Python client.parseDOM函数代码示例

    def resolve(self, url):
        try:
            url = urlparse.urlparse(url).path

            result = ""
            links = [self.link_1, self.link_2, self.link_3]
            for base_link in links:
                result = client.request(urlparse.urljoin(base_link, url), headers=self.headers)
                if "showvideo" in str(result):
                    break

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

            url = client.parseDOM(result, "div", attrs={"id": "showvideo"})[0]
            url = url.replace("<IFRAME", "<iframe").replace(" SRC=", " src=")
            url = client.parseDOM(url, "iframe", ret="src")[0]
            url = client.replaceHTMLCodes(url)
            try:
                url = urlparse.parse_qs(urlparse.urlparse(url).query)["u"][0]
            except:
                pass
            try:
                url = urlparse.parse_qs(urlparse.urlparse(url).query)["url"][0]
            except:
                pass

            url = resolvers.request(url)
            return url
        except:
            return

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

            query = self.tvbase_link + self.index_link
            post = urllib.urlencode({'a': 'retrieve', 'c': 'result', 'p': '{"KeyWord":"%s","Page":"1","NextToken":""}' % url})

            result = client.source(query, post=post)
            result = result.decode('iso-8859-1').encode('utf-8')
            result = client.parseDOM(result, "tr")

            show = cleantitle.tv(url)
            season = '%01d' % int(season)
            episode = '%02d' % int(episode)
            result = [client.parseDOM(i, "h1")[0] for i in result]
            result = [(client.parseDOM(i, "a", ret="href")[0], client.parseDOM(i, "a")[0]) for i in result]
            result = [(i[0], re.sub('\sSeason(|\s)\d*.+', '', i[1]), re.compile('\sSeason *(\d*) *').findall(i[1])[0]) for i in result]
            result = [i for i in result if show == cleantitle.tv(i[1])]
            result = [i[0] for i in result if season == i[2]][0]

            url = result.split('v=', 1)[-1]
            url = '%s|%s' % (url, episode)
            url = client.replaceHTMLCodes(url)
            url = url.encode('utf-8')
            return url
        except:
            return

def resolve(url):
    try:
        result = client.request(url, close=False)

        post = {}
        f = client.parseDOM(result, "Form", attrs={"action": ""})
        k = client.parseDOM(f, "input", ret="name", attrs={"type": "hidden"})
        for i in k:
            post.update({i: client.parseDOM(f, "input", ret="value", attrs={"name": i})[0]})
        post.update(captcha.request(result))
        post = urllib.urlencode(post)

        request = urllib2.Request(url, post)

        for i in range(0, 5):
            try:
                response = urllib2.urlopen(request, timeout=10)
                result = response.read()
                response.close()
                if "download2" in result:
                    raise Exception()
                url = client.parseDOM(result, "a", ret="href", attrs={"target": ""})[0]
                return url
            except:
                time.sleep(1)
    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, show, show_alt, year):
        try:
            result = client.source(self.base_link)
            if not "'index show'" in result:
                cookie = client.source(self.sign_link, post=self.key_link, output="cookie")
                result = client.source(self.base_link, 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
            ]

            shows = [cleantitle.tv(show), cleantitle.tv(show_alt)]
            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 any(x == cleantitle.tv(i[0]) for x in shows)][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 resolve(url):
    try:
        result = client.request(url)

        post = {}
        f = client.parseDOM(result, "Form", attrs = { "action": "" })
        k = client.parseDOM(f, "input", ret="name", attrs = { "type": "hidden" })
        for i in k: post.update({i: client.parseDOM(f, "input", ret="value", attrs = { "name": i })[0]})
        post.update({'method_free': 'Watch Free!'})
        post = urllib.urlencode(post)

        result = client.request(url, post=post)
        result = result.replace('\\/', '/').replace('\n', '').replace('\'', '"').replace(' ', '')

        swfUrl = re.compile('\.embedSWF\("(.+?)"').findall(result)[0]
        swfUrl = urlparse.urljoin(url, swfUrl)

        streamer = re.compile('flashvars=.+?"file":"(.+?)"').findall(result)[0]

        playpath = re.compile('flashvars=.+?p2pkey:"(.+?)"').findall(result)[0]

        url = '%s playpath=%s conn=S:%s pageUrl=%s swfUrl=%s swfVfy=true timeout=20' % (streamer, playpath, playpath, url, swfUrl)

        return url
    except:
        return

    def resolve(self, url):
        try:
            result = client.request(url)
            if not "my_video" in result:
                cookie = client.request(self.sign_link, post=self.key_link, output="cookie")
                result = client.request(url, cookie=cookie)

            url = None
            try:
                url = client.parseDOM(result, "source", ret="src", attrs={"type": "video/webm"})[0]
            except:
                pass
            try:
                url = client.parseDOM(result, "source", ret="src", attrs={"type": "video/mp4"})[0]
            except:
                pass

            if url == None:
                return
            url = urlparse.urljoin(self.base_link, url)
            url = "%s|Cookie=%s" % (url, urllib.quote_plus("video=true"))

            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)

            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.sub('<.+?>', '', i[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]

            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 = 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:
            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 = { "id": "post-.+?" })

            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], client.parseDOM(i, "div", attrs = { "class": "status status-year" }), client.parseDOM(i, "div", attrs = { "class": "mark-8" })) for i in result]
            result = [(i[0], i[1], i[2][0], i[3]) for i in result if len(i[2]) > 0]
            result = [(i[0], i[1], i[2], i[3], re.compile('Season (\d*)$').findall(i[1])) for i in result]
            result = [(i[0], i[1], i[2], i[3]) for i in result if len(i[4]) == 0]
            result = [(i[0], i[1], i[2]) for i in result if len(i[3]) == 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_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)

            result = client.parseDOM(result, "header", attrs = { "class": "entry-header" })

            show = cleantitle.tv(url)

            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('(.+?): Season (\d*).+?Episode (\d*)').findall(i[1])) for i in result]
            result = [(i[0], 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 season == '%01d' % int(i[2]) and episode == '%01d' % int(i[3])]
            result = [i[0] for i in result if show == cleantitle.tv(i[1])][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 resolve(url):
    try:
        result = client.request(url, mobile=True, close=False)

        try:
            post = {}
            f = client.parseDOM(result, "Form", attrs = { "method": "POST" })[0]
            f = f.replace('"submit"', '"hidden"')
            k = client.parseDOM(f, "input", ret="name", attrs = { "type": "hidden" })
            for i in k: post.update({i: client.parseDOM(f, "input", ret="value", attrs = { "name": i })[0]})
            post = urllib.urlencode(post)
        except:
            post=None

        for i in range(0, 10):
            try:
                result = client.request(url, post=post, mobile=True, close=False)
                result = result.replace('\n','')

                result = re.compile('sources *: *\[.+?\]').findall(result)[-1]
                result = re.compile('file *: *"(http.+?)"').findall(result)

                url = [i for i in result if '.m3u8' in i]
                if len(url) > 0: return url[0]
                url = [i for i in result if not '.m3u8' in i]
                if len(url) > 0: return url[0]
            except:
                time.sleep(1)
    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.agent_link + urllib.quote_plus(query))

            result = result.replace('> ', '>').replace(' <', '<')

            r = client.parseDOM(result, "li", attrs = { "class": "first element.+?" })
            r += client.parseDOM(result, "li", attrs = { "class": "element.+?" })

            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"), re.compile('>(.+?\(\d{4}\))<').findall(i)) 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], i[1].split('>')[-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_show(self, imdb, tvdb, show, show_alt, year):


        # import logging
        # LOG_FILENAME = '/home/keeganmccallum/test.log'
        # logging.basicConfig(filename=LOG_FILENAME,level=logging.DEBUG)

        # logging.debug(','.join([imdb, tvdb, show, show_alt, year]))

        try:
            result = client.source(self.base_link)
            if not "'index show'" in result:
                cookie = client.source(self.sign_link, post=self.key_link, output='cookie')
                result = client.source(self.base_link, 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]

            shows = [cleantitle.tv(show), cleantitle.tv(show_alt)]
            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 any(x == cleantitle.tv(i[0]) for x in shows)][0]

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