Python Employee.title方法代码示例

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
def profile_handler(doc, name, url, path):
    filename = os.path.join(path, name + ".html")
    employee = Employee(name=name, url=url)

    # 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(name="div", class_="box_rt01 list", limit=1)
    if not divs or len(divs) == 0:
        div = soup
    else:
        div = divs[0]

    with open(filename, 'wb') as fp:
        content = div.prettify()
        fp.write(content)
        fp.close()

    h3s = div.find_all('h3')
    if h3s and len(h3s) != 0:
        title = h3s[0].get_text()
        title = ''.join(title.split())
        print title
        for t in PROFILE_TITLES:
            if t in title:
                employee.title = title
                print "got => " + title
                break
    else:
        print "not found h3"
    # 使用纯文本方式处理
    lines = div.stripped_strings
    # text=div.get_text(strip=True)
    parser = ProfileParser(lines=lines,employee=employee,force_email=True)
    return parser.parse()

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
def handler(tag):
    name = tag.get_text()
    name = ''.join(name.split())
    names = name.split('_')
    name = names[0]
    employee = Employee(url=tag['href'], name=name)
    if len(names) >= 2:
        employee.title = names[1]
    return employee

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
def profile_handler(doc, name, url, path):
    filename = os.path.join(path, name + ".html")
    employee = Employee(name=name, url=url)

    # 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(name="div", attrs={"class":"page_right addpage_right"}, limit=1)
    if not divs or len(divs) == 0:
        div= soup
    else:
        div = divs[0]
    if not os.path.exists(filename):
        with open(filename, 'wb') as fp:
            content = div.prettify()
            fp.write(content)
            fp.close()

    tds = div.find_all('td')
    if tds and len(tds) == 11:
        department =  tds[2].get_text()
        if department:
            department = ''.join(department.split())
            if department and len(department) != 0:
                employee.departments = department

        title =  tds[4].get_text()
        if title:
            title = ''.join(title.split())
            if title and len(title) != 0:
                employee.title = title

        email = tds[8].get_text()
        if email:
            email = ''.join(email.split())
            if email and len(email) != 0:
                employee.email = email

        research =  tds[10].get_text()
        if research:
            research = ''.join(research.split())
            if research and len(research) != 0:
                employee.research = research

    divs = soup.find_all(name="div", attrs={"class":"text_more"}, limit=1)
    if divs and len(divs) != 0:
        div = divs[0]
    # 使用纯文本方式处理
    lines = div.stripped_strings
    # text=div.get_text(strip=True)
    parser = ProfileParser(lines=lines,employee=employee,set_attr_hook=set_attr_hook)
    return parser.parse()

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
def add_rp14a_form(dictionary):
    with contextlib.closing(make_session()) as session:
        employee = Employee()
        employee.nino = dictionary["employee_national_insurance_number"]
        employee.date_of_birth = dictionary["employee_date_of_birth"]
        employee.title = dictionary["employee_title"]
        employee.forenames = dictionary["employee_forenames"]
        employee.surname =  dictionary["employee_surname"]
        employee.ip_number = "12345" #TODO: should we collect this on the form?
        employee.employer_name = dictionary["employer_name"]
        #TODO: Remove hack around decimals in JSON
        for decimal_key in ["employee_owed_wages_in_arrears", "employee_holiday_owed", "employee_basic_weekly_pay"]:
            if decimal_key in dictionary:
                dictionary[decimal_key] = str(dictionary[decimal_key])
        employee.hstore = {key: json.dumps(value, default=encode_special_types)
                           for key, value in dictionary.items()}
        session.add(employee)
        session.commit()

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
def profile_handler(doc,name,url,path):
    symbols = {
        u'个人主页：'   :'profile',
        u'研究方向：'   :'research',
        u'电话:':'tel',
        u'电话':'tel'
    }
    filename = path+name+".html"
    
    employee = Employee(name=name,url=url)
    # 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="sub_main",limit=1)
    if not divs or len(divs) == 0:
        # xml
        members = soup.find_all(name="member",limit=1)
        if not members or len(members) == 0:
            print("id:main or sub_main not found")
            #print doc
            return employee
        member = members[0]
        # title
        names = member.find_all('name')
        if not names and len(names) != 0:
            name = name[0].string
            if name:
                idx = name.find(' ')
                if idx != -1:
                    employee.title = name[idx:]
        if member.field:
            employee.research = member.field.string or ''
        if member.homepage:
            employee.profile = member.homepage.string or ''
        if member.contact:
            if member.contact.string:
                for i,c in enumerate(member.contact.string):
                    if c.isdigit():
                        employee.tel += c
        
        with open(filename,'wb') as fp:
            content = member.prettify()
            fp.write(content)
            fp.close()
        return employee
    
    div = divs[0]
    with open(filename,'wb') as fp:
        content = div.prettify()
        fp.write(content)
        fp.close()
        
    h4s = div.find_all('h4')
    if not h4s and len(h4s) != 0:
        name = h4s[0].string
        idx = name.find(' ')
        if idx != -1:
            employee.tite = name[idx:]
            employee.tite = ''.join(employee.tite.split())
            
    lis = div.find_all("li",limit=8)
    if not lis or len(lis) == 0:
        return employee
    res = lis[0]
    # 解析详细内容
    for count,tag in  enumerate(lis[0].children):
        text = tag.string
        if not text:
            continue
        if len(text) == 0:
            continue
        text = ''.join(text.split())
        if '@' in text:
            employee.email = text
            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)
                    print (name + ":" + value)
                else:
                    print ("no attr %s in employee" % name)
                break
    return employee

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import title [as 别名]
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