网络爬虫基础练习

import requests
from bs4 import BeautifulSoup
newsurl='http://localhost:63342/untitled/3/29.html?_ijt=ltocl4v68kb1po4608e3291lkm'
res=requests.get(newsurl)
res.encoding="utf-8"
soup=BeautifulSoup(res.text,'html.parser')
print(res.text)
print("1-----------------")
print(soup.div)
print("2-----------------")
print(soup.p) #标签名，返回第一个
print("3-----------------")
print(soup.head)
print("4-----------------")
print(soup.p.name) #字符串
print("5-----------------")
print(soup.p. attrs) #字典，标签的所有属性
print("6-----------------")
print(soup.p. contents) # 列表，所有子标签
print("7-----------------")
print(soup.p.text) #字符串
print("8-----------------")
print(soup.p.string)
print("9-----------------")
print(soup.select('li'))
print("10-----------------")
print(soup.select('#p1Node'))
print("11-----------------")
print(soup.select('.news-list-title'))
print("12-----------------")
#  取出h1标签的文本
print(soup.h1.text)
print("13-----------------")
# 取出a标签的链接
print(soup.a.attrs['href'])
print("14-----------------")
# 取出所有li标签的所有内容
for i in soup.select('li'):
    print(i.contents)

print("15-----------------")
print(soup.select('.news-list-title')[0].text)
print(soup.li.a.attrs['href'])
print(soup.select('.news-list-info')[0].contents[0].text)
print(soup.select('.news-list-info')[0].contents[1].text)