Python Employee.research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 research [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 research [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={"id":"right_2"}, limit=1)
    if not divs or len(divs) == 0:
        return employee

    div = divs[0]
    if not os.path.exists(filename):
        with open(filename, 'wb') as fp:
            content = div.prettify()
            fp.write(content)
            fp.close()
    
    researches = [' ',' ']
    tds = div.find_all(name="td",attrs={"bgcolor":"#FFFFFF","class":"ft12","valign":"top"},limit=4)
    if len(tds) == 4:
        researches[0] = tds[2].get_text().strip()
        researches[1] = tds[3].get_text().strip()
        employee.research = researches[0] + ";" +researches[1]
        print "research:" + employee.research 
    # 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,ignore=set(['research']))
    return parser.parse()

# 需要导入模块: from models import Employee [as 别名]
# 或者: from models.Employee import research [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 research [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_="xq_teacher", limit=1)
    if not divs or len(divs) == 0:
        return employee

    div = divs[0]
    
    if not os.path.exists(filename):
        with open(filename, 'wb') as fp:
            content = div.prettify()
            fp.write(content)
            fp.close()
        
    # 找到科研方向
    details = div.find_all("div",class_="con01_t",limit=3)
    if details and len(details) >= 2:
        employee.research = details[1].get_text()
        employee.research = ''.join(employee.research.split())
        # 过滤掉太短的串
        if len(employee.research) <= (len(u'研究方向')+1):
            employee.research = ''
        else:
            employee.research.replace(',','，')
    
    # 解析其他各人信息
    infos = div.find_all("div",class_="wz_teacher",limit=1)
    if infos and len(infos) != 0:
        # 使用纯文本方式处理
        lines = infos[0].stripped_strings
        parser = ProfileParser(lines=lines,employee=employee,set_attr_hook=set_attr_hook,force_email=True)
        return parser.parse()
    else:
        return employee

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

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