网络爬虫基础练习

import requests
newsurl = ‘http://localhost:56341/bd/123.html?_ijt=7pd1hi6n7j1ue90de4jivbr31k‘
res = requests.get(newsurl)  # 返回response对象
res.encoding = ‘utf-8‘
print(res.text)


from bs4 import BeautifulSoup
soup = BeautifulSoup(res.text, ‘html.parser‘)


# 取出a标签的链接
print(soup.a.attrs[‘href‘])
# 取出h1标签的文本
print(soup.h1.text)
# 取出所有li标签的所有内容
for i in soup.select(‘li‘):
     print(i.contents)

# 取出第4个li标签的a标签的第5个div标签的属性
print(soup.select(‘li‘)[3].a.select(‘div‘)[4].attrs)

# 取出一条新闻的标题、链接、发布时间、来源
print(‘标题：‘+soup.select(‘.news-list-title‘)[1].text)
print(‘链接：‘+soup.select(‘li‘)[1].a.attrs[‘href‘])
print(‘发布时间：‘+soup.select(‘.news-list-info‘)[0].contents[0].text)
print(‘来源：‘+soup.select(‘.news-list-info‘)[0].contents[1].text)