Python cleantitle.movie函数代码示例

    def get_movie(self, imdb, title, year):
        try:
            query = self.search_link % urllib.quote_plus(title +' '+year)
            query = urlparse.urljoin(self.base_link, query)
            control.log('@ONECLICKWA %s' % query)
            result = client.request(self.base_link)
            control.log('Result %s' % result)

            result = client.request(query, headers={'Referer':self.base_link})
            control.log('Result %s' % result)
            years = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1)]
            result = client.parseDOM(result, 'h2', attrs={'class': 'title'})
            result = [(client.parseDOM(i, 'a', ret='href')[0], client.parseDOM(i, 'a')[0]) for i in result]
            #print('R',result)
            result = [i for i in result if cleantitle.movie(title.lower()) in cleantitle.movie(i[1]).lower()]
            #print('R',result)
            result = [i for i in result if any(x in i[1] for x in years)]
            #print('R',result)
            result2 = [i for i in result if '1080' in i[1]]
            #print('R',result)
            result3 = [i for i in result if '720' in i[1].lower()]
            #print('R',result)
            if len(result3) > 0: result = result3
            if len(result2) > 0: result = result2
            url = result[0][0]
            return url
        except:
            return

    def get_movie(self, imdb, title, year):
        try:
            query = self.search_link % urllib.quote_plus(title)
            query = urlparse.urljoin(self.base_link, query)

            result = client.source(query)

            result = result.decode("iso-8859-1").encode("utf-8")
            result = client.parseDOM(result, "div", attrs={"class": "movie_table"})

            title = cleantitle.movie(title)
            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, "a", ret="title")[1]) for i in result]
            result = [i for i in result if title == cleantitle.movie(i[1])]
            result = [i[0] for i in result if any(x in i[1] for x in years)][0]

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

    def get_movie(self, imdb, title, year):
        try:
            self.base_link = random.choice([self.base_link_1, self.base_link_2])

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

            result = client.source(query)

            result = client.parseDOM(result, 'div', attrs = {'class': 'cell_container'})

            title = cleantitle.movie(title)
            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', ret='title')) 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('(.+?) [(](\d{4})[)]').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.movie(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_movie(self, imdb, title, year):
        try:
            query = self.search_link % (urllib.quote_plus(title))
            query = urlparse.urljoin(self.base_link, query)

            result = client.source(query)
            result = client.parseDOM(result, 'div', attrs = {'class': 'home_post_cont.+?'})

            title = cleantitle.movie(title)
            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, 'img', ret='title')[0]) for i in result]
            result = [(i[0], client.replaceHTMLCodes(i[1])) for i in result]
            result = [(i[0], client.parseDOM(i[1], 'a')) for i in result]
            result = [(i[0], i[1][0]) for i in result if len(i[1]) > 0]
            result = [i for i in result if title == cleantitle.movie(i[1])]
            result = [i[0] for i in result if any(x in i[1] 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_movie(self, imdb, title, year):
        try:
            query = urlparse.urljoin(self.base_link, self.moviesearch_link + urllib.quote_plus(title))

            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'})

            title = cleantitle.movie(title)
            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')) for i in r]
            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('(.+? [(]\d{4}[)])').findall(i[1])) for i in result]
            result = [(i[0], i[1][0]) for i in result if len(i[1]) > 0]
            result = [i for i in result if title == cleantitle.movie(i[1])]
            result = [i[0] for i in result if any(x in i[1] for x in years)][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_movie(self, imdb, title, year):
        try:
            query = self.search_link
            post = {'searchquery': title, 'searchin': '1'}
            post = urllib.urlencode(post)
            result = ''

            headers = {"Content-Type":"application/x-www-form-urlencoded", "Referer":urlparse.urljoin(self.base_link, query)}
            result = client.request(urlparse.urljoin(self.base_link, query), post=post, headers=headers)
            #if 'widget search-page' in str(result): break
            print("R",result)
            result = client.parseDOM(result, 'div', attrs = {'class': 'widget search-page'})[0]
            result = client.parseDOM(result, 'td')

            title = cleantitle.movie(title)
            years = ['(%s)' % str(year), '(%s)' % str(int(year)+1), '(%s)' % str(int(year)-1)]
            result = [(client.parseDOM(i, 'a', ret='href')[-1], client.parseDOM(i, 'a')[-1]) for i in result]
            result = [i for i in result if title == cleantitle.movie(i[1])]
            result = [i[0] for i in result if any(x in i[1] for x in years)][0]

            url = client.replaceHTMLCodes(result)
            try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['u'][0]
            except: pass
            url = urlparse.urlparse(url).path
            url = url.encode('utf-8')
            return url
        except Exception as e:
            control.log("ERR iwatch %s" % e)
            return

    def get_movie(self, imdb, title, year):
        try:
            self.base_link = self.base_link
            query = '%s %s' % (title, year)
            query = self.search_link % (urllib.quote_plus(query))
            query = urlparse.urljoin(self.base_link, query)

            result = client.source(query)

            result = result.decode('iso-8859-1').encode('utf-8')

            result = client.parseDOM(result, "div", attrs={"class":"boxinfo"})
            title = cleantitle.movie(title)

            for item in result:
                searchTitle = client.parseDOM(item, "span", attrs={"class":"tt"})[0]
                try : searchTitle = re.compile('(.+?) \d{4} ').findall(searchTitle)[0]
                except: pass
                searchTitle = cleantitle.movie(searchTitle)
                if title in searchTitle:
                    url = client.parseDOM(item, "a", ret="href")[0]
                    url = re.compile(".+/(.+?)/").findall(url)[0]
                    break
            if url == None or url == '':
                raise Exception()
            return url
        except:
            return

    def get_movie(self, imdb, title, year):
        try:
            query = self.search_link % urllib.quote_plus(title)
            query = urlparse.urljoin(self.base_link, query)

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

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

            result = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'img', ret='alt')) 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 for i in result if any(x in i[1] for x in years)]
            result = [i[0] for i in result if title == cleantitle.movie(i[1])][0]

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

    def get_movie(self, imdb, title, year):
        try:
            self.base_link = self.base_link
            query = '%s' % (title)
            query = self.search_link % (urllib.quote_plus(query))
            query = urlparse.urljoin(self.base_link, query)

            result = client.source(query)

            result = result.decode('iso-8859-1').encode('utf-8')
            result = client.parseDOM(result, "div", attrs={"class":"tab-content mt20"})[0]
            result = client.parseDOM(result, "div", attrs={"id":"movies_tab"})[0]
            result = client.parseDOM(result, "div", attrs={"class":"media-left"})

            title = cleantitle.movie(title)
            for item in result:
                searchTitle = client.parseDOM(item, "a", ret="title")[0]
                searchTitle = re.compile('(.+?) [(]\d{4}[)]$').findall(searchTitle)[0]
                searchTitle = cleantitle.movie(searchTitle)
                if title == searchTitle:
                    url = client.parseDOM(item, "a", ret="href")[0]
                    break
            if url == None or url == '':
                raise Exception()
            return url
        except:
            return

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

            result = client.source(query)

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

            result = re.compile('(<li>.+?</li>)').findall(result)
            result = [i for i in result if "'main2'" in i]
            result = [re.compile('href=(.+?)>(.+?)<').findall(i) for i in result]
            result = [i[0] for i in result if len(i) > 0]
            result = [(i[0], re.compile('(.+?) [(](\d{4})[)]').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.movie(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_show(self, imdb, tvdb, tvshowtitle, year):
        try:
            query = self.search_link % (urllib.quote_plus(cleantitle.query2(tvshowtitle)))
            query = urlparse.urljoin(self.base_link, query)
            result = client.request(query)
            result = result.decode('utf-8-sig')
            result = client.parseDOM(result, 'ul', attrs={'id': 'resultList2'})[0]
            result = client.parseDOM(result, 'li')
            result = [(client.parseDOM(i,'div', attrs={'class':'title'}),
                       client.parseDOM(i, 'div', attrs={'class': 'info'}),
                       client.parseDOM(i, 'a', ret='href')[0]) for i in result]
            result = [(i[0][0], re.findall(r"(\d{4})", i[1][0])[0], i[2]) for i in result]

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

        except:
            return

    def get_movie(self, imdb, title, year):
        return

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

            result = client.source(query)
            result = result.decode('utf-8').encode('utf-8')
            result = client.parseDOM(result, 'li')
            title = cleantitle.movie(title)
            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 title == cleantitle.movie(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')
            #print("Result Movie - 3",result,url)

            return url
        except:
            return

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

            try:
                query = self.search2_link % urllib.quote_plus(title)
                query = urlparse.urljoin(self.base_link, query)

                result = client.request(query)

                r = client.parseDOM(result, 'div', attrs = {'class': 'ml-item'})
                r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title')) for i in r]
                r = [(i[0][0], i[1][-1]) for i in r if len(i[0]) > 0 and len(i[1]) > 0]
                r = [(re.sub('http.+?//.+?/','', i[0]), i[1]) for i in r]
                r = [('/'.join(i[0].split('/')[:2]), i[1]) for i in r]
                r = [x for y,x in enumerate(r) if x not in r[:y]]
                r = [i[0] for i in r if t == cleantitle.movie(i[1])]

                for i in r:
                    url = self._info(i, year)
                    if not url == None: return url
            except:
                import traceback
                traceback.print_exc()
                pass

        except:
            return

    def get_movie(self, imdb, title, year):
        try:
            query = self.search_link % urllib.quote(title)
            query = urlparse.urljoin(self.base_link, query)

            result = cloudflare.source(query)

            title = cleantitle.movie(title)
            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 for i in result if any(x in i[2] for x in years)]
            result = [(i[0], re.sub("\d{4}$", "", i[1]).strip()) for i in result]
            result = [i[0] for i in result if title == cleantitle.movie(i[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_movie(self, imdb, title, year):
        try:
            query = self.search_link % (urllib.quote_plus(title))
            query = urlparse.urljoin(self.base_link, query)

            result = cloudflare.source(query)

            result = client.parseDOM(result, "ul", attrs={"class": "listing-videos.+?"})[0]
            result = client.parseDOM(result, "li", attrs={"class": ".+?"})

            title = cleantitle.movie(title)
            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, "a", ret="title")[0]) for i in result]
            result = [i for i in result if title == cleantitle.movie(i[1])]
            result = [i[0] for i in result if any(x in i[1] 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