王明昌博客|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 |
import requests; import re; import os; import parsel; # 1.请求网页 header = { "user-agent":'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36' } response = requests.get('https://www.doutula.com/photo/list/',headers=header) html = response.text # 2.解析网页 selector = parsel.Selector(html) # print(selector) dir_name = 'doutu_list' if not os.path.exists(dir_name): os.mkdir(dir_name) result_list = selector.xpath('//a[@class="col-xs-6 col-sm-3"]') for result in result_list: title = result.xpath('./img/@alt').get() img_url = result.xpath('./img/@data-original').get() ext = img_url.split('.')[-1] file_name = title+'.'+ext print(title,img_url) # 保存 response = requests.get(img_url,headers=header) with open(dir_name+'/'+file_name,'wb') as f: f.write(response.content) |
python 采集斗图啦xpath
未经允许不得转载：王明昌博客 » python 采集斗图啦xpath
