网络爬虫基础练习

import requests
from bs4 import BeautifulSoup
res = requests.get('https://www.cnblogs.com/')
res.encoding = 'UTF-8'
soup = BeautifulSoup(res.text, 'html.parser')

# 取出h1标签的文本
for h1 in soup.find_all('h1'):
    print(h1.text)
# 取出a标签的链接
for a in soup.find_all('a'):
    print(a.attrs.get('href'))
# 取出所有li标签的所有内容
for li in soup.find_all('li'):
    print(li.contents)
# 取出第2个li标签的a标签的第3个div标签的属性
print(soup.find_all('li')[1].a.find_all('div')[2].attrs)

# 取出一条新闻的标题、链接、发布时间、来源
print(soup.select('div .news-list-title')[0].text)
print(soup.select('div .news-list-thumb')[0].parent.attrs.get('href'))
print(soup.select('div .news-list-info > span')[0].text)
print(soup.select('div .news-list-info > span')[1].text)