Initial commit

This commit is contained in:
Alexander Popov 2016-10-28 00:29:36 +03:00
commit bce6731494
5 changed files with 81 additions and 0 deletions

2
.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
.pip
*.jpg

24
LICENSE.txt Normal file
View File

@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org>

View File

@ -0,0 +1 @@
0

2
requirements.txt Normal file
View File

@ -0,0 +1,2 @@
requests==2.11.1
beautifulsoup4==4.5.1

52
stanis-tits.py Normal file
View File

@ -0,0 +1,52 @@
#!/usr/bin/env python3
import sys
sys.path.append('./.pip')
import requests
from bs4 import BeautifulSoup
import re
import shutil
import os.path
__author__ = 'Alexander Popov'
__version__ = '0.0.1'
__license__ = 'Unlicense'
IMAGES_DIR = './images'
COOKIES = dict(block='951')
URL = 'http://blog.stanis.ru/?back=%d'
PAGE = 0
with open('%s/.stanis-tits.latest' % IMAGES_DIR, 'r') as f:
LATEST_FILE = f.read()
STOP = False
NEXT_LATEST = None
while STOP == False:
print('Loading page %d' % PAGE)
r = requests.get(URL % PAGE, cookies=COOKIES)
soup = BeautifulSoup(r.text.encode('cp1251'),
"html.parser", from_encoding="windows-1251")
images = soup.findAll('img', src=re.compile('img/*'))
for image in images:
if int(image['src'].split('/')[1].split('.')[0]) == int(LATEST_FILE):
STOP = True
if PAGE == 0:
if NEXT_LATEST == None:
NEXT_LATEST = str(image['src'].split('/')[1].split('.')[0])
with open('%s/.stanis-tits.latest' % IMAGES_DIR, 'w+') as f:
f.write(NEXT_LATEST)
if not os.path.exists('%s/%s' % (IMAGES_DIR, image['src'].split('/')[1],)):
print('\tDownload %s' % image['src'].split('/')[1])
response = requests.get('http://blog.stanis.ru/%s' % image['src'], stream=True)
with open('%s/%s' % (IMAGES_DIR, image['src'].split('/')[1]), 'wb') as out_image:
shutil.copyfileobj(response.raw, out_image,)
PAGE += 1