# -*- coding: UTF-8 -*- # vi:si:et:sw=4:sts=4:ts=4 import re from oxlib import cache from oxlib import findRe def getPosterUrls(imdbId): url = 'http://www.movieposterdb.com/movie/%s' % imdbId posterUrls = [] if cache.exists(url): posterUrls = parsePage(url) return posterUrls def parsePage(url): print url posterUrls = [] html = cache.getUrlUnicode(url, timeout=86400) groups = re.compile('', re.DOTALL).findall(html) print '%s Groups' % len(groups) for group in groups: posterUrls += parsePage(group) posters = re.compile('', re.DOTALL).findall(html) for poster in posters: print 'Poster: ' + poster html = cache.getUrlUnicode(poster) posterUrls.append(findRe(html, '"(http://www.movieposterdb.com/posters/.*?\.jpg)"')) return posterUrls if __name__ == '__main__': print getPosterUrls('0133093')