Created
January 15, 2017 03:35
-
-
Save MingqianYang/45dc1daabc50f1fb0096565ec7cff477 to your computer and use it in GitHub Desktop.
download_mmpicture
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib.request | |
import os | |
import random | |
def url_open(url): | |
req = urllib.request.Request(url) | |
req.add_header('User-Agent','Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.75 Safari/537.36 QQBrowser/4.1.4132.400') | |
proxies = ['210.245.189.110:80', '121.224.200.248:8998', '124.206.209.244:3128'] | |
proxy = random.choice(proxies) | |
proxy_support = urllib.request.ProxyHandler({'http':proxy}) | |
opener = urllib.request.build_opener(proxy_support) | |
urllib.request.install_opener(opener) | |
response = urllib.request.urlopen(url) | |
html = response.read() | |
#print(url) | |
return html | |
def get_page(url): | |
html = url_open(url).decode('utf-8') | |
a = html.find('current-comment-page') + 23 | |
b = html.find(']', a) | |
#print(html[a:b]) | |
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(html[a+9:b+4]) | |
else: | |
b = a + 9 | |
a = html.find('img src=',b) | |
return img_addrs | |
# for each in img_addrs: | |
# print(each) | |
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 = 'ooxx', pages = 10): | |
#os.mkdir(folder) | |
isexist = os.path.exists(folder) # judge the spicific folder is exist | |
if isexist == False: # if not exist | |
print(isexist) | |
os.makedirs(folder) # then make the corresponding 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_addrs) | |
if __name__ == '__main__': | |
download_mm() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment