Python cleantitle.query函数代码示例

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

            t = cleantitle.get(title)
            tq = cleantitle.query(title)

            r = client.request(query)

            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'big-list'})
            r = dom_parser.parse_dom(r, 'table', attrs={'class': 'row'})
            r = dom_parser.parse_dom(r, 'td', attrs={'class': 'list-name'})
            r = dom_parser.parse_dom(r, 'a', req='href')
            r = [(i.attrs['href'], i.content) for i in r if i]

            url = [i[0] for i in r if t == cleantitle.get(i[1])]
            url = url[0] if len(url) > 0 else [i[0] for i in r if tq == cleantitle.query(i[1])][0]

            url = source_utils.strip_domain(url)

            r = client.request(urlparse.urljoin(self.base_link, url))
            r = dom_parser.parse_dom(r, 'a', attrs={'href': re.compile('.*/tt\d+.*')}, req='href')
            r = [re.findall('.+?(tt\d+).*?', i.attrs['href']) for i in r]
            r = [i[0] for i in r if i]

            return url if imdb in r else None
        except:
            return

 def search(self, title, localtitle, year, search_type):
     try:
         url = self.do_search(cleantitle.query(title), title, localtitle, year, search_type)
         if not url:
             url = self.do_search(cleantitle.query(localtitle), title, localtitle, year, search_type)
         return url
     except:
         return

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

            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)

            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'movie_cell'})
            r = [(dom_parser.parse_dom(i, 'div', attrs={'class': 'bottom'}), dom_parser.parse_dom(i, 'div', attrs={'class': 'year'})) for i in r]
            r = [(dom_parser.parse_dom(i[0], 'a', req=['href', 'title']), re.findall('[(](\d{4})[)]', i[1][0].content)) for i in r if i[0] and i[1]]
            r = [(i[0][0].attrs['href'], i[0][0].content, i[1][0]) for i in r if i[0] and i[1]]
            r = [(i[0], i[1].lower(), i[2]) for i in r if i[2] in y]
            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]

            if len(r) > 1:
                for i in r:
                    data = client.request(urlparse.urljoin(self.base_link, i))
                    data = dom_parser.parse_dom(data, 'a', attrs={'name': re.compile('.*/tt\d+.*')}, req='name')
                    data = [re.findall('.+?(tt\d+).*?', d.attrs['name']) for d in data]
                    data = [d[0] for d in data if len(d) > 0 and d[0] == imdb]

                    if len(data) >= 1:
                        url = i
            else:
                url = r[0]

            if url:
                return source_utils.strip_domain(url)
        except:
            return

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

            q = urllib.quote_plus(cleantitle.query(tvshowtitle))
            p = urllib.urlencode({'term': q})
            h = {'X-Requested-With': 'XMLHttpRequest'}

            r = client.request(self.search_link, post=p, headers=h)
            try: r = json.loads(r)
            except: r = None
            print ("WATCHSERIES RESULT", 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]

            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]]
            print ("WATCHSERIES RESULT 4", r, year)
            url = r[0][0]
            print ("WATCHSERIES RESULT 5", r, url)
            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 = url.strip('/').split('/')[-1]
            url = url.encode('utf-8')
            return url
        except:
            return

    def __search(self, titles, year, content):
        try:
            t = [cleantitle.get(i) for i in set(titles) if i]

            c = client.request(urlparse.urljoin(self.base_link, self.year_link % int(year)), output='cookie')

            p = urllib.urlencode({'search': cleantitle.query(titles[0])})
            c = client.request(urlparse.urljoin(self.base_link, self.search_link), cookie=c, post=p, output='cookie')
            r = client.request(urlparse.urljoin(self.base_link, self.type_link % content), cookie=c, post=p)

            r = dom_parser.parse_dom(r, 'div', attrs={'id': 'content'})
            r = dom_parser.parse_dom(r, 'tr')
            r = [dom_parser.parse_dom(i, 'td') for i in r]
            r = [dom_parser.parse_dom(i, 'a', req='href') for i in r]

            r = [(i[0].attrs['href'], i[0].content, i[1].content) for i in r if i]
            x = []
            for i in r:
                if re.search('(?<=<i>\().*$', i[1]):
                    x.append((i[0], re.search('(.*?)(?=\s<)', i[1]).group(), re.search('(?<=<i>\().*$', i[1]).group(), i[2]))
                else:
                    x.append((i[0], i[1], i[1], i[2]))
            r = [i[0] for i in x if (cleantitle.get(i[1]) in t or cleantitle.get(i[2]) in t) and i[3] == year][0]

            return source_utils.strip_domain(r)
        except:
            return

    def movie(self, imdb, title, localtitle, aliases, year):
        try:
            url = self.search_link % (cleantitle.geturl(title), year)

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

            r = proxy.geturl(q)
            if not r == None: return url

            t = cleantitle.get(title)

            q = self.search_link_2 % urllib.quote_plus(cleantitle.query(title))
            q = urlparse.urljoin(self.base_link, q)

            r = client.request(q)

            r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a'))
            r = [(i[0], re.findall('(?:\'|\")(.+?)(?:\'|\")', i[1])) for i in r]
            r = [(i[0], [re.findall('(.+?)\((\d{4})', x) for x in i[1]]) for i in r]
            r = [(i[0], [x[0] for x in i[1] if x]) for i in r]
            r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if i[1]]
            r = [i[0] for i in r if t == cleantitle.get(i[1]) and year == i[2]]

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

    def __search(self, titles, year):
        try:

            query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0])+' '+year))

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

            t = [cleantitle.get(i) for i in set(titles) if i][0]

            r = client.request(query)

            r = client.parseDOM(r, 'div', attrs={'class': 'karatula'})

            for i in r:
                title = client.parseDOM(i, 'a', ret='title')[0]
                y = re.findall('(\d{4})',title)[0]
                title = cleantitle.get_simple(title)

                if t in title and y == year :
                    x = dom_parser.parse_dom(i, 'a', req='href')
                    return source_utils.strip_domain(x[0][0]['href'])

            return
        except:
            return

    def __search(self, titles, year, season='0'):
        try:
            query = self.search_link % urllib.quote_plus(cleantitle.query(titles[0]))
            query = urlparse.urljoin(self.base_link, query)

            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)

            r = dom_parser.parse_dom(r, 'article', attrs={'class': 'shortstory'})
            r = dom_parser.parse_dom(r, 'div', attrs={'class': 's_info'})
            r = dom_parser.parse_dom(r, 'h2')
            r = dom_parser.parse_dom(r, 'a', req='href')
            r = [(i.attrs['href'], i.content.lower()) for i in r if i]
            r = [(i[0],  re.sub('<.+?>|</.+?>', '', i[1]), re.findall('(.+?) \(*(\d{4})', 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], i[2], re.findall('(.+?)(\d+)\s+(?:staf+el|s)', i[1])) 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

	def __search(self, title, year):
		try:
			r = client.request(self.base_link)
			r = re.findall('sL10n\s*=\s*({.*?});', r)[0]
			r = json.loads(r)['nonce']

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

			t = cleantitle.get(title)
			y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']

			r = client.request(query)
			r = json.loads(r)
			r = [(i, r[i].get('url', ''), r[i].get('title', ''), r[i].get('extra', {}).get('names', ''), r[i].get('extra', {}).get('date', '0')) for i in r]
			r = [(i[0], i[1], client.replaceHTMLCodes(i[2]), client.replaceHTMLCodes(i[3]), i[4]) for i in r]
			r = sorted(r, key=lambda i: int(i[4]), reverse=True)  # with year > no year
			r = [i[1] for i in r if (t == cleantitle.get(i[2]) or t == cleantitle.get(i[3])) and i[4] in y][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, 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 movie(self, imdb, title, year):
        try:
            t = cleantitle.get(title)

            q = '/search/%s.html' % (urllib.quote_plus(cleantitle.query(title)))
            q = urlparse.urljoin(self.base_link, q)

            for i in range(3):
                r = client.request(q)
                if not r == None: break

            r = client.parseDOM(r, '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][0]) for i in r if i[0] and i[1]]
            r = [i[0] for i in r if 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.ymovies_info, 9000, i[1])
                    if not y == year: raise Exception()
                    return urlparse.urlparse(i[0]).path
                except:
                    pass
        except:
            return

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

            t = [cleantitle.get(i) for i in set(titles) if i]

            r = client.request(query)

            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'nag'})
            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'item-video'})
            r = dom_parser.parse_dom(r, 'h2', attrs={'class': 'entry-title'})
            r = dom_parser.parse_dom(r, 'a', req='href')

                           
                                         

            for i in r:
                title = i[1]
                if re.search('\*(?:.*?)\*', title) is not None:
                    title = re.sub('\*(?:.*?)\*', '', title)
                title = cleantitle.get(title)
                if title in t:
                    return source_utils.strip_domain(i[0]['href'])
                else:
                    return
        except:
            return

    def __search(self, titles, type, year, season=0, episode=False):
        try:
            years = [str(year), str(int(year) + 1), str(int(year) - 1)]
            years = ['&veroeffentlichung[]=%s' % i for i in years]

            query = self.search_link % (type, urllib.quote_plus(cleantitle.query(titles[0])))
            query += ''.join(years)
            query = urlparse.urljoin(self.base_link, query)

            t = [cleantitle.get(i) for i in set(titles) if i]

            r = self.__proceed_search(query)
            r = [i[0] for i in r if cleantitle.get(i[1]) in t and int(i[2]) == int(season)][0]

            url = source_utils.strip_domain(r)
            if episode:
                r = client.request(urlparse.urljoin(self.base_link, url))
                r = dom_parser.parse_dom(r, 'div', attrs={'class': 'season-list'})
                r = dom_parser.parse_dom(r, 'li')
                r = dom_parser.parse_dom(r, 'a', req='href')
                r = [i.attrs['href'] for i in r if i and int(i.content) == int(episode)][0]

                url = source_utils.strip_domain(r)
            return url
        except:
            return

    def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, year):
        try:
            query = base64.b64decode(self.search_link) % urllib.quote_plus(cleantitle.query(tvshowtitle))

            result = self.request(query)

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

            result = [i for i in result if any(x in str(i['year']) for x in years)]

            match = [i['href'] for i in result if tvshowtitle == cleantitle.get(i['name'])]
            match = [i['href'] for i in result if tvshowtitle == cleantitle.get(i['name']) and str(year) == str(i['year'])]

            match2 = [i['href'] for i in result]
            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
                    if imdb in str(self.request(i)[0]['imdb']): url = i ; break
                except:
                    pass

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