Python cleantitle.get函数代码示例

    def episode(self, url, imdb, tvdb, title, premiered, season, episode):
        try:
            pages = []
            data = urlparse.parse_qs(url)
            data = dict((i, data[i][0]) for i in data)
            data.update({'season': season, 'episode': episode, 'title': title, 'premiered': premiered})

            season_base = 'S%02dE%02d' % (int(data['season']), int(data['episode']))
            query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', season_base)
            tvshowtitle = data['tvshowtitle']
            tvshowtitle = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', tvshowtitle)

            query = query.replace("&", "and")
            query = query.replace("  ", " ")
            query = query.replace(" ", "+")
            tvshowtitle = tvshowtitle.replace("&", "and")
            tvshowtitle = tvshowtitle.replace("  ", " ")
            tvshowtitle = tvshowtitle.replace(" ", "+")

            start_url = urlparse.urljoin(self.base_link, self.search_link % (tvshowtitle, query))

            html = client.request(start_url)
            results = client.parseDOM(html, 'h2', attrs={'class':'entry-title'})
            for content in results:
                found_link = client.parseDOM(content, 'a', ret='href')[0]
                if self.base_link in found_link:
                    if cleantitle.get(data['tvshowtitle']) in cleantitle.get(found_link):
                        if cleantitle.get(season_base) in cleantitle.get(found_link):
                            pages.append(found_link)
            return pages
        except:
            failure = traceback.format_exc()
            log_utils.log('ALLRLS - Exception: \n' + str(failure))
            return pages

    def movie(self, imdb, title, localtitle, aliases, year):
        try:
            query = self.search_link % (urllib.quote_plus(title))
            query = urlparse.urljoin(self.base_link, query)
            result = client.request(query)
            result = client.parseDOM(result, 'div', attrs={'class': 'movie clearfix'})
            result = [(client.parseDOM(i, 'a', ret='href'),
                  client.parseDOM(i, 'span', attrs={'class': 'title-pl'}),
                  client.parseDOM(i, 'span', attrs={'class': 'title-en'}),
                  client.parseDOM(i, 'img', ret='src'),
                  client.parseDOM(i, 'p'),
                  client.parseDOM(i, 'p', attrs={'class': 'plot'})) for i in result ]

            result = [(i[0][0], u" ".join(i[1] + i[2]), re.findall('(\d{4})', i[4][0])) for i in result]

            result = [i for i in result if cleantitle.get(title) in cleantitle.get(i[1])]
            years = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1)]
            result = [i[0] for i in result if any(x in i[2] for x in years)][0]


            try: url = re.compile('//.+?(/.+)').findall(result)[0]
            except: url = result
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except :
            return

 def matchAlias(self, title, aliases):
     try:
         for alias in aliases:
             if cleantitle.get(title) == cleantitle.get(alias['title']):
                 return True
     except:
         return False

    def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
        try:
            tv_maze = tvmaze.tvMaze()
            tvshowtitle = tv_maze.showLookup('thetvdb', tvdb)
            tvshowtitle = tvshowtitle['name']

            t = cleantitle.get(tvshowtitle)

            q = urlparse.urljoin(self.base_link, self.search_link)
            q = q % urllib.quote_plus(tvshowtitle)

            r = client.request(q)

            r = client.parseDOM(r, 'ul', attrs={'class': 'items'})
            r = client.parseDOM(r, 'li')
            r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title'), re.findall('\d{4}', i)) for i in r]
            r = [(i[0][0], i[1][0], i[2][-1]) for i in r if i[0] and i[1] and i[2]]
            r = [i for i in r if t == cleantitle.get(i[1]) and year == i[2]]
            r = r[0][0]

            url = re.findall('(?://.+?|)(/.+)', r)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            failure = traceback.format_exc()
            log_utils.log('GoGoAnime - Exception: \n' + str(failure))
            return

    def episode(self, url, imdb, tvdb, title, premiered, season, episode):
        try:
            if url == None: return

            url = urlparse.urljoin(self.base_link, url)

            result = proxy.request(url, 'main_body')
            result = client.parseDOM(result, 'div', attrs = {'class': 'tv_episode_item'})

            title = cleantitle.get(title)

            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'span', attrs = {'class': 'tv_episode_name'}), re.compile('(\d{4}-\d{2}-\d{2})').findall(i)) for i in result]
            result = [(i[0], i[1][0], i[2]) for i in result if len(i[1]) > 0] + [(i[0], None, i[2]) for i in result if len(i[1]) == 0]
            result = [(i[0], i[1], i[2][0]) for i in result if len(i[2]) > 0] + [(i[0], i[1], None) for i in result if len(i[2]) == 0]
            result = [(i[0][0], i[1], i[2]) for i in result if len(i[0]) > 0]

            url = [i for i in result if title == cleantitle.get(i[1]) and premiered == i[2]][:1]
            if len(url) == 0: url = [i for i in result if premiered == i[2]]
            if len(url) == 0 or len(url) > 1: url = [i for i in result if 'season-%01d-episode-%01d' % (int(season), int(episode)) in i[0]]

            url = client.replaceHTMLCodes(url[0][0])
            url = proxy.parse(url)
            url = re.findall('(?://.+?|)(/.+)', url)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return

    def __search(self, title, season):
        try:
            query = self.search_link % (urllib.quote_plus(cleantitle.query(title)))
            query = urlparse.urljoin(self.base_link, query)

            t = cleantitle.get(title)

            r = client.request(query)

            r = client.parseDOM(r, 'div', attrs={'class': 'moviefilm'})
            r = client.parseDOM(r, 'div', attrs={'class': 'movief'})
            r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in r]
            r = [(i[0][0], i[1][0].lower()) for i in r if len(i[0]) > 0 and len(i[1]) > 0]
            r = [(i[0], i[1], re.findall('(.+?)\s+(?:saison)\s+(\d+)', i[1])) for i in r]
            r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
            r = [(i[0], i[1], re.findall('\((.+?)\)$', i[1]), i[2]) for i in r]
            r = [(i[0], i[2][0] if len(i[2]) > 0 else i[1], i[3]) for i in r]
            r = [i[0] for i in r if t == cleantitle.get(i[1]) and int(i[2]) == int(season)][0]

            url = re.findall('(?://.+?|)(/.+)', r)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return

    def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
        try:
            t = cleantitle.get(tvshowtitle)

            q = urllib.quote_plus(cleantitle.query(tvshowtitle))
            p = urllib.urlencode({'term': q})

            r = client.request(self.search_link, post=p, XHR=True)
            try: r = json.loads(r)
            except: r = None

            if r:
                r = [(i['seo_url'], i['value'], i['label']) for i in r if 'value' in i and 'label' in i and 'seo_url' in i]
            else:
                r = requests.get(self.search_link_2 % q, 'tv shows').text
                r = client.parseDOM(r, 'div', attrs = {'valign': '.+?'})
                r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title'), client.parseDOM(i, 'a')) for i in r]
                r = [(i[0][0], i[1][0], i[2][0]) for i in r if i[0] and i[1] and i[2]]

            r = [(i[0], i[1], re.findall('(\d{4})', i[2])) for i in r]
            r = [(i[0], i[1], i[2][-1]) for i in r if i[2]]
            r = [i for i in r if t == cleantitle.get(i[1]) and year == i[2]]

            url = r[0][0]
            url = proxy.parse(url)

            url = url.strip('/').split('/')[-1]
            url = url.encode('utf-8')
            return url
        except:
            return

    def __search(self, titles, year):
        try:
            query = self.search_link % (urllib.quote_plus(cleantitle.getsearch(titles[0])))

            query = urlparse.urljoin(self.base_link, query)

            t = cleantitle.get(titles[0])
            scraper = cfscrape.create_scraper()
            data = scraper.get(query).content
            #data = client.request(query, referer=self.base_link)
            data = client.parseDOM(data, 'div', attrs={'class': 'result-item'})
            r = dom_parser.parse_dom(data, 'div', attrs={'class': 'title'})
            r = zip(dom_parser.parse_dom(r, 'a'), dom_parser.parse_dom(data, 'span', attrs={'class': 'year'}))

            url = []
            for i in range(len(r)):
                title = cleantitle.get(r[i][0][1])
                title = re.sub('(\d+p|4k|3d|hd|season\d+)','',title)
                y = r[i][1][1]
                link = r[i][0][0]['href']
                if 'season' in title: continue
                if t == title and y == year:
                    if 'season' in link:
                        url.append(source_utils.strip_domain(link))
                        print url[0]
                        return url[0]
                    else: url.append(source_utils.strip_domain(link))

            return url
        except:
            return

    def movie(self, imdb, title, localtitle, aliases, year):
        try:
            t = cleantitle.get(title)

            q = '%s %s' % (title, year)
            q = self.search_link.decode('base64') % urllib.quote_plus(q)

            r = client.request(q)
            r = json.loads(r)['results']
            r = [(i['url'], i['titleNoFormatting']) for i in r]
            r = [(i[0].split('%')[0], re.findall('(?:^Watch |)(.+?)(?:\(|)(\d{4})', i[1])) for i in r]
            r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if i[1]]
            r = [i for i in r if '/watch/' in i[0] and not '-season-' in i[0]]
            r = [i for i in r if t == cleantitle.get(i[1]) and year == i[2]]
            r = r[0][0]

            url = re.findall('(?://.+?|)(/.+)', r)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            pass

        try:
            url = re.sub('[^A-Za-z0-9]', '-', title).lower()
            url = self.moviesearch_link % (url, year)

            r = urlparse.urljoin(self.base_link, url)
            r = client.request(r, output='geturl')
            if not year in r: raise Exception()

            return url
        except:
            return

    def movie(self, imdb, title, year):
        try:
            t = cleantitle.get(title)

            headers = {'X-Requested-With': 'XMLHttpRequest'}

            query = urllib.urlencode({'keyword': title})

            url = urlparse.urljoin(self.base_link, self.search_link)

            r = client.request(url, post=query, headers=headers)

            r = json.loads(r)['content']
            r = zip(client.parseDOM(r, 'a', ret='href', attrs = {'class': 'ss-title'}), client.parseDOM(r, 'a', attrs = {'class': 'ss-title'}))
            r = [i[0] for i in r if cleantitle.get(t) == cleantitle.get(i[1])][:2]
            r = [(i, re.findall('(\d+)', i)[-1]) for i in r]

            for i in r:
                try:
                    y, q = cache.get(self.onemovies_info, 9000, i[1])
                    if not y == year: raise Exception()
                    return urlparse.urlparse(i[0]).path
                except:
                    pass
        except:
            return

    def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
        try:
            if (self.user == '' or self.password == ''): raise Exception()

            t = cleantitle.get(tvshowtitle)

            u = urlparse.urljoin(self.base_link, self.search_link)

            p = {'q': tvshowtitle.rsplit(':', 1)[0], 'limit': '10', 'timestamp': int(time.time() * 1000), 'verifiedCheck': ''}
            p = urllib.urlencode(p)

            r = client.request(u, post=p, XHR=True)
            r = json.loads(r)

            r = [i for i in r if i['meta'].strip().split()[0].lower() == 'tv']
            r = [i['permalink'] for i in r if t == cleantitle.get(i['title'])][:2]
            r = [(i, urlparse.urljoin(self.base_link, i)) for i in r]
            r = [(i[0], client.request(i[1])) for i in r]
            r = [(i[0], i[1]) for i in r if not i[1] == None]
            r = [(i[0], re.sub('\s|<.+?>|</.+?>', '', i[1])) for i in r]
            r = [(i[0], re.findall('eleased:(\d{4})', i[1])) for i in r]
            r = [(i[0], i[1][0]) for i in r if i[1]]
            r = [i for i in r if year in i[1]]
            r = r[0][0]

            url = re.findall('(?://.+?|)(/.+)', r)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return

    def episode(self, url, imdb, tvdb, title, premiered, season, episode):
        self.zen_url = []	
        try:
			if not debridstatus == 'true': raise Exception()
			data = urlparse.parse_qs(url)
			data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
			title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
			data['season'], data['episode'] = season, episode
			self.zen_url = []
			title = cleantitle.getsearch(title)
			cleanmovie = cleantitle.get(title)			
			episodecheck = 'S%02dE%02d' % (int(data['season']), int(data['episode']))
			episodecheck = str(episodecheck)
			episodecheck = episodecheck.lower()
			titlecheck = cleanmovie+episodecheck
			query = '%s+S%02dE%02d' % (urllib.quote_plus(title), int(data['season']), int(data['episode']))
			movielink = self.search_link + query
			link = client.request(movielink, timeout="10")
			match = re.compile('<h2 class="entry-title"><a href="(.+?)" rel="bookmark">(.+?)</a></h2>').findall(link)
			for movielink,title2 in match:
				c_title = cleantitle.get(title2)
				if titlecheck in c_title:
					self.zen_url.append([movielink,title])
			return self.zen_url
        except:
            return

    def movie(self, imdb, title, year):
        try:
            if not debridstatus == 'true': raise Exception()

            t = cleantitle.get(title)

            headers = {'X-Requested-With': 'XMLHttpRequest'}

            query = self.search_link + urllib.quote_plus(title)
            query = urlparse.urljoin(self.base_link, query)

            r = client.request(query, headers=headers)
            r = json.loads(r)

            r = [i for i in r if 'category' in i and 'movie' in i['category'].lower()]
            r = [(i['url'], i['label']) for i in r if 'label' in i and 'url' in i]
            r = [(i[0], re.findall('(.+?) \((\d{4})', i[1])) for i in r]
            r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if len(i[1]) > 0]
            r = [i[0] for i in r if t == cleantitle.get(i[1]) and year == i[2]][0]

            url = re.findall('(?://.+?|)(/.+)', r)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return

    def movie(self, imdb, title, localtitle, year):
        try:
            q = self.search_link_2.decode('base64') % urllib.quote_plus(title)

            r = client.request(q)
            if r == None: r = client.request(q)
            if r == None: r = client.request(q)
            if r == None: r = client.request(q)

            r = json.loads(r)['results']
            r = [(i['url'], i['titleNoFormatting']) for i in r]
            r = [(i[0], re.findall('(?:^Watch |)(.+? \(\d{4}\))', i[1])) for i in r]
            r = [(urlparse.urljoin(self.base_link, i[0]), i[1][0]) for i in r if i[1]]

            t = cleantitle.get(title)
            years = ['(%s)' % str(year), '(%s)' % str(int(year)+1), '(%s)' % str(int(year)-1)]

            r = [i for i in r if any(x in i[1] for x in years)]

            match = [i[0] for i in r if t in cleantitle.get(i[1]) and '(%s)' % str(year) in i[1] and self.base_link in i[0]]

            match2 = [i[0] for i in r]
            match2 = [x for y,x in enumerate(match2) if x not in match2[:y]]
            if match2 == []: return

            for i in match2[:5]:
                try:
                    if len(match) > 0 : url = match[0] ; break
                except:
                    pass

            return url
        except:
            pass

    def tvshow(self, imdb, tvdb, tvshowtitle, year):
        try:
            r = 'search/tvdb/%s?type=show&extended=full' % tvdb
            r = json.loads(trakt.getTrakt(r))
            if not r: return '0'

            d = r[0]['show']['genres']
            if not ('anime' in d or 'animation' in d): return '0'

            tv_maze = tvmaze.tvMaze()
            tvshowtitle = tv_maze.showLookup('thetvdb', tvdb)
            tvshowtitle = tvshowtitle['name']

            t = cleantitle.get(tvshowtitle)

            q = urlparse.urljoin(self.base_link, self.search_link)
            q = q % urllib.quote_plus(tvshowtitle)

            r = client.request(q)

            r = client.parseDOM(r, 'ul', attrs={'class': 'items'})
            r = client.parseDOM(r, 'li')
            r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title'), re.findall('\d{4}', i)) for i in r]
            r = [(i[0][0], i[1][0], i[2][-1]) for i in r if i[0] and i[1] and i[2]]
            r = [i for i in r if t == cleantitle.get(i[1]) and year == i[2]]
            r = r[0][0]

            url = re.findall('(?://.+?|)(/.+)', r)[0]
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return