爬虫，爬取中国工程院院士信息

爬虫，爬取中国工程院院士信息"/>

爬虫，爬取中国工程院院士信息

爬虫，爬取中国工程院院士信息：

import os
import re
from urllib.request import urlopendirname='yuanshi'
if not os.path.isdir(dirname):os.mkdir(dirname)
os.chdir(dirname)
dirname=os.getcwd()url=r'.html'
with urlopen(url) as fp:content=fp.read().decode()pattern=r'<li class=".*?"><a href="(.+?)" target=".*?">(.+?)</a></li>'content=re.findall(pattern,content)for url,name in content:os.chdir(dirname)print("正在载入%s的信息，waiting....."%name)if not os.path.isdir(name):os.mkdir(name)os.chdir(name)url=r''+urlwith urlopen(url) as fp:txt=fp.read().decode()pattern=r'<img src="(.+?)" style=".*?"/>'pic=re.findall(pattern,txt)pic=pic[0].replace(' ',r'%20')pic=r''+picwith open(name+'.jpg','wb') as fp:fp.write(urlopen(pic).read())pattern=r'<p>(.+?)</p>'info=re.findall(pattern,txt)info='\n'.join(info)pattern=r'<a.+?</a>|(&ensp;)|(&nbsp;)'info=re.sub(pattern,'',info)with open(name+'.txt','w',encoding='utf8') as fp:fp.write(info)print('信息读取完毕')