1.获取古诗文网网页内容**
import requests
url=’http://www.gushiwen.com/‘
r=requests.get(url)
r.encoding=’UTF-8’
print(type(r))
print(r.status_code)
print(type(r.text))
print(r.text)
print(r.cookies)

2.下载古诗文网logo
import requests
from PIL import Image
r=requests.get(“https://www.gushiwen.com/tpl/static/images/allico.png”))
with open(‘allico.png’,’wb’)as f:
f.write(r.content)
im=Image.open(‘allico.png’)
im.show()
![}I%UG0QWKJNUHGFHOSJ8BW.png

import requests
from PIL import Image
r=requests.get(“http://www.siso.edu.cn/dfiles/11358/upload/xc.png”))
with open(‘xc.png’,’wb’)as f:
f.write(r.content)
im=Image.open(‘xc.png’)
im.show()

3.BeautifulSoup4解析网页
from bs4 import BeautifulSoup
soup=BeautifulSoup(‘

Hello

BeautifulSoup

from bs4 import BeautifulSoup
html=”””

html=”””

一年有四个季节：



• 春天<>
  
• 夏天<>
  
• 秋天<>
  
• 冬天<>”””
  
  使用fing_all获取节点
  from bs4 import BeautifulSoup
  soup=BeautifulSoup(html,’lxml’)

  # 方法一：找出所有季节
  print(soup.findall(‘a’)[0].string)
  print(soup.find_all(‘a’,class=’season’)[1].string)
  print(soup.findall(‘a’,{‘class’:’season’})[2].string)
  print(soup.find_all(‘a’,attrs={‘class’:’season’})[3].string)
  

  # 方法二：精确定位
  # print(soup.find_all(‘a’,id=’summer’)[0].string)
  # print(soup.find_all(‘a’,href=’summer.html’)[0].string)
  # print(soup.find_all(‘a’,{‘id’:’summer’})[0].string)
  # print(soup.find_all(‘a’,{‘href’:’summer.html’})[0].string)
  # print(soup.find_all(string=’夏天’)[0].string)

  css选择获取节点
  print(soup.select(‘a’)[0].string)
  print(soup.select(‘ul a’)[2].string)
  print(soup.select(‘.season’)[3].string)
  print(soup.select(‘.red’)[0].string)
  print(soup.select_one(‘.red’).string)
  print(soup.select(‘ul .season’)[3].string)
  print(soup.select(‘#summer’)[0].string)
  print(soup.select(‘li > .season’)[2].string)
  print(soup.select(‘ul > li’)[2].string)

  from bs4 import BeautifulSoup
  soup = BeautifulSoup(‘

  Hello

  BeautifulSoup

  ‘,’lxml’)
  print(soup)
  print(soup.p)
  print(soup.p.name)
  print(soup.p.string)

  html=”””

• 春天
“””soup=BeautifulSoup(html,’lxml’)
print(soup.a.string)
print(soup.li.string)
print(soup.a[‘href’])
print(soup.a[‘class’])
print(soup.a.attrs)