import requests
import re
url='http://588ku.com/png-zhuanti/'
head={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
html=requests.get(url,headers=head)
Sum=re.findall('<!-- 专题列表 -->(.*?)>下一页<',html.text,re.S)
txt=''.join(Sum)
#print(txt)
TxT=re.findall('''<em class="number-icon">(.*?)</div></div><div class="''',txt,re.S)
filename='D:\\python文件\\Python爬虫.txt'
file=open(filename,'w')
for each in TxT:
page=re.findall('''class="number-info">(.*?)</div></div><em class="st-icon">''',each,re.S)
name=re.findall('''target="_blank">(.*?)</a></h2>''',each,re.S)
file.write('图片的名称:'+''.join(name)+'\n')
file.write('图片的张数:'+''.join(page)+'\n\n')
file.close()
print(len(TxT))
print(TxT)
正则表达式实例
最新推荐文章于 2025-05-27 22:20:26 发布