Python利用Beautiful Soup模块修改内容方法示例

html_markup="""
 <div class="ecopyramid">
 <ul id="producers">
  <li class="producerlist">
  <div class="name">plants</div>
  <div class="number">100000</div>
  </li>
  <li class="producerlist">
  <div class="name">algae</div>
  <div class="number">100000</div>
  </li>
 </ul>
 </div>
 """

soup = BeautifulSoup(html_markup,'lxml')
producer_entries = soup.ul
print producer_entries.name
producer_entries.name = "div"
print producer_entries.prettify()

# 修改标签属性
# 更新标签现有的属性值
producer_entries['id'] = "producers_new_value"
print producer_entries.prettify()
# 标签添加新的属性值
producer_entries['class'] = "newclass"
print producer_entries.prettify()
# 删除标签属性值
del producer_entries['class']
print producer_entries.prettify()

# 添加新的标签
# new_tag 生成一个 tag 对象
new_li_tag = soup.new_tag("li")
# 标签对象添加属性的方法
new_atag = soup.new_tag("a",href="www.example.com" rel="external nofollow" )
new_li_tag.attrs = {'class':'producerlist'}
soup = BeautifulSoup(html_markup,'lxml')
producer_entries = soup.ul
# 使用 append() 方法添加到末尾
producer_entries.append(new_li_tag)
print producer_entries.prettify()
# 生成两个 div 标签,将其插入到 li 标签中
new_div_name_tag = soup.new_tag("div")
new_div_name_tag['class'] = "name"
new_div_number_tag = soup.new_tag("div")
new_div_number_tag["class"] = "number"
# 使用 insert() 方法指定位置插入
new_li_tag.insert(0,new_div_name_tag)
new_li_tag.insert(1,new_div_number_tag)
print new_li_tag.prettify()

# 修改字符串内容
# 使用 .string 属性修改字符串内容
new_div_name_tag.string = 'new_div_name'
# 使用 .append() 方法添加字符串内容
new_div_name_tag.append("producer")
# 使用 soup 对象的 new_string() 方法生成字符串
new_string_toappend = soup.new_string("producer")
new_div_name_tag.append(new_string_toappend)
# 使用insert() 方法插入
new_string_toinsert = soup.new_string("10000")
new_div_number_tag.insert(0,new_string_toinsert)
print producer_entries.prettify()

# 删除节点
third_producer = soup.find_all("li")[2]
# 使用 decompose() 方法删除 div 节点
div_name = third_producer.div
div_name.decompose()
print third_producer.prettify()
# 使用 extract() 方法删除节点
third_producer_removed = third_producer.extract()
print soup.prettify()

# wrap()方法
li_tags = soup.find_all('li')
for li in li_tags:
 new_div_tag = soup.new_tag('div')
 li.wrap(new_div_tag)
print soup.prettify()
# unwrap()方法
li_tags = soup.find_all("li")
for li in li_tags:
 li.div.unwrap()
print soup.prettify()