iiiypuk/stanis-tits-scrap
iiiypuk/stanis-tits-scrap
1
0
Fork 0
Code Issues Pull Requests Projects Releases 2 Wiki Activity

rename variables

Browse Source
This commit is contained in:
Alexander Popov 2016-11-13 16:05:25 +03:00
parent 6d2397301b
commit 751040515b
1 changed files with 24 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
stanis-tits.py
View File

@ -3,12 +3,6 @@
import re import re
import shutil import shutil
import os.path import os.path
try:
import requests
from bs4 import BeautifulSoup
except ImportError:
import sys
sys.path.append('./.pip')
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
@ -16,46 +10,50 @@ __author__ = 'Alexander Popov'
__version__ = '0.1.0' __version__ = '0.1.0'
__license__ = 'Unlicense' __license__ = 'Unlicense'
IMAGES_DIR = './images' dwnImageDir = './images'
COOKIES = dict(block='951') cookies = dict(block='951')
URL = 'http://blog.stanis.ru/?back=%d' siteUrl = 'http://blog.stanis.ru/?back=%d'
PAGE = 0 imgPage = 0
if not os.path.exists('%s/.stanis-tits.latest' % IMAGES_DIR):
if not os.path.exists('%s' % IMAGES_DIR):
os.mkdir('%s' % IMAGES_DIR)
with open('%s/.stanis-tits.latest' % IMAGES_DIR, 'w') as f: # create .stanis-tits.latest file and download image directory
if not os.path.exists('%s/.stanis-tits.latest' % dwnImageDir):
if not os.path.exists('%s' % dwnImageDir):
os.mkdir('%s' % dwnImageDir)
with open('%s/.stanis-tits.latest' % dwnImageDir, 'w') as f:
f.write('0') f.write('0')
with open('%s/.stanis-tits.latest' % IMAGES_DIR, 'r') as f:
LATEST_FILE = f.read() with open('%s/.stanis-tits.latest' % dwnImageDir, 'r') as f:
latestDwnFile = f.read()
STOP = False STOP = False
NEXT_LATEST = None NEXT_LATEST = None
while STOP is False: while STOP is False:
print('Loading page %d' % PAGE) print('Loading page %d' % imgPage)
r = requests.get(URL % PAGE, cookies=COOKIES) r = requests.get(siteUrl % imgPage, cookies=cookies)
soup = BeautifulSoup(r.text.encode('cp1251'), soup = BeautifulSoup(r.text.encode('cp1251'),
"html.parser", from_encoding="windows-1251") "html.parser", from_encoding="windows-1251")
images = soup.findAll('img', src=re.compile('img/*')) images = soup.findAll('img', src=re.compile('img/*'))
for image in images: for image in images:
if image['src'].split('/')[1].split('.')[0] == LATEST_FILE: if image['src'].split('/')[1].split('.')[0] == latestDwnFile:
STOP = True STOP = True
if PAGE == 0: if imgPage == 0:
if NEXT_LATEST is None: if NEXT_LATEST is None:
NEXT_LATEST = str(image['src'].split('/')[1].split('.')[0]) NEXT_LATEST = str(image['src'].split('/')[1].split('.')[0])
with open('%s/.stanis-tits.latest' % IMAGES_DIR, 'w+') as f: with open('%s/.stanis-tits.latest' % dwnImageDir, 'w+') as f:
f.write(NEXT_LATEST) f.write(NEXT_LATEST)
if not os.path.exists('%s/%s' % (IMAGES_DIR, if not os.path.exists('%s/%s' % (dwnImageDir,
image['src'].split('/')[1],)): image['src'].split('/')[1],)):
print('\tDownload %s' % image['src'].split('/')[1]) print('\tDownload %s' % image['src'].split('/')[1])
response = requests.get('http://blog.stanis.ru/%s' response = requests.get('http://blog.stanis.ru/%s'
% image['src'], stream=True) % image['src'], stream=True)
with open('%s/%s' % (IMAGES_DIR, image['src'].split('/')[1]), with open('%s/%s' % (dwnImageDir, image['src'].split('/')[1]),
'wb') as out_image: 'wb') as out_image:
shutil.copyfileobj(response.raw, out_image,) shutil.copyfileobj(response.raw, out_image,)
PAGE += 1 imgPage += 1