BeautifulSoup4

BeautifulSoup4

是一个Python库，用于从HTML和XML文件中提取数据。它与您最喜欢的解析器一起使用，提供导航，搜索和修改解析树的惯用方法。它通常可以节省程序员数小时或数天的工作量。

安装BeautifulSoup4

pip install bs4

from bs4 import BeautifulSoup
from urllib import request
#获取网页内容
base_url = 'http://langlang2017.com/route.html'
response  = request.urlopen(base_url)
html = response.read()

#数据解析（从页面当中提取数据）
#创建bs4对象
soup = BeautifulSoup(html,'lxml')
#格式化输出对象中的内容
content = soup.prettify()

#提取页面当中的指定内容
# print(soup.title)  #获取title内容

#一  只能匹配到第一个标签内容
#1.tag(name)
# print(soup.name)   #输出文档类型
# print(soup.div.name) #输出标签名
#2attrs
# print(soup.title.attrs)
# print(soup.img.attrs)

#3修改属性值
img = soup.img.attrs
# print(img)
domain = 'http://www.langlang2017.com'
img["src"] = domain+ img["src"]
# print(img)

#4删除
img= soup.img.attrs
# print(img)
del  img["alt"]
# print(img)

#二
#1获取文本
# print(soup.title)
# print(soup.title.attrs)
# print(soup.title.name)
#格式：标签名.string
# print(soup.title.string)

#三 标签名.contents 获取子节点列表
head = soup.head.contents
# print(head)
# print(head[3])

#标签名.children  --子节点
head_children = soup.head.children
# for i in head_children:
    # print(i)

#便签名.descendants  --子孙节点
# print(soup.div)
# for i in soup.div.descendants:
#     print(i)

#搜索文档 find_all()
# print(soup.meta)  #只能获取一个
# for i in soup.find_all('meta'):
#     print(i)

#标签列表
# print(soup.find_all(["h1","h2"]))

#关键词
# print(soup.find_all(id='weixin'))

#四 css选择器 soup.select()
#通过类名查找
# print(soup.select('.logo'))
#通过标签名查找
# print(soup.select('a'))
#通过id查找
# print(soup.select('#weixin'))

运行报错

bs4.FeatureNotFound: Couldn't find a tree builder with the features you requested: lxml. Do you need
安装 lxml包
pip install lxml