BeautifulSoup官方文档:https://beautifulsoup.readthedocs.io/zh_CN/latest/#id8
太繁琐的,精简了一些自己用的到的。
1.index.html
<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>
2..prettify()--标准的缩进格式输出
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc, 'html.parser')
print(soup.prettify())
# <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 class="sister" href="http://example.com/elsie" id="link1">
# Elsie
# </a>
# ,
# <a class="sister" href="http://example.com/lacie" id="link2">
# Lacie
# </a>
# and
# <a class="sister" href="http://example.com/tillie" id="link2">
# Tillie
# </a>
# ; and they lived at the bottom of a well.
# </p>
# <p class="story">
# ...
# </p>
# </body>
# </html>
3.选择标签,属性
soup.title
# <title>The Dormouse's story</title>
soup.title.name
# u'title'
soup.title.string
# u'The Dormouse's story'
soup.title.parent.name
# u'head'
soup.p
# <p class="title"><b>The Dormouse's story</b></p>
soup.p['class']
# u'title'
soup.a
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
soup.find_all('a')
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
soup.find(id="link3")
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
for link in soup.find_all('a'):
print(link.get('href'))
# http://example.com/elsie
# http://example.com/lacie
# http://example.com/tillie
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.
#
# ...
#Tag
soup = BeautifulSoup('<b class="boldest">Extremely bold</b>')
tag = soup.b
type(tag)
# <class 'bs4.element.Tag'>
#Name
tag.name
# u'b'
tag.name = "blockquote"
tag
# <blockquote class="boldest">Extremely bold</blockquote>
#Attributes
tag['class']
# u'boldest'
tag.attrs
# {u'class': u'boldest'}
tag['class'] = 'verybold'
tag['id'] = 1
tag
# <blockquote class="verybold" id="1">Extremely bold</blockquote>
del tag['class']
del tag['id']
tag
# <blockquote>Extremely bold</blockquote>
tag['class']
# KeyError: 'class'
print(tag.get('class'))
# None
2.find_all
1）name 参数#A.传字符串soup.find_all('b')
# [<b>The Dormouse's story</b>]
print soup.find_all('a')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>,
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
print soup.find_all('a')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>,
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
<
a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
#B.传正则表达式
import re
for tag in soup.find_all(re.compile("^b")):
print(tag.name)
# body
# b
#C.传列表
soup.find_all(["a", "b"])
# [<b>The Dormouse's story</b>,
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
#D.传 True
for tag in soup.find_all(True):
print(tag.name)
# html
# head
# title
# body
# p
# b
# p
# a
# a
#E.传方法
def has_class_but_no_id(tag):
return tag.has_attr('class') and not tag.has_attr('id')
soup.find_all(has_class_but_no_id)
# [<p class="title"><b>The Dormouse's story</b></p>,
# <p class="story">Once upon a time there were...</p>,
# <p class="story">...</p>]
2）keyword 参数
soup.find_all(id='link2')
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
soup.find_all(href=re.compile("elsie"))
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
soup.find_all(href=re.compile("elsie"), id='link1')
# [<a class="sister" href="http://example.com/elsie" id="link1">three</a>]
soup.find_all("a", class_="sister")
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
data_soup = BeautifulSoup('<div data-foo="value">foo!</div>')
data_soup.find_all(data-foo="value")
# SyntaxError: keyword can't be an expression
data_soup.find_all(attrs={"data-foo": "value"})
# [<div data-foo="value">foo!</div>]
3）text 参数
soup.find_all(text="Elsie")
# [u'Elsie']
soup.find_all(text=["Tillie", "Elsie", "Lacie"])
# [u'Elsie', u'Lacie', u'Tillie']
soup.find_all(text=re.compile("Dormouse"))
[u"The Dormouse's story", u"The Dormouse's story"]
4）limit 参数
soup.find_all("a", limit=2)
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
5）recursive 参数
#调用tag的 find_all() 方法时,Beautiful Soup会检索当前tag的所有子孙节点,如果只想搜索tag的直接子节点,可以使用参数 recursive=False
soup.html.find_all("title")
# [<title>The Dormouse's story</title>]
soup.html.find_all("title", recursive=False)
# []
3.CSS选择器
（1）通过标签名查找
print soup.select('title')
#[<title>The Dormouse's story</title>]
print soup.select('a')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
print soup.select('b')
#[<b>The Dormouse's story</b>]
（2）通过类名查找
print soup.select('.sister')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
（3）通过 id 名查找
print soup.select('#link1')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>]
（4）组合查找
print soup.select('p #link1')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>]
print soup.select("head > title")
#[<title>The Dormouse's story</title>]
（5）属性查找
print soup.select('a[class="sister"]')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
print soup.select('a[href="http://example.com/elsie"]')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>]
print soup.select('p a[href="http://example.com/elsie"]')
#[<a class="sister" href="http://example.com/elsie" id="link1"><!-- Elsie --></a>]
soup = BeautifulSoup(html, 'lxml')
print type(soup.select('title'))
print soup.select('title')[0].get_text()
for title in soup.select('title'):
print title.get_text()
