python 爬网页

原创于 2020-08-21 11:14:22 发布 · 180 阅读

0 ·

CC 4.0 BY-SA版权

python 同时被 2 个专栏收录

3 篇文章

订阅专栏

爬虫

2 篇文章

订阅专栏

import requests
import re

url = 'https://blog.youkuaiyun.com/jidawanghao/article/details/108092545'
htmlfile = requests.get(url)
if htmlfile.status_code==requests.codes.ok:
  pattern = input("请输入欲搜寻的字符串：")
  if  pattern in htmlfile.text:
      print("搜寻 %s 成功 "% pattern)
  else:
      print("搜寻 %s 失败" % pattern)

  name = re.findall(pattern,htmlfile.text)
  if name !=None:
      print("%s 出现 %d 次"  % (pattern,len(name)))
  else:
      print("%s 出现  0次  "% pattern)
else:
    print("网页下载失败")