基于bs4库的html内容查找方法

>>> for link in soup.find_all("a"):
...     print(link.get('href'))
...
http://www.icourse163.org/course/BIT-268001
http://www.icourse163.org/course/BIT-1001870001
>>> soup.find_all('a')#查找tag为a
[<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>, <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>]
>>> soup.find_all(['a','b'])
[<b>The demo python introduces several python courses.</b>, <a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>, <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>]
>>> for tag in soup.find_all(True):
...      print(tag.name)
...
html
head
title
body
p
b
p
a
a
>>> import re#正则表达式
>>> for tag in soup.find_all(re.compile('b')):#返回所有含b的标签
...     print(tag.name)#name是find_all的参数
...
body
b
>>> soup.find_all('p','course')#course属性值
[<p class="course">Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a> and <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>.</p>]
>>> soup.find_all(id='link1')
[<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>]
>>> soup.find_all(id='link')#找id属性为link的属性标签
[]
>>> soup.find_all(id=re.compile('link'))#正则表达式检索所有含有“link”的标签信息
[<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>, <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>]
>>> soup.find_all('a')
[<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>, <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">Advanced Python</a>]
>>> soup.find_all('a',recursive=False)#recursive=False表示只对儿子节点检索
[]
>>> soup.find_all(string="Basic Python")
['Basic Python']
>>> soup.find_all(string=re.compile("python"))#正则表达式找出含有python的语句
['This is a python demo page', 'The demo python introduces several python courses.']

总结