python爬虫之—中国工程院信息

import requests
import re

url = 'http://www.cae.cn/cae/html/main/col48/column_48_1.html'

html = requests.get(url) #获取网页源代码

html.encoding = 'utf-8'  #编码格式

nuber = re.findall(r'<a href="/cae/html/main/colys/(\d+).html" target="_blank">',html.text)

for n in nuber[:2]:
    nextUrl = 'http://www.cae.cn/cae/html/main/colys/{}.html'.format(n) #获取所有url
    text = requests.get(nextUrl)
    text.encoding = 'utf-8'
    text2 = re.findall('<div class="intro">(.*?)</div>',text.text,re.S) #正则表达式
    text3 = re.sub(r'&ensp;|<p>|&nbsp;|</p>','',text2[0]).strip()  #去掉特殊字符
    print(text3)
    with open(r'C:\Users\Administrator\Desktop\888.txt',mode= 'a+') as f: #指定文件路径，追加格式
        f.write(text3 + '\n'*2)  #写入文件