|

楼主 |
发表于 2019-12-6 16:32:24
|
显示全部楼层
import requests
import re
for j in range(56730,57947):
x1 = str(j)
url = 'https://www.rzlib.net/b/0/83/{0}.html'.format(x1)
res = requests.get(url,headers={'User-Agent': 'User-Agent:Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'})
res.encoding = res.apparent_encoding
s1 = res.text
s2 = re.findall(' (.*?)<br /><br />',s1,re.S)
s3 = ''
s4 = re.findall('<title>(.*?)</title>',s1,re.S)
for i in s2:
s3 = s3+i
file_handle = open(s4[0]+'.txt',mode='w+',encoding='utf-8')
file_handle.write(s3)
file_handle.close()
麻烦各位帮忙看看,谢啦 |
|