#coding:utf-8
from lxml import etree
import requests
header={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'+
'Chrome/67.0.3396.87 Safari/537.36'
}
urls=['http://konachan.com/post?page={}&tags='.format(str(i))
for i in range(1,2)]
path='E://K/'
for url in urls :
res=requests.get(url)
selector=etree.HTML(res.text)
second_urls=selector.xpath('//ul[@id="post-list-posts"]/li')
for second_url in second_urls:
second_url_nums=second_url.xpath('div/a')
for second_url_num in second_url_nums :
new_url = second_url_num.xpath('@href')[0]
new_url='http://konachan.com'+str(new_url)
new_res=requests.get(new_url)
new_selector=etree.HTML(new_res.text)
new_second_urls=new_selector.xpath('//*[@id="image"]')
img_src = new_second_urls[0].xpath('@src')[0]
data=requests.get(img_src,headers=header)
fp=open(path+new_url.split('/')[-1]+'.'+img_src.split('.')[-1],'wb')
fp.write(data.content)
fp.close()
可以设置页数,range(m,n)
可以修改路径path,运行时需要首先建好文件夹,例如E://K/