Python Employee.tel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 tel [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":"phy-main"}, 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()
    
    #email
    email_div = soup.find_all(name='a',class_="phy-mail")
    if email_div and len(email_div) != 0:
        employee.email = email_div[0].get_text().strip()

    te_div = soup.find_all(name='a',class_="phy-phone")
    if te_div and len(te_div) != 0:
        employee.tel = te_div[0].get_text().strip()
    
    # 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 tel [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 tel [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 tel [as 别名]
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

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

    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": "view_pannel"}, 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()

    # email image
    item_divs = div.find_all(name="div", attrs={"class": "item_list"})

    ignores = []
    for div in item_divs:
        string = div.get_text()
        if string and len(string) != 0:
            if u"邮件" in string and len(employee.email) == 0:
                employee.email = image2text(imageSrc(div), email_image_filename, "eng2")
                print(employee.email)
                ignores.append("email")
            elif u"电话" in string and len(employee.tel) == 0:
                employee.tel = image2text(imageSrc(div), tel_image_filename, "eng")
                print(employee.tel)
                ignores.append("tel")

    # 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, max_line=256, ignore=set(ignores)
    )
    return parser.parse()