python爬虫——BeautifulSoup基础操作

最新推荐文章于 2024-08-12 23:17:41 发布

Nani_xiao

最新推荐文章于 2024-08-12 23:17:41 发布

阅读量1.4k

点赞数

分类专栏： Python 文章标签： python

本文链接：https://blog.csdn.net/xiao_lxl/article/details/77374426

版权

Python 专栏收录该内容

31 篇文章 3 订阅

订阅专栏

安装好BeautifulSoup4和Jupyter之后，在cmd中输入jupyter notebook 运行，会直接跳转到网页jupyter编辑器中。

import requests
newsurl = "http://news.sina.com.cn/china/"
res = requests.get(newsurl)
res.encoding = 'utf-8'
print(res.text)

from bs4 import BeautifulSoup
html_sample = ' \
<html> \
 <body>  \
 <h1 id="title">Hello World</h1> \
 <a href="#" class="link"> This is link1</a> \
 <a href="# link2" class="link"> This is link2</a> \
 </body> \
 </html> ' 

soup = BeautifulSoup(html_sample, 'html.parser')
print(soup.text)

from bs4 import BeautifulSoup
html_sample = ' \
<html> \
 <body>  \
 <h1 id="title">Hello World</h1> \
 <a href="#" class="link"> This is link1</a> \
 <a href="# link2" class="link"> This is link2</a> \
 </body> \
 </html> ' 

soup = BeautifulSoup(html_sample, 'html.parser')
header = soup.select('h1')
#print(type(soup))
print(header)

#使用select找出含有‘h1’标签的词
from bs4 import BeautifulSoup
html_sample = ' \
<html> \
 <body>  \
 <h1 id="title">Hello World</h1> \
 <a href="#" class="link"> This is link1</a> \
 <a href="# link2" class="link"> This is link2</a> \
 </body> \
 </html> ' 

soup = BeautifulSoup(html_sample, 'html.parser')
header = soup.select('h1')
#print(type(soup))
print(header)
print(header[0])
print(header[0].text)

from bs4 import BeautifulSoup
html_sample = ' \
<html> \
 <body>  \
 <h1 id="title">Hello World</h1> \
 <a href="#" class="link"> This is link1</a> \
 <a href="# link2" class="link"> This is link2</a> \
 </body> \
 </html> ' 

soup = BeautifulSoup(html_sample, 'html.parser')
alink = soup.select('a')
#print(type(soup))
print(alink)
for link in alink:
    print(link)
    print(link.text)

from bs4 import BeautifulSoup
html_sample = ' \
<html> \
 <body>  \
 <h1 id="title">Hello World</h1> \
 <a href="#" class="link"> This is link1</a> \
 <a href="# link2" class="link"> This is link2</a> \
 </body> \
 </html> ' 
soup = BeautifulSoup(html_sample, 'html.parser')
alink = soup.select('#title')
print(alink)
for link in soup.select('.link'):
    print(link)

alinks = soup.select('a')
for link in alinks:
    print(link['href'])

a =  '<a href="#" qoo=123, abc=456> I am a  link</a>'
soup2 = BeautifulSoup(a, 'html.parser')
print(soup2.select('a')[0]['qoo'])
print(soup2.select('a')[0]['abc'])
print(soup2.select('a')[0]['href'])