|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
language="javascript">
setTimeout("location.replace(location.href.split(\"#\")[0
import urllib.request
import os
def get_page(url):
req =urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36')
response = urllib.request.urlopen(url)
html=response.read().decode('utf-8')
a = html.find('current-comment-page')+23
b = html.find(']',a)
print (html[a:b])
def find_imgs(url):
pass
def download_mm(folder='ooxx',pages=10):
os.mkdir(folder)
os.chdir(folder)
url = 'http://jandan.net/ooxx'
page_num = int(get_page(url))
for i in range(pages):
page_num -= i
page_url = url +'/page-'+str(page_num) +'#comments'
img_addrs=find_imgs(page_url)
save_imgs(folder,img_addres)
if __name__=='__main__':
download_mm()
|
|