Skip to content

Instantly share code, notes, and snippets.

@naspeh
Created February 16, 2011 10:18
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save naspeh/bc258429fee09f4d7c32 to your computer and use it in GitHub Desktop.
Save naspeh/bc258429fee09f4d7c32 to your computer and use it in GitHub Desktop.
dimetris-hack.py
'''
Need install mechanize::
easy_install mechanize
'''
import re
import mechanize
cookies = mechanize.CookieJar()
br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
br.addheaders = [("User-agent", "Mozilla/5.0 (compatible; MyProgram/0.1)"),]
count = 10
user = 'nayavu'
host = 'http://dimetris.ru'
main_url = '/flowers/new/%s' % user
item_url = '/flower_new/%s/' % user
def get_photos(page_url):
rv = br.open(host + page_url).read()
photos = re.findall(r'%s.*?\/\d+' % re.escape(item_url), rv)
return photos or []
def get_photos_by_pages():
rv = br.open(host + main_url).read()
pages = set(re.findall(r'%s\?page=\d+' % re.escape(main_url), rv))
photos = []
for page in pages:
photos += get_photos(page)
return photos
def go_to_photos(photos):
br = mechanize.Browser()
for photo in photos:
print photo
br.open(host + photo)
photos = get_photos_by_pages()
for i in xrange(count):
print '%s>>>' % (i + 1)
go_to_photos(photos)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment