|
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
原始代码如下:
截图:
import urllib.request
import os
def url_open(url):
req=urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36')
response=urllib.request.urlopen(url)
html=response.read()
def get_page(url):
html=url_open(url).decode('utf-8')
a=html.find("current-comment-page")+23
b=html.find(']',a)
return html[a:b]
def find_imgs(url):
html=url_open(url).decode('utf-8')
img_addres=[]
a=html.find('img src=')
while a!=-1:
b=html.find('.jpg',a,a+255)
if b!=-1:
img_addres.append(html[a+9:b+4])
else:
b=a+9
a=html.find('img src=',b)
return img_addres
def save_imgs(folder,img_addrs):
for each in img_addrs:
filename=each.split('/')[-1]
with open(filename,'wb') as f:
img=url_open(each)
f.write(img)
def download_mm(folder='xxoo',pages=5):
os.mkdir(folder)
os.chdir(folder)
url='http://jandan.net/ooxx/'
page_num=int(get_page(url))
page_url=url+'page-'+str(page_num)+'#comments'
img_addrs=find_imgs(page_url)
save_imgs(folder,img_addrs)
if __name__=='__main__':
download_mm()
反爬了,光加user- 是没用的。换网站练吧。别问有什么办法;技术还没有到家。先学着
|
|