Python source_utils.strip_domain函数代码示例

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

            query = self.search_link % (urllib.quote_plus(cleantitle.getsearch(titles[0])))

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

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

            r = client.request(query)

            r = client.parseDOM(r, 'div', attrs={'class': 'tab-content clearfix'})

            if content == 'movies':
                r = client.parseDOM(r, 'div', attrs={'id': 'movies'})
            else:
                r = client.parseDOM(r, 'div', attrs={'id': 'series'})

            data = dom_parser.parse_dom(r, 'figcaption')

            for i in data:
                title = i[0]['title']
                title = cleantitle.get(title)
                if title in t:
                    x = dom_parser.parse_dom(i, 'a', req='href')
                    return source_utils.strip_domain(x[0][0]['href'])
                else:
                    url = dom_parser.parse_dom(i, 'a', req='href')
                    data = client.request(url[0][0]['href'])
                    data = re.findall('<h1><a.+?">(.+?)\((\d{4})\).*?</a></h1>', data, re.DOTALL)[0]
                    if titles[0] in data[0] and year == data[1]: return source_utils.strip_domain(url[0][0]['href'])

            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 __search(self, titles, year, season=0, episode=False):
        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': 'container'})
            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'ml-item-content'})

            f = []
            for i in r:
                _url = dom_parser.parse_dom(i, 'a', attrs={'class': 'ml-image'}, req='href')[0].attrs['href']

                _title = re.sub('<.+?>|</.+?>', '', dom_parser.parse_dom(i, 'h6')[0].content).strip()
                try: _title = re.search('(.*?)\s(?:staf+el|s)\s*(\d+)', _title, re.I).group(1)
                except: pass

                _season = '0'

                _year = re.findall('calendar.+?>.+?(\d{4})', ''.join([x.content for x in dom_parser.parse_dom(i, 'ul', attrs={'class': 'item-params'})]))
                _year = _year[0] if len(_year) > 0 else '0'

                if season > 0:
                    s = dom_parser.parse_dom(i, 'span', attrs={'class': 'season-label'})
                    s = dom_parser.parse_dom(s, 'span', attrs={'class': 'el-num'})
                    if s: _season = s[0].content.strip()

                if cleantitle.get(_title) in t and _year in y and int(_season) == int(season):
                    f.append((_url, _year))
            r = f
            r = sorted(r, key=lambda i: int(i[1]), reverse=True)  # with year > no year
            r = [i[0] for i in r if r[0]][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'], i.content) for i in r]
                r = [i[0] for i in r if i[1] and int(i[1]) == int(episode)][0]
                url = source_utils.strip_domain(r)
            return url
        except:
            return

    def episode(self, url, imdb, tvdb, title, premiered, season, episode):
        try:
            if not url:
                return

            data = urlparse.parse_qs(url)
            data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
            tvshowtitle = data['tvshowtitle']
            localtvshowtitle = data['localtvshowtitle']
            aliases = source_utils.aliases_to_array(eval(data['aliases']))

            url = self.__search([localtvshowtitle] + aliases, data['year'], season)
            if not url and tvshowtitle != localtvshowtitle: url = self.__search([tvshowtitle] + aliases, data['year'], season)
            if not url: return

            r = client.request(urlparse.urljoin(self.base_link, url))

            r = dom_parser.parse_dom(r, 'ul', attrs={'class': ['list-inline', 'list-film']})
            r = dom_parser.parse_dom(r, 'li')
            r = dom_parser.parse_dom(r, 'a', req='href')
            r = [(i.attrs['href'], i.content) for i in r if i]
            r = [(i[0], i[1] if re.compile("^(\d+)$").match(i[1]) else '0') for i in r]
            r = [i[0] for i in r if int(i[1]) == int(episode)][0]

            return source_utils.strip_domain(r)
        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, 'ul', attrs={'class': ['products', 'row']})
            r = dom_parser.parse_dom(r, 'div', attrs={'class': ['box-product', 'clearfix']})
            if int(season) > 0:
                r = [i for i in r if dom_parser.parse_dom(i, 'div', attrs={'class': 'episode'})]
            else:
                r = [i for i in r if not dom_parser.parse_dom(i, 'div', attrs={'class': 'episode'})]
            r = dom_parser.parse_dom(r, 'h3', attrs={'class': 'title-product'})
            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], 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('(.+?)\s+(?:staf+el|s)\s+(\d+)', 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].replace(' hd', ''), 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]

            url = source_utils.strip_domain(r)
            url = url.replace('-info', '-stream')
            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 __search(self, titles, year, season='0'):
        try:
            url = 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']

            post = {'story': utils.uni2cp(titles[0]), 'titleonly': 3, 'do': 'search', 'subaction': 'search', 'search_start': 1, 'full_search': 0, 'result_from': 1}
            r = client.request(url, post=post)

            r = r.decode('cp1251').encode('utf-8')

            r = dom_parser.parse_dom(r, 'table', attrs={'class': 'eBlock'})
            r = [(dom_parser.parse_dom(i, 'div', attrs={'class': 'eTitle'}), dom_parser.parse_dom(i[1], 'a', attrs={'href': re.compile('.*\d+_goda/')})) for i in r]
            r = [(dom_parser.parse_dom(i[0][0], 'a', req='href'), [x.content for x in i[1] if re.match('\d{4}', x.content)][0] if i[1] else '0') for i in r if i[0]]
            r = [(i[0][0].attrs['href'], i[0][0].content, i[1]) for i in r if i[0]]
            r = [(i[0], i[1], i[2], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r if i]
            r = [(i[0], i[3][0][0] if i[3] else i[1], i[2]) for i in r]
            r = [(i[0], i[1], i[2], re.findall(u'(.+?)\s+(\d+)\s+(?:сезон)', 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 = 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, titles, year, episode='0'):
        try:
            title = titles[0]
            if int(episode) > 0: title += ' episode %s' % episode

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

            r = dom_parser.parse_dom(r, 'div', attrs={'id': 'entries'})
            r = dom_parser.parse_dom(r, 'div', attrs={'class': 'post'})
            r = dom_parser.parse_dom(r, 'h3', attrs={'class': 'title'})
            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], 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('(.+?)\s+(?:episode)\s+(\d+)', 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].replace(' hd', ''), i[2], '1' if int(episode) > 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(episode)][0]

            return source_utils.strip_domain(r)
        except:
            return

    def __search(self, search_link, imdb, titles):
        try:
            query = 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': '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']for i in r if i and cleantitle.get(i.content) in t][0]

            url = source_utils.strip_domain(r)

            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, titles, year, imdb):
        try:
            query = self.search_link % (urllib.quote_plus(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 __search(self, titles, year):
        try:
            query = self.search_link % (urllib.quote_plus(cleantitle.getsearch(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 = dom_parser.parse_dom(r, 'div', attrs={'class': 'v_pict'})

            for i in r:
                title = re.findall('alt="(.+?)"',i[1], re.DOTALL)[0]
                y = re.findall('(\d{4})', title, re.DOTALL)[0]
                title = re.sub('<\w+>|</\w+>','',title)
                title = cleantitle.get(title)
                title = re.findall('(\w+)', cleantitle.get(title))[0]

                if title in t and year == y:
                    url = re.findall('href="(.+?)"',i[1], re.DOTALL)[0]
                    return source_utils.strip_domain(url)
            return
        except:
            return

    def __search(self, titles, year):
        try:
            query = self.search_link % (cleantitle.getsearch(titles[0].replace(' ','%20')))

            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, 'li', attrs={'class': 'item everyone-item over_online haveTooltip'})

            for i in r:
                title = client.parseDOM(i, 'a', ret='title')[0]
                url = client.parseDOM(i, 'a', ret='href')[0]
                data = client.request(url)
                y = re.findall('<p><span>Año:</span>(\d{4})',data)[0]
                original_t = re.findall('movie-text">.+?h2.+?">\((.+?)\)</h2>',data, re.DOTALL)[0]
                original_t, title = cleantitle.get(original_t), cleantitle.get(title)

                if (t in title or t in original_t) 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):
        try:

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

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

            t =  cleantitle.get(titles[0])

            r = client.request(query)

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

            r = client.parseDOM(r, 'h3')

            for i in r:
                data = re.findall('<span.*?>(.+?)</span>.+?date">\s*\((\d{4}).*?</span>', i, re.DOTALL)
                for title, year in data:
                    title = cleantitle.get(title)
                    y = year
                    if title in t and year == y:
                        url = client.parseDOM(i, 'a', ret='href')[0]
                        return source_utils.strip_domain(url)

            return
        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