Python-сообщество

# -*- coding: utf-8 -*-
from grab import Grab
import time, random
g = Grab()
g.setup(hammer_mode=True, hammer_timeouts=((2, 5), (10, 15), (20, 30)))
a = 4
i = 0 
while a < 650:
    g.go('http://www.anekdotov-mnogo.ru/smeshnie_kartinki.php?page='+str(a), log_file='outpage.html')
    time.sleep(2)
    print 'page-' + str(a)
    for elem in g.doc.select("html/body/table/tbody/tr/td/div/p/img")[0:15]:
        img = elem.attr('src')
        print img 
        g.go('http://www.anekdotov-mnogo.ru/' + str(img))
        rand = random.randint(0, 9999)
        f = open("/home/montana/biz/python/tools/fotostrana/parser/umor/18.12.2014/" + str(rand)+ '-' + str(i) +".jpg", "wb")
        #print '%s' % (elem.attr('src'))
        f.write(img)
        f.close()
        print 'foto-'+str(i) 
        i = i + 1
        time.sleep(2) 
    a = a+1

# -*- coding: utf-8 -*-
import requests  
from lxml import html  
import sys  
import urlparse
a = 4
while a < 650:
    print 'page-'+str(a)
    response = requests.get('http://www.anekdotov-mnogo.ru/smeshnie_kartinki.php?page='+str(a))  
    parsed_body = html.fromstring(response.text)
# Парсим ссылки с картинками
    images = parsed_body.xpath('html/body/table/tbody/tr/td/div/p/img@src')  
    if not images:  
        sys.exit("Found No Images")
# Конвертирование всех относительных ссылок в абсолютные
    images = [urlparse.urljoin(response.url, url) for url in images]  
    print 'Found %s images' % len(images)
# Скачиваем только первые 10
    for url in images[0:15]:  
        r = requests.get(url)
        f = open('/home/montana/biz/python/tools/fotostrana/parser/umor/18.12.2014/%s' % url.split('/')[-1], 'w')
        f.write(r.content)
        f.close()
    a = a + 1 

from grab import Grab
def main():
    g = Grab()
    g.setup(hammer_mode=True, hammer_timeouts=((2, 5), (10, 15), (20, 30)))
    a = 4
    i = 0 
    while a < 650:
        g.go('http://www.anekdotov-mnogo.ru/smeshnie_kartinki.php?page=%s' % a)
        print ('page-%d' % a)
        for elem in g.doc.select('//div[@class="line_old_content"]/p/img/@src'):
            img_url = 'http://www.anekdotov-mnogo.ru%s' % elem.text().lstrip('.')
            g.go(img_url)
            g.response.save('%d.jpg' % i)
            print ('foto-%d' % i)
            i += 1
        a += 1
if __name__ == '__main__':
    main()