python beautifulsoup

Beautiful Soup类的基本元素

例子

from bs4 import BeautifulSoup
r = requests.get('https://python123.io/ws/demo.html')
demo = r.text
soup = BeautifulSoup(demo,'html.parser')  #'html.parser'是解析器
print(soup.prettify())

结果

Beautiful Soup库的理解

基于bs4库的HTML内容遍历方法

下行遍历

from bs4 import BeautifulSoup
r = requests.get('https://python123.io/ws/demo.html')
demo = r.text
demo
soup = BeautifulSoup(demo,'html.parser')
soup.head   #head标签，任何html可以分为head、body标签
soup.head.contents   #head的儿子节点
soup.body.contents   #body的儿子节点
len(soup.body.contents)  #body标签的儿子节点数量
soup.body.contents[1]  #body标签的第二个儿子节点

for child in soup.body.children:  #遍历儿子节点
    #print(child)
    
    
for child in soup.body.descendants:  #遍历子孙节点
    print(child)

上行遍历

from bs4 import BeautifulSoup
import requests
r = requests.get('https://python123.io/ws/demo.html')
demo = r.text
demo
soup = BeautifulSoup(demo,'html.parser')
#打印a标签的所有父辈标签的名字
for parent in soup.a.parents:
    if parent is None:
        print(parent)
    else:
        print(parent.name)

平行遍历（只能平行遍历同一个父辈标签下的标签）

from bs4 import BeautifulSoup
import requests
r = requests.get('https://python123.io/ws/demo.html')
demo = r.text
demo
soup = BeautifulSoup(demo,'html.parser')
soup.a.next_sibling  #a标签的下一个节点
                     #下一个节点不一定是标签，也有可能是NavigableString类型
soup.a.next_sibling.next_sibling  #a标签的下一个节点的下一个节点
soup.a.previous_sibling  #a标签的上一个节点

for sibling in soup.a.next_siblings:   #遍历后续节点
    print(sibling)

基于bs4库的HTML格式化和编码

from bs4 import BeautifulSoup
import requests
r = requests.get('https://python123.io/ws/demo.html')
demo = r.text
soup = BeautifulSoup(demo,'html.parser')
soup.prettify()  #.prettify()在标签后加换行符
print(soup.prettify())  #print函数将\n换行符实现