利用它可以不用編寫正則表達式即可方便的實現網頁信息的提取。
pip3 install beautifulsoup4
用法講解：
常用解析庫：
lxml HTML解析器?
lxml XML解析器
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.prettify())? #格式化代碼
print(soup.title.string)
------------------------------------------------------------------
#標簽選擇器：
##選擇元素：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.title)
print(type(soup.title))
print(soup.head)
print(soup.p)
如果有很多滿足條件，只會輸出第一個。
##獲取名稱：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.title.name)
##獲取屬性：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.p.attrs['name'])#獲取name屬性的值
print(soup.p['name'])
##獲取內容:
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.p.string)
##嵌套選擇：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.head.title.string)
##1、子節點和子孫節點：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.p.children)#迭代器
for i,child in enumerate(soup.p.children):
? ? print(i,child)
##2
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.p.contents)#獲取p內的所有內容，列表
##3
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.p.descendants) #迭代器
for i,child in enumerate(soup.p.descendants):
? ? print(i,child)
##1、父節點和祖先節點：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.p.parent) #迭代器
##2
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(enumerate(list(soup.p.parents))) #迭代器
##兄弟節點
from bst import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(list(enumerate(soup.a.next_siblings)))
print(list(enumerate(soup.a.privious_siblings)))
------------------------------------------------------------------
#標準選擇器
find_all(name,attrs,recursive,text,**kwargs)
可根據標簽名、屬性、內容查找文檔
##name
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'html')
print(soup.find_all(''ul))
print(type(soup.find_all('ul')[0]))
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
for ul in soup.find_all('ul'):
????print(ul.find_all('li'))
##attrs
from bs4? import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.find_all(attrs={'id':'list-1'}))
print(soup.find_all(attrs = {'name':'element'}))
print(soup.find_all(id = 'list-1'))
print(soup.find_all(class_='element')) ##以上四句的輸出一樣
##text
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.find_all(text='Foo'))
#find(name,attrs,recursive,text,**kwargs)
返回單個元素.
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
print(soup.find('ul'))
print(type(soup.find('ul')))
print(soup.find('page'))
#find_parents()，find_parent()
find_next_siblings() find_next_sibling()
find_all_next()? find_next()
find_all_previous() find_previous()
#CSS選擇器??
通過select()直接傳入CSS選擇器即可完成選擇
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
pirnt(soup.select('.panel.panel-heading'))# class用.
print(soup.select('ul li'))
print(soup.select('#list-2.element'))
print(type(soup.select('ul')[0]))#
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
for ul in soup.select('ul'):
? ? print(ul.select('li'))
##獲取屬性
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
for ul in soup.select('ul'):? ? print(u['id'])
? ? print(ul.attrs['id'])
##獲取內容
from bs4 import BeautifulSoup
soup = BeautifulSoup(html,'lxml')
for ul in soup.select('li'):
? ? print(li.get_text())
#標簽選擇器
#標準選擇器
#CSS選擇器
總結：
?* 推薦使用lxml解析庫,必要使用html.parser
?* 標簽選擇篩選功能弱但是速度快。
?* 建議使用find()，find_all()查詢匹配單個結果或者多個結果。
?* 如果對CSS選擇器熟悉可以使用select()
?* 記住常用的獲取屬性和文本值的方法。
)
