xhamster_gal.py

import requests
import bs4
import re
import sys

def main():
    requests.packages.urllib3.disable_warnings()
    hedr = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:49.0) Gecko/20100101 Firefox/49.0'}
    if len(sys.argv) == 1:
        print 'Argument required'
        return 1
    gal_url = str(sys.argv[1])
    rr = re.findall('http.+xhamster.com/photos/gallery/[0-9]+/(.+).html', gal_url)
    if len(rr) < 1:
        print 'Not xhamster gallery url'
        return 1
    r = requests.get(gal_url, headers = hedr)
    soup = bs4.BeautifulSoup(r.text, 'lxml')
    z = soup.find_all('div', {'class': 'gallery iItem '})
    list_images = list()
    page = 1
    while len(z) > 0:
        print 'Processing page', page
        sys.stdout.flush()
        for divim in z:
            alnk = divim.find('a')
            list_images.append(str(alnk['href']))
        page += 1
        r = requests.get(gal_url+'?page='+str(page), headers = hedr)
        soup = bs4.BeautifulSoup(r.text, 'lxml')
        z = soup.find_all('div', {'class': 'gallery iItem '})
    print 'Found %i images' % len(list_images)
    sys.stdout.flush()
    for i in xrange(len(list_images)):
        print 'Downloading image', i+1,
        sys.stdout.flush()
        try:
            r = requests.get(list_images[i], headers = hedr)
            soup = bs4.BeautifulSoup(r.text, 'lxml')
            z = soup.find('img', {'id': 'imgSized', 'class': 'slideImg'})
            r = requests.get(z['src'], headers = hedr)
            f = open(str(rr[0])+'_'+str(i+1)+'.'+str(z['src'].split('.')[-1]), 'wb')
            f.write(r.content)
            f.close()
        except KeyboardInterrupt:
            raise KeyboardInterrupt
        except:
            print 'Fail:', sys.exc_info()[1]
            continue
        print 'OK'
        sys.stdout.flush()
    return 0

if __name__ == '__main__':
    main()