from bs4 import BeautifulSoup
html = """
The Dormouse's story
The Dormouse's story
Once upon a time there were three little sisters; and their names were
,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
"""
#按标签名查找
soup = BeautifulSoup(html,"lxml") #使用lxml库解析网页
res = soup.select("title") #查找标签为title的内容
print("标签title : ",res)
>>>标签title : [
The Dormouse's story] #输出一个list
soup = BeautifulSoup(html,"lxml")
res = soup.select("a")
print("标签a : ",res)
#此处输出的list有三个元素,因为标签a有三对
>>>标签a : [, Lacie, Tillie]
#通过类名查找
soup = BeautifulSoup(html,"lxml")
res = soup.select(".title") #查找class=title的内容
print("通过类名查找class=title : ",res)
>>>通过类名查找class=title : [
The Dormouse's story
]
soup = BeautifulSoup(html,"lxml")
res = soup.select(".sister")
print("通过类名查找class=sister : ",res)
>>>通过类名查找class=sister : [, Tillie]
#通过 id 名查找
soup = BeautifulSoup(html,"lxml")
res = soup.select("#link1") #查找id=link1的内容
print("通过 id 名查找id=link1 : ",res)
>>>通过类名查找class=sister : []
#通过组合查找
组合查找和写 class 文件时,标签名与类名、id名进行的组合原理是一样的,例如查找 p 标签中,id 等于 link1的内容,二者需要用空格分开
soup = BeautifulSoup(html,"lxml")
res = soup.select("p #link1") #查找p标签中,id=link1的内容
print("通过组合查找group=p #link1 : ",res)
>>>通过组合查找group=p #link1 : []
soup = BeautifulSoup(html,"lxml")
res = soup.select("p .brother")
print("通过组合查找group=p .brother : ",res)
>>>通过组合查找group=p .brother : [Lacie]
#通过子标签查找
soup = BeautifulSoup(html,"lxml")
res = soup.select("head > title") #head标签下的title子标签
print("通过子标签查找head > title : ",res)
>>>通过子标签查找head > title : [
The Dormouse's story]
#通过属性查找
查找时还可以加入属性元素,属性需要用中括号括起来,注意属性和标签属于同一节点,所以中间不能加空格,否则会无法匹配到。
soup = BeautifulSoup(html,"lxml")
res = soup.select('a[href="/elsie"]') #a标签下属性为/elsie的内容
print("通过属性查找 : ",res)
>>>通过属性查找 : []