Python cleantitle.tv函数代码示例

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            result = client.source(self.base_link, headers=self.headers)
            if not "'index show'" in result:
                cookie = client.source(self.sign_link, headers=self.headers, post=self.key_link, output="cookie")
                result = client.source(self.base_link, headers=self.headers, cookie=cookie)

            result = client.parseDOM(result, "div", attrs={"class": "index show"})
            result = [
                (
                    client.parseDOM(i, "a", attrs={"class": "name"})[0],
                    client.parseDOM(i, "span", attrs={"class": "value"})[0],
                    client.parseDOM(i, "a", ret="href")[0],
                )
                for i in result
            ]

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = [str(year), str(int(year) + 1), str(int(year) - 1)]
            result = [i for i in result if any(x in i[1] for x in years)]
            result = [i[2] for i in result if tvshowtitle == cleantitle.tv(i[0])][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 get_episode(self, url, imdb, tvdb, title, date, season, episode):
        try:
            tvshowtitle, year = re.compile('(.+?) [(](\d{4})[)]$').findall(url)[0]

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

            result = client.source(query)

            tvshowtitle = cleantitle.tv(tvshowtitle)
            season = '%01d' % int(season)
            episode = '%01d' % int(episode)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]

            result = client.parseDOM(result, 'div', attrs = {'class': 'ml-item'})
            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'h2'), re.compile('class *= *[\'|\"]jt-info[\'|\"]>(\d{4})<').findall(i)) for i in result]
            result = [(i[0][0], i[1][0], i[2][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0 and len(i[2]) > 0]
            result = [(i[0], re.compile('(.+?) - Season (\d*)$').findall(i[1]), i[2]) for i in result]
            result = [(i[0], i[1][0][0], i[1][0][1], i[2]) for i in result if len(i[1]) > 0]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = [i for i in result if season == i[2]]
            result = [(i[0], i[1], str(int(i[3]) - int(i[2]) + 1)) for i in result]
            result = [i[0] for i in result if any(x in i[2] for x in years)][0]

            result += '?S%02dE%02d' % (int(season), int(episode))

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

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = self.search_link % urllib.quote_plus(tvshowtitle)
            query = urlparse.urljoin(self.base_link, query)

            result = cloudflare.source(query, safe=True)
            result = client.parseDOM(result, 'div', {'class': 'movie-grid grid-.+?'})

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]

            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'div', {'class': 'movie-grid-title'})) for i in result]
            result = [(i[0][0], i[1][0], i[1][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0]
            result = [(i[0], i[1].split('<')[0].strip(), client.parseDOM(i[2], 'span', {'class': '[^"]*year'})) for i in result]
            result = [(i[0], i[1], i[2][0]) for i in result if len(i[2]) > 0]
            result = [i for i in result if '/series/' in i[0]]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[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 get_episode(self, url, imdb, tvdb, title, date, season, episode):
        try:
            if url == None: return

            season = '%01d' % int(season)
            episode = '%01d' % int(episode)

            query = '%s "Season %s" "Episode %s"' % (url, season, episode)
            query = urlparse.urljoin(self.base_link, self.tvsearch_link + urllib.quote_plus(query))

            result = cloudflare.source(query)
            if result == None: result = client.source(self.__proxy() + urllib.quote_plus(query))

            r = client.parseDOM(result, 'li', attrs = {'class': 'first element.+?'})
            r += client.parseDOM(result, 'li', attrs = {'class': 'element.+?'})
            r += client.parseDOM(result, 'header', attrs = {'class': 'entry-header'})

            tvshowtitle = cleantitle.tv(url)

            result = [(client.parseDOM(i, 'a', ret='href'), re.compile('(.+?): Season (\d*).+?Episode (\d*)').findall(i)) for i in r]
            result = [(i[0][0], i[1][-1]) for i in result if len(i[0]) > 0 and len(i[1]) > 0]
            result = [(i[0], i[1][0].split('>')[-1], i[1][1], i[1][2]) for i in result]
            result = [i for i in result if season == '%01d' % int(i[2]) and episode == '%01d' % int(i[3])]
            result = [i[0] for i in result if tvshowtitle == cleantitle.tv(i[1])][0]

            url = client.replaceHTMLCodes(result)
            try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['u'][0]
            except: pass
            try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['q'][0]
            except: pass
            url = urlparse.urlparse(url).path
            url = url.encode('utf-8')
            return url
        except:
            return

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = self.search_link % (urllib.quote_plus(tvshowtitle))
            query = urlparse.urljoin(self.base_link, query)

            result = client.source(query)
            result = result.decode("iso-8859-1").encode("utf-8")
            result = client.parseDOM(result, "ol", attrs={"id": "searchresult"})[0]
            result = client.parseDOM(result, "h2")

            tvshowtitle = cleantitle.tv(tvshowtitle)
            result = [(client.parseDOM(i, "a", ret="href")[0], client.parseDOM(i, "a")[0]) for i in result]
            result = [(i[0], re.sub("<.+?>|</.+?>", "", i[1])) for i in result]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = result[-1][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 get_episode(self, url, imdb, tvdb, title, date, season, episode):
        try:
            if url == None: return

            query = '%s S%02dE%02d' % (url, int(season), int(episode))
            query = urlparse.urljoin(self.tvbase_link, self.search_link + urllib.quote_plus(query))

            result = client.source(query)

            #if result == None: result = client.source(self.__proxy() + urllib.quote_plus(query))

            r = client.parseDOM(result, 'li', attrs = {'class': 'first element.+?'})
            r += client.parseDOM(result, 'li', attrs = {'class': 'element.+?'})
            r += client.parseDOM(result, 'header', attrs = {'class': 'entry-heade.+?'})

            tvshowtitle = cleantitle.tv(url)
            hdlr = 'S%02dE%02d' % (int(season), int(episode))

            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in r]
            result = [(i[0][0], i[1][0].upper()) for i in result if len(i[0]) > 0 and len(i[1]) > 0]
            result = [(i[0], re.compile('(.+?) (S\d+E\d+)').findall(i[1])) for i in result]
            result = [(i[0], i[1][0][0], i[1][0][-1]) for i in result if len(i[1]) > 0]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = [i[0] for i in result if hdlr == i[2]][0]

            url = client.replaceHTMLCodes(result)
            try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['u'][0]
            except: pass
            try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['q'][0]
            except: pass
            url = urlparse.urlparse(url).path
            url = url.encode('utf-8')
            return url
        except:
            return

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = urlparse.urljoin(self.base_link, self.ajax_link)
            post = self.search_link % (urllib.quote_plus(tvshowtitle))

            result = client.source(query, post=post, headers=self.headers)
            result = json.loads(result)

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]

            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'h3'), re.compile('<h5>.+?(\d{4}).+?</h5>').findall(i)) for i in result]
            result = [(i[0][0], i[1][0], i[2][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0 and len(i[2]) > 0]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = [i[0] for i in result if any(x in i[2] for x in years)][0]

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

            result = client.source(url)

            url = client.parseDOM(result, 'div', ret='value', attrs = {'id': 'icerikid'})[0]
            url = url.encode('utf-8')
            return url
        except:
            return

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = self.tvsearch_link % (urllib.quote_plus(tvshowtitle))
            query = urlparse.urljoin(self.base_link, query)

            result = client.request(query)
            result = client.parseDOM(result, 'div', attrs = {'class': 'searchResult'})

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]
            result = [(client.parseDOM(i, 'a', ret='href')[0], client.parseDOM(i, 'h2', ret='title')[0], client.parseDOM(i, 'span', attrs = {'itemprop': 'copyrightYear'})) for i in result]
            print result

            result = [i for i in result if len(i[2]) > 0]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = [i[0] for i in result if any(x in i[2][0] for x in years)][0]

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

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = urlparse.urljoin(self.base_link, self.tvsearch_link)

            result = client.source(query)

            result = client.parseDOM(result, 'div', attrs = {'class': 'movies_content'})[0]

            tvshowtitle = cleantitle.tv(tvshowtitle)

            result = re.compile('(<li>.+?</li>)').findall(result)
            result = [re.compile('href="(.+?)">(.+?)<').findall(i) for i in result]
            result = [i[0] for i in result if len(i) > 0]
            result = [i[0] for i in result if tvshowtitle == cleantitle.tv(i[1])][0]

            check = urlparse.urljoin(self.base_link, result)
            check = client.source(check)
            if not str(imdb) in check: raise Exception()

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

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = self.search_link % (urllib.quote_plus(tvshowtitle))
            query = urlparse.urljoin(self.base_link, query)

            result = cloudflare.source(query)
            result = client.parseDOM(result, 'div', attrs = {'class': 'tv-series-single'})

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]

            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', {'class': 'title'}), re.compile('<span>\s*(\d{4})\s*</span>').findall(i)) for i in result]
            result = [(i[0][0], i[1][0], i[2][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0 and len(i[2]) > 0]
            result = [(i[0], re.compile('([^>]+)$').findall(i[1]), i[2]) for i in result]
            result = [(i[0], i[1][0], i[2]) for i in result if len(i[1]) > 0]

            result = [i for i in result if tvshowtitle == cleantitle.tv(i[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 get_episode(self, url, imdb, tvdb, title, date, season, episode):
        try:
            if url == None: return

            title = url
            hdlr = 'S%02dE%02d' % (int(season), int(episode))

            query = self.tvsearch_link % (urllib.quote_plus('"%s %s"' % (title, hdlr)))

            result = client.source(query)

            tvshowtitle = cleantitle.tv(title)

            result = client.parseDOM(result, 'h3', attrs = {'class': '.+?'})
            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in result]
            result = [(i[0][0], i[1][-1]) for i in result if len(i[0]) > 0 and len(i[1]) > 0]

            result = [(i[0], re.compile('(^Watch Full "|^Watch |)(.+?) %s' % hdlr).findall(i[1])) for i in result]
            result = [(i[0], i[1][0][-1]) for i in result if len(i[1]) > 0]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = [i[0] for i in result][-1]

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

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

            title = url
            hdlr = 'S%02dE%02d' % (int(season), int(episode))

            query = self.search_link % (urllib.quote_plus('%s "%s"' % (title, hdlr)))
            query = urlparse.urljoin(self.tvbase_link, query)

            result = client.source(query)
            result = client.parseDOM(result, 'header', attrs = {'class': "post-title"})

            title = cleantitle.tv(title)
            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in result]
            result = [(i[0][0], i[1][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0]
            result = [(i[0], re.compile('(.+?) (S\d*E\d*)').findall(i[1])) for i in result]
            result = [(i[0], i[1][0][0], i[1][0][1]) for i in result if len(i[1]) > 0]
            result = [i for i in result if title == cleantitle.tv(i[1])]
            result = [i[0] for i in result if hdlr == i[2]][0]

            url = result.replace(self.tvbase_link, '')
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return

    def get_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            result = cache.get(self.moviefarsi_shows, 168, table='chronic')
            if result == None: return

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]

            result = [i[0] for i in result if tvshowtitle == cleantitle.tv(i[1])][0]

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

            result = client.source(url, cookie=self.cookie_link)
            if result == None: result = cloudflare.source(url)

            result = client.parseDOM(result, 'article', attrs = {'id': 'post-\d*'})[0]

            y = client.parseDOM(result, 'strong')[0]
            y = re.compile('(\d{4})').findall(y)[0]
            if not y in years: return

            result = client.parseDOM(result, 'a', ret='href')[0]

            url = re.compile('//.+?/(\d*)').findall(result)[0]
            url = url.encode('utf-8')
            return url
        except:
            return

    def tvrageEpisode(self, tvrage, title, date, season, episode):
        monthMap = {'01':'Jan', '02':'Feb', '03':'Mar', '04':'Apr', '05':'May', '06':'Jun', '07':'Jul', '08':'Aug', '09':'Sep', '10':'Oct', '11':'Nov', '12':'Dec'}
        title = cleantitle.tv(title)

        try:
            url = self.tvrage_link % tvrage
            result = client.request(url, timeout='5')
            search = re.compile('<td.+?><a.+?title=.+?season.+?episode.+?>(\d+?)x(\d+?)<.+?<td.+?>(\d+?/.+?/\d+?)<.+?<td.+?>.+?href=.+?>(.+?)<').findall(result.replace('\n',''))
            d = '%02d/%s/%s' % (int(date.split('-')[2]), monthMap[date.split('-')[1]], date.split('-')[0])
            match = [i for i in search if d == i[2]]
            if len(match) == 1: return (str('%01d' % int(match[0][0])), str('%01d' % int(match[0][1])))
            match = [i for i in search if title == cleantitle.tv(i[3])]
            if len(match) == 1: return (str('%01d' % int(match[0][0])), str('%01d' % int(match[0][1])))
        except:
            pass

        try:
            url = self.epguides_link % tvrage
            result = client.request(url, timeout='5')
            search = re.compile('\d+?,(\d+?),(\d+?),.+?,(\d+?/.+?/\d+?),"(.+?)",.+?,".+?"').findall(result)
            d = '%02d/%s/%s' % (int(date.split('-')[2]), monthMap[date.split('-')[1]], date.split('-')[0][-2:])
            match = [i for i in search if d == i[2]]
            if len(match) == 1: return (str('%01d' % int(match[0][0])), str('%01d' % int(match[0][1])))
            match = [i for i in search if title == cleantitle.tv(i[3])]
            if len(match) == 1: return (str('%01d' % int(match[0][0])), str('%01d' % int(match[0][1])))
        except:
            pass

    def get_episode(self, url, imdb, tvdb, title, date, season, episode):
        try:
            tvshowtitle, year = re.compile('(.+?) [(](\d{4})[)]$').findall(url)[0]

            season, episode = '%01d' % int(season), '%01d' % int(episode)

            query = '%s season %s' % (tvshowtitle, season)
            query = self.search_link % (urllib.quote_plus(query))

            result = client.request(query)
            result = json.loads(result)
            result = result['results']

            tvshowtitle = cleantitle.tv(tvshowtitle)
            years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]

            result = [(i['url'], i['titleNoFormatting']) for i in result]
            result = [(i[0], re.compile('(^Watch Full "|^Watch |)(.+?[(]\d{4}[)])').findall(i[1])) for i in result]
            result = [(i[0], i[1][0][-1].lower()) for i in result if len(i[1]) > 0]
            result = [(i[0], re.compile('(.+) season (\d+)\s*[(](\d{4})[)]').findall(i[1])) for i in result]
            result = [(i[0], cleantitle.tv(i[1][0][0]), i[1][0][1], i[1][0][2]) for i in result if len(i[1]) > 0]
            result = [i for i in result if tvshowtitle == cleantitle.tv(i[1])]
            result = [i for i in result if season == i[2]]
            result = [(i[0], i[1], str(int(i[3]) - int(i[2]) + 1)) for i in result]
            result = [i[0] for i in result if any(x in i[2] for x in years)][0]

            result += '?S%02dE%02d' % (int(season), int(episode))

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