【模块】：BeautifulSoup
BeautifulSoup
BeautifulSoup是一个模块，该模块用于接收一个HTML或XML字符串，然后将其进行格式化，之后遍可以使用他提供的方法进行快速查找指定元素，从而使得在HTML或XML中查找指定元素变得简单
1、安装：
pip3 install beautifulsoup4 pip install lxml # python2.x
2、简单使用：
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
asdf
<div class="title">
<b>The Dormouse's story总共</b>
<h1>f</h1>
</div>
<div class="story">Once upon a time there were three little sisters; and their names were
<a class="sister0" id="link1">Els<span>f</span>ie</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.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
# soup = BeautifulSoup(html_doc, features="lxml")
soup = BeautifulSoup(html_doc, features="html.parser") # 等同于上面
# 找到第一个a标签
tag1 = soup.find(name='a')
# 找到所有的a标签
tag2 = soup.find_all(name='a')
# 找到id＝link2的标签
tag3 = soup.select('#link2')
print(tag1)
print(tag2)
print(tag3)
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
# [<a class="sister0" id="link1">Els<span>f</span>ie</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>]
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
3、标签方法：
① name标签名称
# name
tag = soup.find('a')
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
name = tag.name # 获取
print(name) # a
tag.name = 'span' # 设置 替换第一个a标签为span标签
print(soup)
② attrs标签属性
# attrs
tag = soup.find('a')
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
attrs = tag.attrs # 获取
print(attrs)
# {'class': ['sister0'], 'id': 'link1'}
tag.attrs = {'ik':123} # 设置属性
tag.attrs['id'] = 'iiiii' # 更改id
print(soup)
③ children所有子标签
# 子标签，只是获取儿子
tag = soup.find('a')
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
v = tag.children
print(v)
# <list_iterator object at 0x02E71230>
for i in v:
print(i)
# Els
# <span>f</span>
# ie
④ descendants子子孙孙标签
# 获得子子孙孙
body = soup.find('body')
v = body.descendants
print(v)
for i in v:
print(i)
⑤ clear将标签的所有子标签全部清空（保留标签名）
# 清空表签内容
tag = soup.find('body')
tag.clear()
print(soup)
# <html><head><title>The Dormouse's story</title></head>
# <body></body>
# </html>
⑥ decompose,递归的删除所有的标签
# 递归的删除所有的标签
body = soup.find('body')
body.decompose()
print(soup)
# <html><head><title>The Dormouse's story</title></head>
#
# </html>
⑦ extract递归的删除所有的标签，并获取删除的标签
# 递归的删除所有的标签，并获取删除的标签
body = soup.find('body')
v = body.extract()
print(soup)
# <html><head><title>The Dormouse's story</title></head>
#
# </html>
print(v,type(v))
# <body>
# asdf
# <div class="title">
# <b>The Dormouse's story总共</b>
# <h1>f</h1>
# </div>
# <div id="story">Once upon a time there were three little sisters; and their names were
# <a class="sister0" id="link1">Els<span>f</span>ie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a> and
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>;
# and they lived at the bottom of a well.</div>
# ad<br/>sf
# <p class="story">...</p>
# </body> <class 'bs4.element.Tag'>
⑧ decode转换为字符串（含当前标签）；decode_contents（不含当前标签）
# 转换为字符串
tag = soup.find('a')
v1 = tag.decode()
print(v1)
v2 = tag.decode_contents()
print(v2)
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
# Els<span>f</span>ie
⑨ find获取匹配的第一个标签
# find使用
tag = soup.find('a')
print(tag)
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie') # recursive子子孙孙中去找
print(tag)
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tag)
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
⑩ find_all获取匹配的所有标签
####### 单标签 #######
tags = soup.find_all('a')
print(tags)
# [<a class="sister0" id="link1">Els<span>f</span>ie</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>]
tags = soup.find_all('a',limit=1)
print(tags)
# [<a class="sister0" id="link1">Els<span>f</span>ie</a>]
tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
print(tags)
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
####### 列表 #######
v = soup.find_all(name=['a','div']) # 获取所有的a标签和div标签，列表形式
print(v)
v = soup.find_all(class_=['sister0', 'sister']) # 所有class是sister0和sister的标签
print(v)
# [<a class="sister0" id="link1">Els<span>f</span>ie</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>]
v = soup.find_all(text=['Tillie']) # 获取到匹配的内容非标签
print(v, type(v[0]))
# ['Tillie'] <class 'bs4.element.NavigableString'>
v = soup.find_all(id=['link1','link2']) # 获取多个id
print(v)
# [<a class="sister0" id="link1">Els<span>f</span>ie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
v = soup.find_all(href=['link1','link2']) # 获取多个href
print(v)
# []
# ####### 正则 #######
import re
rep = re.compile('p')
rep = re.compile('^p')
v = soup.find_all(name=rep)
print(v)
rep = re.compile('sister.*')
v = soup.find_all(class_=rep)
print(v)
rep = re.compile('http://www.oldboy.com/static/.*')
v = soup.find_all(href=rep)
print(v)
####### 方法筛选 #######
def func(tag):
return tag.has_attr('class') and tag.has_attr('id')
v = soup.find_all(name=func)
print(v)
# [<a class="sister0" id="link1">Els<span>f</span>ie</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>]
## get,获取标签属性
tag = soup.find('a')
v = tag.get('id')
print(v)
# link1
⑪ has_attr检查标签是否具有该属性
# 标签是否具有该属性
tag = soup.find('a')
v = tag.has_attr('id')
print(v)
# True
⑫ get_text获取标签内部文本内容
# 获取标签内部文本内容
tag = soup.find('a')
# <a class="sister0" id="link1">Els<span>f</span>ie</a>
v = tag.get_text('##') # 以##进行分割
print(v)
# Els##f##ie
⑬ index检查标签在某标签中的索引位置
# 获取标签所在的索引，从0开始
tag = soup.find('body')
v = tag.index(tag.find('div'))
print(v)
# 1
tag = soup.find('body')
for i,v in enumerate(tag):
print(i,v)
⑭ is_empty_element,是否是空标签(是否可以是空)或者自闭合标签， 判断是否是如下标签：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
# 是否是空标签
tag = soup.find('br')
v = tag.is_empty_element
print(v)
# True
⑮ 当前的关联标签
soup.next soup.next_element soup.next_elements soup.next_sibling soup.next_siblings tag.previous tag.previous_element tag.previous_elements tag.previous_sibling tag.previous_siblings tag.parent tag.parents
⑯ 查找某标签的关联标签
tag.find_next(...) tag.find_all_next(...) tag.find_next_sibling(...) tag.find_next_siblings(...) tag.find_previous(...) tag.find_all_previous(...) tag.find_previous_sibling(...) tag.find_previous_siblings(...) tag.find_parent(...) tag.find_parents(...) 参数同find_all
⑰ elect,select_one, CSS选择器
soup.select("title") soup.select("p nth-of-type(3)") soup.select("body a") soup.select("html head title") tag = soup.select("span,a") soup.select("head > title") soup.select("p > a") soup.select("p > a:nth-of-type(2)") soup.select("p > #link1") soup.select("body > a") soup.select("#link1 ~ .sister") soup.select("#link1 + .sister") soup.select(".sister") soup.select("[class~=sister]") soup.select("#link1") soup.select("a#link2") soup.select('a[href]') soup.select('a[href="http://example.com/elsie"]') soup.select('a[href^="http://example.com/"]') soup.select('a[href$="tillie"]') soup.select('a[href*=".com/el"]') from bs4.element import Tag def default_candidate_generator(tag): for child in tag.descendants: if not isinstance(child, Tag): continue if not child.has_attr('href'): continue yield child tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator) print(type(tags), tags) from bs4.element import Tag def default_candidate_generator(tag): for child in tag.descendants: if not isinstance(child, Tag): continue if not child.has_attr('href'): continue yield child tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1) print(type(tags), tags)
⑱ 标签的内容
tag = soup.find('span')
print(tag.string) # 获取
tag.string = 'new content' # 设置
print(soup)
tag = soup.find('body')
print(tag.string)
tag.string = 'xxx'
print(soup)
tag = soup.find('body')
v = tag.stripped_strings # 递归内部获取所有标签的文本
print(v)
⑲ append在当前标签内部追加一个标签
tag = soup.find('body')
v = tag.stripped_strings # 递归内部获取所有标签的文本
print(v)
tag = soup.find('body')
tag.append(soup.find('a'))
print(soup)
from bs4.element import Tag
obj = Tag(name='i',attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
tag.append(obj)
print(soup)
⑳ insert在当前标签内部指定位置插入一个标签
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
tag.insert(2, obj)
print(soup)
㉑ insert_after,insert_before 在当前标签后面或前面插入
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
# tag.insert_before(obj)
tag.insert_after(obj)
print(soup)
㉒ replace_with 在当前标签替换为指定标签
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('div')
tag.replace_with(obj)
print(soup)
㉓ 创建标签之间的关系
tag = soup.find('div')
a = soup.find('a')
tag.setup(previous_sibling=a)
print(tag.previous_sibling)
㉔ wrap将指定标签把当前标签包裹起来
from bs4.element import Tag
obj1 = Tag(name='div', attrs={'id': 'it'})
obj1.string = '我是一个新来的'
tag = soup.find('a')
v = tag.wrap(obj1)
print(soup)
tag = soup.find('a')
v = tag.wrap(soup.find('p'))
print(soup)
㉕ unwrap，去掉当前标签，将保留其包裹的标签
tag = soup.find('a')
v = tag.unwrap()
print(soup)
