BeautifulSopu
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
from bs4 import BeautifulSopu
soup = BeautifulSoup(html_doc, 'html.parser')
print(soup.prettify())
The Dormouse's story
Once upon a time there were three little sisters; and their names were
Elsie
,
Lacie
and
Tillie
;
and they lived at the bottom of a well.
...
soup.a
soup.find_all("a")
soup.findAll("a")
#在文档中找到所有<a>标签的链接
for link in soup.find_all('a'):
print(link.get('href'))
http://example.com/elsie
http://example.com/lacie
http://example.com/tillie
#从文档中获取所有文字内容:
print(soup.get_text())
The Dormouse's story
The Dormouse's story
Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
#通过正则表达式的search()来匹配内容
import re
for tag in soup.find_all(re.compile("^b")):
print(tag.name)
body
b
#如果传入列表参数,BS会将列表中任一元素匹配的内容返回
soup.find_all(["a",'b'])
[The Dormouse's story,
Elsie,
Lacie,
Tillie]
def has_class_but_no_id(tag):
return tag.has_attr('class') and not tag.has_attr('id')
#将这个方法作为参数传入find_all()方法,将得到所有<p>标签
soup.find_all(has_class_but_no_id)
[
The Dormouse's story
,Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
]soup.find_all("p")
[
The Dormouse's story
,Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
]soup.find_all("p","title")
#find_all(name,attrs,recursive,string,**kwargs)
[
The Dormouse's story
]按CSS搜索
soup.find_all("a",class_="sister")
CSS选择器
soup.select("title")
[
soup.select("body a")
soup.select("head>title")
[
soup.select("p>a")
soup.select("p>a:nth-of-type(2)")
[Lacie]
soup.select("p> #link1")
[Elsie]
#通过css的类名查找
soup.select(".sister")
#通过tag的id查找
soup.select("a#link2")
[Lacie]
#get_text()
markup = '<a href="http://example.com/">\nI linked to <i>example.com</i>\n</a>'
soup = BeautifulSoup(markup)
print(soup.get_text("|",strip=True))
print(soup.i.get_text())
#或使用.stripped_strings生成器,并获得文本列表后手动处理列表:
[text for text in soup.stripped_strings]
I linked to|example.com
example.com
['I linked to', 'example.com']
解析器之间的区别
from lxml import etree
root = etree.Element("root")
print(root.tag)
root
root.append(etree.Element("child1"))
child2=etree.SubElement(root,"child2")
child3=etree.SubElement(root,"child3")
print(etree.tostring(root, pretty_print=True))
b'
#Elements are lists
child = root[0]
print(child.tag)
print(len(root))
child1
14
for child in root:
print(child.tag)
child1
child1
child1
child2
child3
child1
child2
child3
child1
child2
child3
child1
child2
child3
浙公网安备 33010602011771号