|
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
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/51.0.2704.79 Safari/537.36 Edge/14.14393')
response = urllib.request.urlopen(req)
html = response.read()
return html
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_addrs = []
a = html.find('img src=')
while a != -1:
b = html.find('.jpg',a,a+255)
if b !=-1:
img_addrs.append('http:'+html[a+9:b+4])
else:
b = a+9
a = html.find('img src=',b)
return img_addrs
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 (folder = 'F:\\pic\\meimei',pages=200):
#os.mkdir(folder)#创建meimei的文件夹
os.chdir(folder)#将当前工作目录更改为meimei文件夹下
url = 'http://jiandan.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_addrs)
if __name__=='__main__':
download()
|
评分
-
查看全部评分
|