爬虫新练习

import requests
import re
from bs4 import BeautifulSoup

url="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res=requests.get(url)
res.encoding="utf-8"

url1="http://oa.gzcc.cn/api.php?op=count&id=9183&modelid=80"
res1=requests.get(url1)
print(res1.text.split(".html")[-1].lstrip("(‘").rstrip("‘);"))

newUrl =‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html‘
re1 = re.search(‘\_(.*).html‘,newUrl)
re2 = re.match(‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_(.*).html‘,newUrl)
print(re1.group(1).split(‘/‘)[-1],re2.group(1).split(‘/‘)[-1])