tata.py 文件源码

def __search_movie(self, imdb, year):
        try:
            query = urlparse.urljoin(self.base_link, self.search_link % imdb)

            y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']

            r = client.request(query)

            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'container'})
            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'ml-item-content'})
            r = [(dom_parser.parse_dom(i, 'a', attrs={'class': 'ml-image'}, req='href'), dom_parser.parse_dom(i, 'ul', attrs={'class': 'item-params'})) for i in r]
            r = [(i[0][0].attrs['href'], re.findall('calendar.+?>.+?(\d{4})', ''.join([x.content for x in i[1]]))) for i in r if i[0] and i[1]]
            r = [(i[0], i[1][0] if len(i[1]) > 0 else '0') for i in r]
            r = sorted(r, key=lambda i: int(i[1]), reverse=True)  # with year > no year
            r = [i[0] for i in r if i[1] in y][0]

            url = urlparse.urlparse(r).path
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return