Python pCommon.CParsingHelper类代码示例

 def getLinksForVideo(self, cItem):
     printDBG("MoviesHDCO.getLinksForVideo [%s]" % cItem)
     urlTab = []
     
     sts, data = self.getPage(cItem['url'])
     if not sts: return urlTab
     
     #printDBG(data)
     
     data = CParsingHelper.getDataBeetwenMarkers(data, '<div class="video-embed">', '</div>', False)[1]
     oneLink = CParsingHelper.getDataBeetwenMarkers(data, 'data-rocketsrc="', '"', False)[1]
     if oneLink == '': oneLink =  self.cm.ph.getSearchGroups(data, '<iframe[^>]+?src="([^"]+?)"')[0]
     if oneLink == '': oneLink =  self.cm.ph.getSearchGroups(data, '<script[^>]+?src="([^"]+?)"')[0]
     
     if oneLink.startswith('//'):
         oneLink = 'http:' + oneLink
         
     oneLink = self._getFullUrl(oneLink)
     
     if 'videomega.tv/validatehash.php?' in oneLink:
         sts, data = self.cm.getPage(oneLink, {'header':{'Referer':cItem['url'], 'User-Agent':'Mozilla/5.0'}})
         if not sts: return urlTab
         data = self.cm.ph.getSearchGroups(data, 'ref="([^"]+?)"')[0]
         if '' == data: return urlTab
         oneLink = 'http://videomega.tv/view.php?ref={0}&width=700&height=460&val=1'.format(data)
         
     if '' == oneLink: return urlTab
     name = self.up.getHostName(oneLink)
     urlTab.append({'name':name, 'url':oneLink, 'need_resolve':1})
     return urlTab

 def getLink(self, url):
     printDBG("getLink url[%s]" % url)
     urlItem = url.split('|')
     if 3 == len(urlItem):
         url        = urlItem[0]
         post_data  = { 'action': 'getPlayer', 'id': urlItem[1], 'playerType': urlItem[2] }
         HEADER = dict(self.AJAX_HEADER)
         HEADER['Referer'] = url
         if 'free' == urlItem[2]:
             http_params = {'header': HEADER}
         else:
             http_params = {'header': HEADER, 'use_cookie': True, 'save_cookie': False, 'load_cookie': True, 'cookiefile': self.COOKIE_FILE}
             
         sts, data = self.cm.getPage( url, http_params, post_data)
         if not sts: return ''
         data = CParsingHelper.getDataBeetwenMarkers(data, '<div class="player">', '<div class="playerTypes">', False)[1]
         if 'free' == urlItem[2]:
             data = CParsingHelper.getSearchGroups(data, '<iframe [^>]*?src="([^"]+?)"')[0]
             sts, data = self.cm.getPage( data )
             if not sts: return ''
             data = CParsingHelper.getSearchGroups(data, '<iframe [^>]*?src="([^"]+?)"')[0]
             return self.up.getVideoLink( data )
         else:
             return CParsingHelper.getSearchGroups(data, 'url: [\'"](http[^\'"]+?)[\'"]')[0]
         return ''
     else:
         return url

 def getTeamCastList(self, cItem):
     printDBG('getTeamCastList start')
     #http://team-cast.pl.cp-21.webhostbox.net/kanalyFlash/
     #http://team-cast.pl.cp-21.webhostbox.net/
     #src="http://team-cast.pl.cp-21.webhostbox.net/kanalyFlash/film/hbo.html"
     url = cItem['url']
     # list categories
     if '' == url :
         self.teamCastTab = {}
         url = 'http://team-cast.pl.cp-21.webhostbox.net/'
         sts, data = self.cm.getPage(url)
         if not sts: return
         data = CParsingHelper.getDataBeetwenMarkers(data, '<div id="stream-frame">', '<div id="now-watching">', False)[1]
         # remove commented channels
         data = re.sub('<!--[^!]+?-->', '', data)
         data = data.split('<li class="menu_right">')
         del data[0]
         for cat in data:
             catName  = CParsingHelper.getDataBeetwenMarkers(cat, '<a href="#" class="drop">', '</a>', False)[1].strip()
             channels = re.findall('<a href="([^"]+?)">([^<]+?)<img src="http://wrzucaj.net/images/2014/09/12/flash-player-icon.png"', cat)
             if len(channels): 
                 self.teamCastTab[catName] = channels
                 newItem = dict(cItem)
                 newItem.update({'url':catName, 'title':catName + ' (%d)' % len(channels)})
                 self.addDir(newItem)
     elif url in self.teamCastTab:
         # List channels
         for item in self.teamCastTab[url]:
             newItem = dict(cItem)
             newItem.update({'url':item[0], 'title':item[1]})
             self.playVideo(newItem)
     else:
         printExc()

    def __init__(self, session, params={}):
        # params: vk_title, movie_title
        self.session = session
        Screen.__init__(self, session)
        
        self.params = params
        self.params['login']    = config.plugins.iptvplayer.opensuborg_login.value
        self.params['password'] = config.plugins.iptvplayer.opensuborg_password.value
        
        self.searchPattern = CParsingHelper.getNormalizeStr( self.params.get('movie_title', '') )
        
        # try to guess season and episode number
        try:
            tmp = CParsingHelper.getSearchGroups(self.searchPattern + ' ', 's([0-9]+?)e([0-9]+?)[^0-9]', 2)
            self.episodeData = {'season': int(tmp[0]), 'episode':int(tmp[1])}
        except:
            self.episodeData = {'season':-1, 'episode':-1}

        self.onShown.append(self.onStart)
        self.onClose.append(self.__onClose)
        
        self.subProvider = OpenSubOrgProvider()
        
        self["title"]         = Label(" ")
        self["console"]       = Label(" ")
        
        self["label_red"]     = Label(_("Cancel"))
        self["label_yellow"]  = Label(_("Move group"))
        self["label_green"]   = Label(_("Apply"))
        
        self["icon_red"]     = Cover3()
        self["icon_yellow"]  = Cover3()
        self["icon_green"]   = Cover3()
        
        self["list"] = IPTVMainNavigatorList()
        self["list"].connectSelChanged(self.onSelectionChanged)
        
        self["actions"] = ActionMap(["ColorActions", "SetupActions", "WizardActions", "ListboxActions"],
            {
                "cancel": self.keyExit,
                "ok"    : self.keyOK,
                "red"   : self.keyRed,
                "yellow": self.keyYellow,
                "green" : self.keyGreen,
            }, -2)
        
        self.iconPixmap = {}
        for icon in ['red', 'yellow', 'green']:
            self.iconPixmap[icon] = LoadPixmap(GetIconDir(icon+'.png'))
            
        self.movieTitle = ''
        self.stackList  = []
        self.stackItems = []
        
        self.defaultLanguage = GetDefaultLang()
    
        self.listMode = False
        self.downloadedSubFilePath = ''
        self.loginPassed = False
        self.tmpItem = None

 def getWebCamera(self, cItem):
     printDBG("getWebCamera start")
     sts, data = self.cm.getPage(cItem['url'])
     if sts:
         if cItem['title'] == 'WebCamera PL':
             params = dict(cItem)
             params.update({'title':'Polecane kamery'})
             self.addDir(params)
             data = CParsingHelper.getDataBeetwenMarkers(data, '<h4>Kamery wg kategorii</h4>', '</div>', False)[1]
             data = data.split('</a>')
             del data[-1]
             for item in data:
                 url = self.cm.ph.getSearchGroups(item, """href=['"](http[^'^"]+?)['"]""")[0]
                 if '' != url:
                     params = dict(cItem)
                     params.update({'title':self._cleanHtmlStr(item), 'url':url})
                     self.addDir(params)
         else:
             data = CParsingHelper.getDataBeetwenMarkers(data, '<div class="inlinecam', '<div id="footerbar">', False)[1]
             data = data.split('<div class="inlinecam')
             for item in data:
                 item = CParsingHelper.getDataBeetwenMarkers(item, '<a', '</div>', True)[1]
                 url = self.cm.ph.getSearchGroups(item, """href=['"](http[^'^"]+?)['"]""")[0]
                 if '' != url:
                     title = self._cleanHtmlStr(CParsingHelper.getDataBeetwenMarkers(item, '<div class="bar">', '</div>', False)[1])
                     icon  = self.cm.ph.getSearchGroups(item, """data-src=['"](http[^'^"]+?)['"]""")[0]
                     params = dict(cItem)
                     params.update({'title':title, 'url':url, 'icon':icon})
                     self.playVideo(params)

    def fillFilters(self, refresh=False):
        printDBG('getFilters')
        def SetFilters(raw, tab):
            printDBG("---------------------")
            for it in raw:
                tab.append({'tab': it[1], 'val': it[0]})
                printDBG("filter: %r" % tab[-1])
                
        if self.filtersFilled and not refresh: 
            return False
        
        sts, data = self.cm.getPage(self.MAINURL)
        if False == sts:
            return

        rawSortFilters = CParsingHelper.getDataBeetwenMarkers(data, 'Sortuj:', '</div>', False)[1]
        rawVerFilters  = CParsingHelper.getDataBeetwenMarkers(data, 'Wyświetl:', '</div>', False)[1]
        rawCatFilters  = CParsingHelper.getDataBeetwenMarkers(data, 'Kategorie Filmowe', '<script>', False)[1]
        data = '' # free data ;)
        rawSortFilters = re.compile('href="[^,]+?\,([^,]+?)\,wszystkie,0\.html">([^<]+?)<').findall(rawSortFilters)
        rawVerFilters  = re.compile('href="[^,]+?\,[^,]+?\,([^,]+?),0\.html">([^<]+?)<').findall(rawVerFilters)
        rawCatFilters  = re.compile('href="([^,]+?\,[^.]+?)\.html">([^<]+?)<').findall(rawCatFilters)
        
        if 0 < len(rawSortFilters) and 0 < len(rawVerFilters) and 0 < len(rawCatFilters):
            self.filters['sort'] = []
            self.filters['ver'] = []
            self.filters['cat'] = [{'tab': 'Wszystkie', 'val': 'glowna'}]
            SetFilters(rawSortFilters, self.filters['sort'])
            SetFilters(rawVerFilters, self.filters['ver'])
            SetFilters(rawCatFilters, self.filters['cat'])
            self.filtersFilled = True

    def getVideosList(self, url):
        printDBG("getVideosList url[%s]" % url)
        sts, data = self.cm.getPage(url)
        if not sts:
            printDBG("getVideosList except")
            return
        
        # get pagination HTML part
        nextPageData = CParsingHelper.getDataBeetwenMarkers(data, 'class="pager"', '</div>', False)[1]
        # get Video HTML part
        data = CParsingHelper.getDataBeetwenMarkers(data, '<!-- ************ end user menu ************ -->', '</ul>', False)[1].split('<li>')
        del data[0]
        
        for videoItemData in data:
            printDBG('                              videoItemData')
            icon     = ''
            duration = ''
            gatunek  = ''
            plot     = ''
            title    = ''
            url      = ''
            
            if 'class="playIcon"' in videoItemData:
                # get icon src
                match = re.search('src="(http://[^"]+?)"', videoItemData)
                if match: icon = match.group(1).replace('&amp;', '&')
                # get duration
                match = re.search('class="duration"[^>]*?>([^<]+?)<', videoItemData)
                if match: duration = match.group(1).replace('&#39;', "'")
                # get gatunek
                match = re.search('"gatunek"[^>]*?>([^<]+?)<', videoItemData)
                if match: gatunek = match.group(1)
                # get plot
                match = re.search('class="text"[^>]*?>([^<]+?)<', videoItemData)
                if match: plot = match.group(1)
                # get title and url
                match = re.search('<a href="([^"]+?)" class="title"[^>]*?>([^<]+?)</a>', videoItemData)
                if match:
                    url   = self.MAIN_URL + match.group(1)
                    title = match.group(2)
                    params = {'type': 'video', 'page': url, 'title': title, 'icon': icon, 'duration': duration, 'gatunek': gatunek, 'plot': plot}
                    self.currList.append( params )

        # check next page
        nextPageUrl = ''
        match = re.search('href="([^"]+?)" class="nextPage"', nextPageData)
        if match: 
            nextPageUrl = match.group(1)
        else:
            match = re.search('href="([^"]+?)" class="lastPage"', nextPageData)
            if match:
                nextPageUrl = match.group(1)

        if '' != nextPageUrl:
            params = {'type': 'category', 'name': 'sub-category', 'page': self.MAIN_URL + nextPageUrl.replace('&amp;', '&'), 'title': 'Następna strona'}
            self.currList.append( params )

 def listsCategoriesMenu(self, url):
     sts, data = self.cm.getPage( url, {'header': self.HEADER } )
     if not sts: return 
     data = CParsingHelper.getDataBeetwenMarkers(data, 'movie-kat-selection">', '</ul>', False)[1]
     data = data.split('</li>')
     for item in data:
         title = self.cleanHtmlStr(item)
         catID = CParsingHelper.getSearchGroups(item, 'data-value="([^"]+?)"', 1)[0]
         params = {'name': 'category', 'title': title, 'category': catID}
         self.addDir(params)

 def listSerialSeasons(self, category, url, icon):
     printDBG("listSerialSeasons")
     sts, data = self.cm.getPage( url )
     if False == sts: return
     
     plot = CParsingHelper.getDataBeetwenMarkers(data, '<p class="serialDescription">', '</p>', False)[1]
     data = CParsingHelper.getDataBeetwenMarkers(data, '<div class="seasonExpand">', '<script>', False)[1]
     data = re.compile('<a href="[/]?(serial,[^,]+?,sezon,[1-9][0-9]*?.html)">([^<]+?)</a>').findall(data)
     for item in data:
         if not item[0].startswith('http'):
             url =  self.MAINURL + item[0]
         params = {'name': 'category', 'title': item[1], 'category': category, 'url': url, 'icon':icon, 'plot':plot}
         self.addDir(params)

 def listSearchResults(self, pattern, searchType):
     printDBG("listFilms pattern[%s], searchType[%s]" % (pattern, searchType))
     url = self.MAINURL + 'szukaj.html?query=%s&mID=' % pattern
     sts, data = self.cm.getPage( url )
     if False == sts: return
     
     if 'filmy' == searchType:
         sts, data = CParsingHelper.getDataBeetwenMarkers(data, '<h2 id="movies-res">Filmy:', '<a href="#top"', False)
         category = 'video'
     else:
         sts, data = CParsingHelper.getDataBeetwenMarkers(data, '<h2 id="serials-res">Seriale:', '<a href="#top"', False)
         category = 'Serial_seasons_list'
     data = data.split('<li data-url=')
     self.listItems(data, category)  

 def getArticleContent(self, cItem):
     printDBG("Filmy3dEU.getArticleContent [%s]" % cItem)
     retTab = []
     
     if 'url' not in cItem: return retTab
     
     sts, data = self.cm.getPage(cItem['url'])
     if not sts: return retTab
     
     sts, data = CParsingHelper.getDataBeetwenMarkers(data, "<div id='dle-content'>", '<div class="gf-right">', False)
     title = CParsingHelper.getDataBeetwenMarkers(data, '<h1 class="title">', '</h1>', False)[1]
     icon = self.cm.ph.getSearchGroups(data, 'srct="([^"]+?)"')[0]
     desc = self.cleanHtmlStr( self.cm.ph.getDataBeetwenMarkers(data, '<div class="comment-box-block" id="comment1">', '</div>', False)[1] )
     
     return [{'title':title, 'text':desc, 'images':[]}]

    def getVideoUrl(self, url):
        #show adult content
        #self.cm.addCookieItem(COOKIEFILE, {'name': 'AnyF18', 'value': 'mam18', 'domain': 'video.anyfiles.pl'}, False)
        if not self.isLogged():
            self.tryTologin()

        # GET VIDEO ID
        u = url.split('/')
        vidID = u[-1]
        match = re.search('([0-9]+?)\,', url )
        if match:
            vidID = match.group(1)

        # get COOKIE
        sts, data = self.cm.getPage(self.MAINURL + '/videos.jsp?id=' + vidID, self.defaultParams)
        if not sts: 
            return []
        fUrl = self.MAINURL + "/w.jsp?id=%s&width=620&height=349&pos=&skin=0" % vidID
        COOKIE_JSESSIONID = self.cm.getCookieItem(self.COOKIEFILE,'JSESSIONID')
        HEADER = {'Referer' : url, 'Cookie' : 'JSESSIONID=' + COOKIE_JSESSIONID, 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:33.0) Gecko/20100101 Firefox/33.0'}
        request_param = {'header':HEADER}
        sts, data = self.cm.getPage(fUrl, request_param)
        if not sts: 
            return []
        
        #document.cookie = "__utdc_8a85608c7ff88b4de47cdc08107a8108=f68082abdaab664660b0c60289346552"+expires+"; path=";
        match = re.search('document.cookie = "([^"]+?)"',data)
        if match:
            printDBG("========================================================================== B")
            #printDBG(data)
            printDBG("========================================================================== C")
            HEADER['Cookie'] = HEADER['Cookie'] + '; ' + match.group(1)
            HEADER['Referer'] = self.MAINURL + '/flowplaer/flowplayer.commercial-3.2.16.swf'
            config = CParsingHelper.getSearchGroups(data, 'var flashvars = {[^"]+?config: "([^"]+?)" }', 1)[0]
            if '' == config: 
                printDBG("========================================================================== D")
                config = CParsingHelper.getSearchGroups(data, 'src="/?(pcsevlet\?code=[^"]+?)"', 1)[0]
            if '' != config:
                printDBG("========================================================================== E")
                sts,data = self.cm.getPage( self.MAINURL + '/' + config,  {'header': HEADER})
                if sts:
                    url = CParsingHelper.getSearchGroups(data, "'url':'(http[^']+?mp4)'", 1)[0]
                    if '' != url: 
                        return [{ 'name': 'AnyFiles', 'url': url}]
                    url = CParsingHelper.getSearchGroups(data, "'url':'api:([^']+?)'", 1)[0]
                    if '' != url: 
                        return self.getYTVideoUrl('http://www.youtube.com/watch?v='+url)
        return []

def getF4MLinksWithMeta(manifestUrl, checkExt=True):
    if checkExt and not manifestUrl.split("?")[0].endswith(".f4m"):
        return []

    cm = common()
    headerParams, postData = cm.getParamsFromUrlWithMeta(manifestUrl)

    retPlaylists = []
    sts, data = cm.getPage(manifestUrl, headerParams, postData)
    if sts:
        liveStreamDetected = False
        if "live" == CParsingHelper.getDataBeetwenMarkers("<streamType>", "</streamType>", False):
            liveStreamDetected = True
        bitrates = re.compile('bitrate="([0-9]+?)"').findall(data)
        for item in bitrates:
            link = strwithmeta(manifestUrl, {"iptv_proto": "f4m", "iptv_bitrate": item})
            if liveStreamDetected:
                link.meta["iptv_livestream"] = True
            retPlaylists.append({"name": "[f4m/hds] bitrate[%s]" % item, "url": link})

        if 0 == len(retPlaylists):
            link = strwithmeta(manifestUrl, {"iptv_proto": "f4m"})
            if liveStreamDetected:
                link.meta["iptv_livestream"] = True
            retPlaylists.append({"name": "[f4m/hds]", "url": link})
    return retPlaylists

 def __addLastVersion(self, servers):
     mainUrl = "https://gitlab.com/iptvplayer-for-e2/iptvplayer-for-e2"
     sts, data = self.cm.getPage(mainUrl + '/tree/master')
     if sts:
         crcSum = CParsingHelper.getSearchGroups(data, '"/iptvplayer-for-e2/iptvplayer-for-e2/commit/([^"]+?)">')[0]
         if 40 == len(crcSum):
             finalurl = mainUrl + '/blob/%s/IPTVPlayer/version.py' % crcSum
             sts, data = self.cm.getPage(finalurl)
             if sts:
                 newVerNum = CParsingHelper.getSearchGroups(data, '"([0-9]+\.[0-9]+\.[0-9]+\.[0-9]+)"')[0]
                 sourceUrl = mainUrl + "/repository/archive.tar.gz?ref=%s" % crcSum
                 server = {'name':'gitlab.com', 'version':newVerNum, 'url':sourceUrl, 'subdir':'iptvplayer-for-e2.git/', 'pyver':'X.X', 'packagetype':'sourcecode'}
                 printDBG("UpdateMainAppImpl.__addLastVersion server: [%s]" % str(server))
                 servers.append(server)
         else:
             printDBG("Wrong crcSum[%s]" % crcSum)

 def getArticleContent(self, cItem):
     printDBG("MoviesHDCO.getArticleContent [%s]" % cItem)
     retTab = []
     
     if 'url' not in cItem: return []
     
     sts, data = self.getPage(cItem['url'])
     if not sts: return retTab
     
     sts, data = CParsingHelper.getDataBeetwenMarkers(data, '<table id="imdbinfo">', '</table>', False)
     if not sts: return retTab
     
     tmp = data.split('</tr>')
     if len(tmp) < 2: return retTab
     
     title = self.cleanHtmlStr(tmp[0])
     if '' == title: icon = self.cm.ph.getSearchGroups(tmp[1], 'alt="([^"]+?)"')[0]
     icon  = self.cm.ph.getSearchGroups(tmp[1], 'src="([^"]+?)"')[0]
     desc  = self.cm.ph.getDataBeetwenMarkers(tmp[1], '<b>Plot:</b>', '</td>', False)[1]
     
     otherInfo = {}
     tmpTab = [{'mark':'<b>Rating:</b>',   'key':'rating'},
               {'mark':'<b>Director:</b>', 'key':'director'},
               {'mark':'<b>Writer:</b>',   'key':'writer'},
               {'mark':'<b>Stars:</b>',    'key':'stars'},
               {'mark':'<b>Runtime:</b>',  'key':'duration'},
               {'mark':'<b>Rated:</b>',    'key':'rated'},
               {'mark':'<b>Genre:</b>',    'key':'genre'},
               {'mark':'<b>Released:</b>', 'key':'released'},
     ]
     for item in tmpTab:
         val = self.cm.ph.getDataBeetwenMarkers(tmp[1], item['mark'], '</td>', False)[1]
         if '' != val: otherInfo[item['key']] =  self.cleanHtmlStr(val)
     
     return [{'title':self.cleanHtmlStr( title ), 'text': self.cleanHtmlStr( desc ), 'images':[{'title':'', 'url':self._getFullUrl(icon)}], 'other_info':otherInfo}]