Last active
November 15, 2017 02:08
-
-
Save cnDelbert/96881e8d0c2a9bb072db to your computer and use it in GitHub Desktop.
一个简单的unsplash全站下载脚本。 使用Python3及BeautifulSoup4。
This file contains 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
# -*- coding:utf-8 -*- | |
__author__ = 'Delbert' | |
# Using Python3 | |
# beautifulsoup4 is needed. | |
from bs4 import BeautifulSoup | |
from urllib import request | |
import os | |
def main(): | |
begin_page = int(input("From: ")) | |
end_page = int(input("To: "))+1 | |
for page in range(begin_page, end_page): | |
url = "https://unsplash.com/?page=%s" %page | |
print(url) | |
data = BeautifulSoup(request.urlopen(url)) | |
a_link = data.find_all("a", text="Download") | |
for d_link in a_link: | |
id = str(d_link).split('/')[2] | |
if(os.path.exists("./unsplash/"+id+".jpg") and (os.path.getsize("./unsplash/"+id+".jpg") > 0)): | |
continue | |
else: | |
print("Downloading pic: "+id+".jpg ... ", end="") | |
f = open("./unsplash/"+id+".jpg", "wb") | |
id_url = "https://unsplash.com/photos/"+id+"/download" | |
f.write(request.urlopen(id_url).read()) | |
f.close() | |
print("Done") | |
if __name__ == '__main__': | |
if(not os.path.exists('./unsplash/')): | |
os.mkdir("./unsplash/") | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
貌似现在用不了了。。。