fullstream.py 文件源码

def __search(self, titles, year, season='0'):
        try:
            query = urlparse.urljoin(self.base_link, self.search_link)

            t = [cleantitle.get(i) for i in set(titles) if i]
            y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']

            r = client.request(query, post={'do': 'search', 'subaction': 'search', 'search_start': 0, 'full_search': 0, 'result_from': 1, 'story': cleantitle.query(titles[0])})

            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'fullstream'})
            r = [(dom_parser.parse_dom(i, 'h3', attrs={'class': 'mov-title'}), dom_parser.parse_dom(i, 'div', attrs={'class': 'fullmask'})) for i in r]
            r = [(dom_parser.parse_dom(i[0], 'a', req='href'), dom_parser.parse_dom(i[1], 'a', attrs={'href': re.compile('.*/year/\d+')})) for i in r]
            r = [(i[0][0].attrs['href'], i[0][0].content, i[1][0].content if i[1] else '0') for i in r if i[0]]
            r = [(i[0], i[1], i[2], re.findall('(.+?)\s+(?:\s*-\s*saison)\s+(\d+)', i[1], re.I)) for i in r]
            r = [(i[0], i[3][0][0] if len(i[3]) > 0 else i[1], i[2], i[3][0][1] if len(i[3]) > 0 else '0') for i in r]
            r = [(i[0], i[1], i[2], '1' if int(season) > 0 and i[3] == '0' else i[3]) for i in r]
            r = sorted(r, key=lambda i: int(i[2]), reverse=True)  # with year > no year
            r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y and int(i[3]) == int(season)][0]

            return source_utils.strip_domain(r)
        except:
            return