_TMPL_OF_FIRST_NAVI_CN%20&%20secondSelId=CARD_TMPL_OF_ALL_TEACHER_CN%20&cardId='+card_id
print ("card_id=[%s]"%card_id)
lines = tag.stripped_strings
parser = ProfileParser(lines=lines,employee=employee)
return parser.parse()
def handler(tag):
tds = tag.find_all(name='td')
if not tds or len(tds) != 3:
return None
employee = Employee()
employee.name = tds[0].get_text() or ''
employee.name = ''.join(employee.name.split())
# 过滤表头
if employee.name == u'姓名':
return None
employee.title = tds[1].get_text()
employee.title = ''.join(employee.title.split())
employee.email = tds[2].get_text()
employee.email = ''.join(employee.email.split())
employee.email = email_value_strip(employee.email)
# print(tag)
return employee
def handler(tag):
tds = tag.find_all(name='td')
if not tds or len(tds) != 3:
return None
employee = Employee()
employee.name = tds[0].get_text() or ''
employee.name = ''.join(employee.name.split())
# 过滤表头
if employee.name == u'姓名':
return None
employee.title = tds[1].get_text()
employee.title = ''.join(employee.title.split())
employee.email = tds[2].get_text()
employee.email = ''.join(employee.email.split())
employee.email = email_value_strip(employee.email)
# print(tag)
return employee
def handler(tag):
dd_tables = {
"Email":"email",
"Phone":"tel",
"Homepage":"profile",
'Math Fields':'research'
}
lis = tag.find_all('li')
if len(lis) < 4:
return None
employee = Employee()
pre_len = len(u'职务：')
employee.name = lis[0].get_text()
employee.profile = lis[0].a['href']
employee.url = employee.url or employee.profile
if not employee.name:
employee.name = employee.name[pre_len:]
employee.name = ''.join(employee.name.split())
employee.title = lis[1].get_text()
if employee.title:
employee.title = employee.title[pre_len:]
employee.title = ''.join(employee.title.split())
employee.tel = lis[2].get_text()
if employee.tel:
employee.tel = employee.tel[pre_len:]
employee.tel = ''.join(employee.tel.split())
employee.email = lis[3].get_text()
if employee.email:
employee.email = employee.email[pre_len:]
employee.email = ''.join(employee.email.split())
print("name:"+employee.name+",email:"+employee.email)
return employee
def handler(tag):
employee = Employee()
names = tag.get_text()
names = ''.join(names.split())
names = names.replace('）','')
names = names.replace(')','')
names = names.replace('（','(')
names = names.split('(')
employee.name = names[0]
if len(names) >= 2:
employee.title = names[1]
employee.url = tag['href']
print employee.name, employee.title
return employee
def handler(tag):
dd_tables = {
"Email":"email",
"Phone":"tel",
"Homepage":"profile",
'Math Fields':'research'
}
h3 = tag.find_all(name='h3')
if not h3:
return None
employee = Employee()
employee.name = h3[0].get_text() or ''
employee.name = ''.join(employee.name.split())
title_spans = tag.find_all(name="span",class_="faculty-title")
employee.title = title_spans[0].get_text()
#employee.title = ''.join(employee.title.split())
tds = tag.find_all(name='dt',class_="faculty-info")
if not tds or len(tds) < 5:
return None
employee.email = tds[0].get_text()
employee.email = ''.join(employee.email.split())
employee.tel = tds[1].get_text()
employee.tel = ''.join(employee.tel.split())
employee.profile = tds[3].get_text()
employee.profile = ''.join(employee.profile.split())
employee.research = tds[4].get_text()
#employee.research = ''.join(employee.research.split())
return employee
def handler(tag):
dd_tables = {
"Email": "email",
"Phone": "tel",
"Homepage": "profile",
'Math Fields': 'research'
}
h3 = tag.find_all(name='h3')
if not h3:
return None
employee = Employee()
employee.name = h3[0].get_text() or ''
employee.name = ''.join(employee.name.split())
title_spans = tag.find_all(name="span", class_="faculty-title")
employee.title = title_spans[0].get_text()
#employee.title = ''.join(employee.title.split())
tds = tag.find_all(name='dt', class_="faculty-info")
if not tds or len(tds) < 5:
return None
employee.email = tds[0].get_text()
employee.email = ''.join(employee.email.split())
employee.tel = tds[1].get_text()
employee.tel = ''.join(employee.tel.split())
employee.profile = tds[3].get_text()
employee.profile = ''.join(employee.profile.split())
employee.research = tds[4].get_text()
#employee.research = ''.join(employee.research.split())
return employee
def update_employee(self, employee_id):
# -------------------------
# Update data of employee
# -------------------------
if request.form.get('_method') != 'PUT':
app.logger.Info(
'Cannot perform this action. Please contact administrator')
abort(405)
employee = Employee(id=employee_id)
try:
employee = employee.list_one_or_none_employee()
if employee is None:
app.logger.info(
f'No data with Employee ID = {employee_id} could be found!')
abort(422)
except BaseException:
app.logger.info(
f'An error occurred. No data with Employee ID\
= {employee_id} could be found!')
abort(422)
employee.id = employee_id
employee.name = request.form.get('name', employee.name)
temp = request.form.get('department_name')
employee.department_id = temp.split(' - ', 2)[0]
employee.title = request.form.get('title', employee.title)
employee.emp_number = request.form.get('emp_number', employee.emp_number)
employee.address = request.form.get('address', employee.address)
employee.phone = request.form.get('phone', employee.phone)
employee.wage = request.form.get('wage', employee.wage)
employee.is_active = 'is_active' in request.form
try:
employee.update_employee_in_database()
flash(
f'Employee {employee_id} was successfully updated!',
'success')
except BaseException:
app.log.info(f'An error occurred. Employee {employee_id} \
could not be updated!')
abort(422)
return redirect(url_for('employees'))
def create_Employee(emp : createEmployee, db : Session = Depends(get_db)):
_employee = Employee()
_employee.id = emp.id
_employee.name = emp.name
_employee.email = emp.email
_employee.position = emp.position
_employee.works_on: emp.works_on
_employee.reporting_manager : emp.reporting_manager
db.add(_employee)
db.commit()
# Background_tasks.add_task(fetch_emp_data,employee.id)
return{
"code":"Success",
"messege": "Employee created the name"+emp.name
}
def create_employee_process():
employee = Employee()
employee.name = request.form['name']
employee.phone = request.form['phone']
employee.email = request.form['email']
employee.address = {
'street': request.form['street'],
'city': request.form['city'],
'state': request.form['state'],
'zipcode': request.form['zipcode'],
}
if employee.create_employee():
msg = Message()
employee.send_email(mail, msg, app)
return 'Success'
else:
raise Exception
def handler(tag):
symbols = set([u'首页',u'第一页',u'下一页',u'最后页 ',u'上一页',])
if not tag.string:
return None
name = tag.string.strip()
if name in symbols:
return None
employee = Employee(name=name, url=tag['href'])
# 根据预定的关键词推测身分
for keyword in PROFILE_TITLES:
idx = name.find(keyword)
if idx != -1:
employee.name = name[:idx]
employee.title = name[idx:]
break
return employee
def handler(tag):
name_symbol = u'姓名'
tds = tag.find_all('td')
if len(tds) != 7:
return None
if tds[0].get_text().strip() == name_symbol:
return None
employee = Employee()
ass = tds[0].find_all('a')
if len(ass) != 0:
employee.url = ass[0]['href']
employee.name = tds[0].get_text().strip()
employee.email = tds[2].get_text().strip()
employee.title = tds[3].get_text().strip()
employee.research = tds[6].get_text().strip()
employee.research.replace('\n', '.')
print employee.name, employee.email, employee.title
return employee
def handler(tag):
name_symbol = u'姓名'
tds = tag.find_all('td')
if len(tds) != 7:
return None
if tds[0].get_text().strip() == name_symbol:
return None
employee = Employee()
ass = tds[0].find_all('a')
if len(ass) != 0:
employee.url = ass[0]['href']
employee.name = tds[0].get_text().strip()
employee.email = tds[2].get_text().strip()
employee.title = tds[3].get_text().strip()
employee.research = tds[6].get_text().strip()
employee.research.replace('\n','.')
print employee.name,employee.email,employee.title
return employee
def handler(tag):
tds = tag.find_all("td")
if not tds or len(tds) != 3:
return None
employee = Employee()
name = tds[0].get_text()
if not name:
return None
name = name.strip()
if name == u'姓名':
return None
names = name.split('/')
name = names[0]
employee.name = name
employee.title = tds[1].string.strip()
ass = tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
return employee
def handler(tag):
symbols = ['首页' ,'尾页','师资队伍' ,'教师简介','教授', '上一页','下一页','[1]','[2]','1','2']
name = tag.get_text()
if not name or len(name) == 0:
return None
employee = Employee(url = tag['href'])
name = name.strip()
# 特殊过滤去掉说明头
for s in symbols:
if name == s:
return None
names = name.split(' ')
if len(names) >= 2:
employee.title = names[1]
employee.name = ''.join(names[:-1])
return employee
def handler(tag):
tds = tag.find_all("td")
if not tds or len(tds) != 3:
return None
employee = Employee()
name = tds[0].get_text()
if not name:
return None
name = name.strip()
if name == u'姓名':
return None
names = name.split('/')
name = names[0]
employee.name = name
employee.title = tds[1].string.strip()
ass = tag.find_all('a')
if ass and len(ass) != 0:
employee.url = ass[0]['href']
return employee
def handler(tag):
symbols = [
'首页', '尾页', '师资队伍', '教师简介', '教授', '上一页', '下一页', '[1]', '[2]', '1', '2'
]
name = tag.get_text()
if not name or len(name) == 0:
return None
employee = Employee(url=tag['href'])
name = name.strip()
# 特殊过滤去掉说明头
for s in symbols:
if name == s:
return None
names = name.split(' ')
if len(names) >= 2:
employee.title = names[1]
employee.name = ''.join(names[:-1])
return employee
def profile_handler(doc, name, url, path):
# employee可用属性(url, name, email, tel, title, profile, research, departments,fax,addr):
symbols = {
'email': u'电子邮件：',
'tel': u'办公电话：',
'addr': u'办公地址：',
'research': u'研究方向：'
}
employee = None
soup = BeautifulSoup(doc, Config.SOUP_PARSER)
divs = soup.find_all("td", attrs={"valign": "top"}, limit=1)
if not divs or len(divs) == 0:
return employee
div = divs[0]
employee = Employee()
# save file
filename = path + name + ".html"
with open(filename, 'wb') as fp:
content = div.prettify()
fp.write(content)
fp.close()
# parse name
name_h3 = div.h3
if name_h3:
employee.name = name_h3.string.strip(' \t\n\r')
else:
print name_h3
# parse title
dls = soup.dl
if dls and len(dls) >= 1:
print dls
if dls.dt:
employee.title = dls.dt.string
# parse everything
for tag in dls.children:
if not tag.string:
continue
text = tag.string.strip(' \t\n\r')
if len(text) == 0:
continue
for name, symbol in symbols.items():
idx = text.find(symbol)
if idx != -1:
idx += len(symbol)
value = text[idx:]
if hasattr(employee, name):
setattr(employee, name, value)
# print (name + ":" + value)
else:
print("no attr %s in employee" % name)
break
# parse profile
teachcontent = soup.find_all("div", class_="teachcontent", limit=1)
if len(teachcontent) != 0:
content = teachcontent[0]
link = content.a
if link:
employee.url = link['href']
return employee
def profile_handler(doc,name,url,path):
# employee可用属性(url, name, email, tel, title, profile, research, departments,fax,addr):
symbols = {
'email': u'电子邮件：',
'tel': u'办公电话：',
'addr': u'办公地址：',
'research':u'研究方向：'
}
employee = None
soup = BeautifulSoup(doc, Config.SOUP_PARSER)
divs = soup.find_all("td",attrs={"valign":"top"},limit=1)
if not divs or len(divs) == 0:
return employee
div = divs[0]
employee = Employee()
# save file
filename = path+name+".html"
with open(filename,'wb') as fp:
content = div.prettify()
fp.write(content)
fp.close()
# parse name
name_h3 = div.h3
if name_h3:
employee.name = name_h3.string.strip(' \t\n\r')
else:
print name_h3
# parse title
dls = soup.dl
if dls and len(dls) >= 1:
print dls
if dls.dt:
employee.title = dls.dt.string
# parse everything
for tag in dls.children:
if not tag.string:
continue
text = tag.string.strip(' \t\n\r')
if len(text) == 0:
continue
for name, symbol in symbols.items():
idx = text.find(symbol)
if idx != -1:
idx += len(symbol)
value = text[idx:]
if hasattr(employee, name):
setattr(employee, name, value)
# print (name + ":" + value)
else:
print ("no attr %s in employee" % name)
break
# parse profile
teachcontent = soup.find_all("div",class_="teachcontent",limit=1)
if len(teachcontent) != 0:
content = teachcontent[0]
link= content.a
if link:
employee.url = link['href']
return employee