Python爬虫练习1

from bs4 import BeautifulSoup

html='''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element1">Foo-1</li>
            <li class="element1">Bar</li>
        </ul>
    </div>
</div>'''

soup=BeautifulSoup(html,'html.parser')
h4_1=soup.h4
print('h4:',h4_1)
print('h4的文本:',h4_1.text)
# ul1=soup.ul
# li1=ul1.li
ul1=soup.find('ul')
li1=ul1.findChild('li')
print('第一个ul下的第一个li的文本:',li1.text)

from bs4 import BeautifulSoup

soup=BeautifulSoup(open('default.html',encoding='utf-8'),'html.parser')

print('class为p2的段落:')
class_p2=soup.find_all('p',class_='p2')
for i in class_p2:
    print(i.text)

print('\nclass为p2的段落,且段落文本为"此段文字以26像素大小，玫红色字体显示2":')
class_p2_t1=soup.find_all('p',class_='p2',string='此段文字以26像素大小，玫红色字体显示2')
for i in class_p2_t1:
    print(i.text)

print('\ndiv，id为“divdemo1”，其文本:')
div=soup.find_all('div',id='divdemo1')
for i in div:
    print(i.text)