Python helpers.get_xml_text函数代码示例

    def _get_title_and_url(self, item):
        
        title, url = None, None

        self.cache._remove_namespace(item)

        title = helpers.get_xml_text(item.find('title'))
        
        attempt_list = [lambda: helpers.get_xml_text(item.find('magnetURI')),
                        
                        lambda: item.find('enclosure').get('url'),
                        
                        lambda: helpers.get_xml_text(item.find('link'))]

        
        for cur_attempt in attempt_list:
            try:
                url = cur_attempt()
            except:
                continue
        
            if title and url:
                return (title, url)
            
        return (title, url)

    def _get_title_and_url(self, item):
        """
        Retrieves the title and URL data from the item XML node.
        Overridden here so that we can have a preference for magnets.
        
        item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed
        Returns: A tuple containing two strings representing title and URL respectively
        """
        title = helpers.get_xml_text(item.getElementsByTagName("title")[0])
        url = None
        try:
            if sickbeard.PREFER_MAGNETS:
                try:
                    url = helpers.get_xml_text(item.getElementsByTagName("magnetURI")[0])
                    torrent_hash = self.getHashFromMagnet(url)
                    if not torrent_hash:
                        logger.log(
                            u'magnetURI "%s" found for "%s", but it has no valid hash - ignoring' % (url, title),
                            logger.WARNING,
                        )
                        url = None
                except Exception:
                    pass
            if url is None:
                url = helpers.get_xml_text(item.getElementsByTagName("link")[0])
                if url:
                    url = url.replace("&amp;", "&")
        except IndexError:
            url = None

        return (title, url)

    def _get_title_and_url(self, item):
        title = helpers.get_xml_text(item.find('title'))
        # logger.log('publichd got title' + title)
        url = None
        if sickbeard.PREFER_MAGNETS:
            magnetURI = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}magnetURI'))
            # logger.log('publichd got magnetURI' + magnetURI)
            if magnetURI:
                url = magnetURI

        if not url:
            enclos = item.find('enclosure')
            if enclos is not None:
                url = enclos.get('url')
                # logger.log('publichd got enclosure url ' + url)
                if url:
                    url = url.replace('&', '&')

        if title.startswith('[TORRENT] '):
            title = title[10:]

        # these guys also get creative with the torrent names, adding crud at the
        # end like "[PublicHD]", "[P2PDL]" etc. which confuses sb.  Best to
        # just remove it if present
        crudAtEndMatch = re.match(r'(.*) \[\w+\]$', title)
        if crudAtEndMatch:
            title = crudAtEndMatch.group(1)

        return (title, url)

    def _doSearch(self, searchString, show=None, season=None, french=None):
        results = []
        searchUrl = self.url+'rdirect.php?type=search&'+searchString.replace('!','')
        logger.log(u"Search URL: " + searchUrl, logger.DEBUG)
        
        data = self.getURL(searchUrl)
        if "bad key" in str(data).lower() :
            logger.log(u"GKS key invalid, check your config", logger.ERROR)
            return []

        parsedXML = parseString(data)
        channel = parsedXML.getElementsByTagName('channel')[0]
        description = channel.getElementsByTagName('description')[0]
        description_text = helpers.get_xml_text(description).lower()
        
        if "user can't be found" in description_text:
            logger.log(u"GKS invalid digest, check your config", logger.ERROR)
            return []
        elif "invalid hash" in description_text:
            logger.log(u"GKS invalid hash, check your config", logger.ERROR)
            return []
        else :
            items = channel.getElementsByTagName('item')
            for item in items:
                title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
                if "aucun resultat" in title.lower() :
                    logger.log(u"No results found in " + searchUrl, logger.DEBUG)
                    return []
                count=1
                if season:
                    count=0
                    if show:
                        if show.audio_lang=='fr' or french:
                            for frword in['french', 'truefrench', 'multi']:
                                if frword in title.lower():
                                    count+=1
                        else:
                            count +=1
                    else:
                        count +=1
                if count==0:
                    continue                                
                else :
                    downloadURL = helpers.get_xml_text(item.getElementsByTagName('link')[0])
                    quality = Quality.nameQuality(title)
                    if quality==Quality.UNKNOWN and title:
                        if '720p' not in title.lower() and '1080p' not in title.lower():
                            quality=Quality.SDTV
                    if show and french==None:
                        results.append( GksSearchResult( self.opener, title, downloadURL, quality, str(show.audio_lang) ) )
                    elif show and french:
                        results.append( GksSearchResult( self.opener, title, downloadURL, quality, 'fr' ) )
                    else:
                        results.append( GksSearchResult( self.opener, title, downloadURL, quality ) )
        return results

    def _parseItem(self, item):
        title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
        url = helpers.get_xml_text(item.getElementsByTagName('link')[0])

        if not title or not url:
            logger.log("The XML returned from the FreshOnTV RSS feed is incomplete, this result is unusable", logger.ERROR)
            return

        logger.log("Adding item from RSS to cache: " + title, logger.DEBUG)
        self._addCacheEntry(title, url,
                            quality=common.Quality.nameQuality(title))

    def _get_title_and_url(self, item):
        """
        Retrieves the title and URL data from the item XML node

        item: An xml.dom.minidom.Node representing the <item> tag of the RSS feed

        Returns: A tuple containing two strings representing title and URL respectively
        """
        title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
        url = helpers.get_xml_text(item.getElementsByTagName('link')[0])
        if url:
            url = url.replace('&amp;','&')
        
        return (title, url)

 def _get_title_and_url(self, item):
     title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
     url = item.getElementsByTagName('enclosure')[0].getAttribute('url').replace('&','&')
     if title.startswith('[TORRENT] '):
         title = title[10:]    
     
     return (title, url)

    def _get_title_and_url(self, item):
        (title, url) = generic.TorrentProvider._get_title_and_url(self, item)
        
        if url and url.startswith(('http://twitter.com/', 'https://twitter.com/')):
            # this feed came from twitter
            #
            # we need to extract the filename and url from the twitter message (the url we have currently is just that of the twitter message,
            # which is of little use to us).
            # The message looks something like this:
            # eztv_it: History Ch The Universe Season 4 08of12 Space Wars XviD AC3 [MVGroup org] - http://t.co/mGTrhB4a
            #
            # Start by splitting the (real) url from the filename
            title, url = title.rsplit(' - http', 1)
            url = 'http' + url
            
            # Then strip off the leading eztv_it:
            if title.startswith('eztv_it:'):
                title = title[8:]
                
            # For safety we remove any whitespace too.
            title = title.strip()
            
            logger.log(u"Extracted the name %s and url %s from the twitter link"%(title, url), logger.DEBUG)
        else:
            # this feed came from ezrss
            torrent_node = item.getElementsByTagName('torrent')[0]
            filename_node = torrent_node.getElementsByTagName('fileName')[0]
            filename = get_xml_text(filename_node)
        
            new_title = self._extract_name_from_filename(filename)
            if new_title:
                title = new_title
                logger.log(u"Extracted the name "+title+" from the torrent link", logger.DEBUG)

        return (title, url)

    def _get_title_and_url(self, item):
        #(title, url) = generic.TorrentProvider._get_title_and_url(self, item)

        title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
        
        url = None
            # if we have a preference for magnets, go straight for the throat...
        try:
            url = helpers.get_xml_text(item.getElementsByTagName('magnetURI')[0])
        except Exception:
            pass
                
        if url is None:
            url = item.getElementsByTagName('enclosure')[0].getAttribute('url').replace('&','&')

        return (title, url)

    def _get_title_and_url(self, item):
        (title, url) = generic.TorrentProvider._get_title_and_url(self, item)

        filename = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}fileName'))
        magnet = helpers.get_xml_text(item.find('{http://xmlns.ezrss.it/0.1/}torrent/{http://xmlns.ezrss.it/0.1/}magnetURI'))

        if filename:
            new_title = self._extract_name_from_filename(filename)
            if new_title:
                title = new_title
                logger.log(u"Extracted the name " + title + " from the torrent link", logger.DEBUG)

        if self.useMagnet() and magnet:
            url = magnet

        return (title, url)

    def findPropers(self, search_date=None):

        search_terms = ['.proper.', '.repack.']

        cache_results = self.cache.listPropers(search_date)
        results = [classes.Proper(x['name'], x['url'], datetime.datetime.fromtimestamp(x['time'])) for x in cache_results]

        for term in search_terms:
            for item in self._doSearch({'q': term}, max_age=4):

                (title, url) = self._get_title_and_url(item)

                description_node = item.find('pubDate')
                description_text = helpers.get_xml_text(description_node)

                try:
                    # we could probably do dateStr = descriptionStr but we want date in this format
                    date_text = re.search('(\w{3}, \d{1,2} \w{3} \d{4} \d\d:\d\d:\d\d) [\+\-]\d{4}', description_text).group(1)
                except:
                    date_text = None

                if not date_text:
                    logger.log(u"Unable to figure out the date for entry " + title + ", skipping it")
                    continue
                else:

                    result_date = email.utils.parsedate(date_text)
                    if result_date:
                        result_date = datetime.datetime(*result_date[0:6])

                if not search_date or result_date > search_date:
                    search_result = classes.Proper(title, url, result_date)
                    results.append(search_result)

        return results

    def _parseItem(self, item):

        title = helpers.get_xml_text(item.getElementsByTagName('title')[0])
        url = helpers.get_xml_text(item.getElementsByTagName('link')[0])

        self._checkItemAuth(title, url)

        if not title or not url:
            logger.log(u"The XML returned from the "+self.provider.name+" feed is incomplete, this result is unusable", logger.ERROR)
            return

        url = self._translateLinkURL(url)

        logger.log(u"Adding item from RSS to cache: "+title, logger.DEBUG)

        self._addCacheEntry(title, url)

    def _get_title_and_url(self, item):
        (title, url) = generic.TorrentProvider._get_title_and_url(self, item)
        
        
        try:
            # ezrss feed will have a 'torrent' node
            torrent_node = item.getElementsByTagName('torrent')[0]
            filename_node = torrent_node.getElementsByTagName('fileName')[0]
            filename = get_xml_text(filename_node)
        
            new_title = self._extract_name_from_filename(filename)
            if new_title:
                title = new_title
                logger.log(u"Extracted the name "+title+" from the torrent link", logger.DEBUG)
        except IndexError:
            # we'll get an IndexError above when there's no 'torrent' node,
            # which likely means that this isn't in the special ezrss format.
            # So assume we're working with with a standard rss feed.
            logger.log(u"IndexError while parsing the ezrss feed, maybe it's just standard RSS? Trying that ...", logger.DEBUG)
            (title, url) = generic.TorrentProvider._get_title_and_url(self, item)
                
        # feedburner adds "[eztv] " to the start of all titles, so trim it off
        if title and title[:7] == "[eztv] ":
            title = title[7:]
            logger.log(u"Trimmed [eztv] from title to get %s" % title, logger.DEBUG)
            
        # ditto VTV:
        if title and title[:6] == "[VTV] ":
            title = title[6:]
            logger.log(u"Trimmed [VTV] from title to get %s" % title, logger.DEBUG)

        return (title, url)

    def getQuality(self, item):
        attributes = item.report[0]
        attr_dict = {}

        for attribute in attributes.getElementsByTagName('report:attribute'):
            cur_attr = attribute.getAttribute('type')
            cur_attr_value = helpers.get_xml_text(attribute)
            if cur_attr not in attr_dict:
                attr_dict[cur_attr] = [cur_attr_value]
            else:
                attr_dict[cur_attr].append(cur_attr_value)

        logger.log("Finding quality of item based on attributes " + str(attr_dict), logger.DEBUG)

        if self._is_SDTV(attr_dict):
            quality = Quality.SDTV
        elif self._is_SDDVD(attr_dict):
            quality = Quality.SDDVD
        elif self._is_HDTV(attr_dict):
            quality = Quality.HDTV
        elif self._is_WEBDL(attr_dict):
            quality = Quality.HDWEBDL
        elif self._is_720pBluRay(attr_dict):
            quality = Quality.HDBLURAY
        elif self._is_1080pBluRay(attr_dict):
            quality = Quality.FULLHDBLURAY
        else:
            quality = Quality.UNKNOWN

        logger.log("Resulting quality: " + str(quality), logger.DEBUG)

        return quality

    def _get_title_and_url(self, item):
        description_node = item.getElementsByTagName("description")[0]

        title = get_xml_text(description_node).replace("_", ".").split(" (")[0]
        url = item.getElementsByTagName("enclosure")[0].getAttribute("url")

        return (title, url)