Last active
December 1, 2018 12:14
-
-
Save ShapeLayer/f5dace144c54555c7c5f65ef532ddceb to your computer and use it in GitHub Desktop.
Image scrapper
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
import urllib.request | |
import re | |
import datetime | |
title = re.compile(r'<title>(?P<title>(.*?))<\/title>') | |
regex = re.compile(r'<img[^>]*src="(?P<src>[0-9a-zA-Zㄱ-ㅣ가-힣(?=.*[!@#$%^*()\-_=+\\\|\[\]{};:\'",.<>\/?]*)"[^>]*>') | |
re_ext = re.compile(r'\.(bmp|gif|jpg|jpeg|png)$') | |
target = input() | |
req = urllib.request.Request(target, headers={'User-Agent': 'Mozilla/5.0'}) | |
scrap = urllib.request.urlopen(req).read().decode('utf-8') | |
titleobj = title.search(scrap).group('title') | |
print('불러왔습니다: {}'.format(titleobj)) | |
matchobj = regex.findall(scrap) | |
print('{}개 이미지 찾음: {}'.format(len(matchobj), titleobj)) | |
for i in range(len(matchobj)): | |
print('{} 다운로드중..'.format(matchobj[i])) | |
try: | |
exten = re_ext.search(matchobj[i]).group() | |
urllib.request.urlretrieve(matchobj[i], '{}-{}{}'.format(titleobj, i+1, exten)) | |
print('Done. {}/{}'.format(i+1, len(matchobj))) | |
except: | |
print('Failed. {}/{}'.format(i+1, len(matchobj))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment