Python SearchModule.sanitize_strings方法代码示例

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def generate_music_nabresponse(self):
		dstring = []
		if(self.args.has_key('artist')):
			dstring.append(SearchModule.sanitize_strings(self.args['artist']))
		if(self.args.has_key('album')):
			dstring.append(SearchModule.sanitize_strings(self.args['album']))
		if(self.args.has_key('track')):
			dstring.append(SearchModule.sanitize_strings(self.args['track']))
		if(self.args.has_key('year')):
			dstring.append(SearchModule.sanitize_strings(self.args['year']))

		music_search_str = ''
		for i in xrange(len(dstring)):
			if(len(dstring[i]) and i<len(dstring)-1):
				music_search_str = music_search_str + dstring[i]

		print music_search_str
		#~ print movie_search_str
		self.searchstring = music_search_str
		self.typesearch = 0
		#~ compile results
		#~ results = SearchModule.performSearch(movie_search_str, self.cfg )
		#~ flatten and summarize them
		#~ cleaned_results = megasearch.summary_results(results,movie_search_str)
		#~ render XML
		#~ return self.cleanUpResultsXML(cleaned_results)
		return 'm'

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
    def generate_music_nabresponse(self):
        dstring = []
        if self.args.has_key("artist"):
            dstring.append(SearchModule.sanitize_strings(self.args["artist"]))
        if self.args.has_key("album"):
            dstring.append(SearchModule.sanitize_strings(self.args["album"]))
        if self.args.has_key("track"):
            dstring.append(SearchModule.sanitize_strings(self.args["track"]))
        if self.args.has_key("year"):
            dstring.append(SearchModule.sanitize_strings(self.args["year"]))

        music_search_str = ""
        for i in xrange(len(dstring)):
            if len(dstring[i]) and i < len(dstring) - 1:
                music_search_str = music_search_str + dstring[i]

        print music_search_str
        # ~ print movie_search_str
        self.searchstring = music_search_str
        self.typesearch = 0
        # ~ compile results
        # ~ results = SearchModule.performSearch(movie_search_str, self.cfg )
        # ~ flatten and summarize them
        # ~ cleaned_results = megasearch.summary_results(results,movie_search_str)
        # ~ render XML
        # ~ return self.cleanUpResultsXML(cleaned_results)
        return "m"

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def generate_tvserie_nabresponse(self,tvrage_show ):
		#~ compile string
		season_num = self.args.get('season',-1, type=int)
		relaxed_seasonmatch = 0
		serie_search_str = SearchModule.sanitize_strings(tvrage_show['showtitle'])
		if(self.args.has_key('ep')):
			ep_num = self.args.get('ep',-1, type=int)
			serie_search_str = serie_search_str + '.s%02d' % season_num + 'e%02d' % ep_num
		else:
			serie_search_str = serie_search_str + '.s%02d' % season_num
			relaxed_seasonmatch = 1

		self.typesearch = 1
		self.searchstring = serie_search_str
		#~ compile results
		results = SearchModule.performSearch(serie_search_str, self.cfg , self.cfg_ds )

		cleaned_results = []
		if(relaxed_seasonmatch):
			#~ no cleaning just flatten in one array
			for provid in xrange(len(results)):
				if(results[provid] is not None):
					for z in xrange(len(results[provid])):
						cleaned_results.append(results[provid][z])
		else:
			#~ flatten and summarize them
			cleaned_results = megasearch.summary_results(results,serie_search_str)

		#~ render XML
		return self.cleanUpResultsXML(cleaned_results)

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def dosearch(self, args):
		#~ restore originals
		self.cfg = copy.deepcopy(self.cfg_cpy)
		
		if('q' not in args):
			self.results = []
			return self.results
		nuqry = args['q'] + ' ' + self.cgen['searchaddontxt']
		self.logic_items = self.logic_expr.findall(nuqry)
		self.qry_nologic = self.logic_expr.sub(" ",nuqry)
		if('selcat' in args):
			if(args['selcat'] != ""):
				self.qry_nologic += " " + args['selcat']

		#~ speed class
		speed_class_sel = 1	
		if('tm' in args):
			speed_class_sel = int(args['tm'])
		
		#~ speed class deepsearch
		self.ds.set_timeout_speedclass(speed_class_sel)
		#~ speed class Nabbased	
		for conf in self.cfg :
			if ( (conf['speed_class'] <=  speed_class_sel) and (conf['valid'])):
				conf['timeout']  = self.cgen['timeout_class'][ speed_class_sel ]
				#~ print conf['type'] + " " + str(conf['timeout'] ) + ' ' + str(speed_class_sel )
			else:
				conf['valid']  = 0
		 
					
		if( len(args['q']) == 0 ):
			if('selcat' in args):
				if(len(args['selcat'])==0):
					self.results = []
					return self.results
			else:
				self.results = []
				return self.results
		if(self.qry_nologic.replace(" ", "") == ""):
			self.results = []
			return self.results
						
		self.cleancache()
		#~ cache hit, no server report
		self.returncode_fine['code'] = 2
		self.resultsraw = self.chkforcache(self.wrp.chash64_encode(SearchModule.sanitize_strings(self.qry_nologic)), speed_class_sel)
		if( self.resultsraw is None):
			self.resultsraw = SearchModule.performSearch(self.qry_nologic, self.cfg, self.ds )
			self.prepareretcode();
			
		if( self.cgen['smartsearch'] == 1):
			#~ smartsearch
			self.results = summary_results(self.resultsraw, self.qry_nologic, self.logic_items)
		else:
			#~ no cleaning just flatten in one array
			self.results = []
			for provid in xrange(len(self.resultsraw)):
				for z in xrange(len(self.resultsraw[provid])):
					if (self.resultsraw[provid][z]['title'] != None):
						self.results.append(self.resultsraw[provid][z])

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def generate_tsearch_nabresponse(self):

		if(self.args.has_key('q')):
			freesearch_str = SearchModule.sanitize_strings(self.args['q'])
			self.searchstring = freesearch_str
			self.typesearch = 2
			#~ compile results
			results = SearchModule.performSearch(freesearch_str, self.cfg, self.cfg_ds )
			#~ flatten and summarize them
			cleaned_results = megasearch.summary_results(results, freesearch_str)
			#~ render XML
			return self.cleanUpResultsXML(cleaned_results)

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def prepareforquery_show(self, sugg_info_raw, lastepisode, sugg_info):	
		
		for i in xrange(len(lastepisode)):
			si = {'searchstr': SearchModule.sanitize_strings(sugg_info_raw['title']) 
								+ '.S%02d' % int(lastepisode[i]['season']) 
								+  'E%02d' %  int(lastepisode[i]['ep']),
				  'prettytxt': sugg_info_raw['title'] +  ' S%02d ' %  int(lastepisode[i]['season']) 
								+ 'E%02d' %  int(lastepisode[i]['ep']),
				  'imdb_url': sugg_info_raw['tvdb_url']}
			sugg_info.append(si)
		
		return sugg_info 

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def prepareforquery(self, sugg_info_raw):	
		
		sugg_info = []
		for i in xrange(len(sugg_info_raw)):
			shorinfo = sugg_info_raw[i]['title']
			if (len(shorinfo) > MAX_CHAR_LEN):
				shorinfo = shorinfo[0:MAX_CHAR_LEN-2] + '..'
			si = {'searchstr': SearchModule.sanitize_strings(sugg_info_raw[i]['title']) +  '.' + sugg_info_raw[i]['year'] ,
				  'prettytxt': shorinfo + '('+ sugg_info_raw[i]['year'] + ')',
				  'imdb_url': sugg_info_raw[i]['imdb_url']}
			
			sugg_info.append(si)	  			
			#~ print si
			#~ print 'dcdddddddddddddddd'

		return sugg_info

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def generate_tvserie_nabresponse(self,tvrage_show ):
		#~ compile string
		season_num = self.args.get('season',-1, type=int)
		serie_search_str = SearchModule.sanitize_strings(tvrage_show['showtitle'])
		if(self.args.has_key('ep')):
			ep_num = self.args.get('ep',-1, type=int)			
			serie_search_str = serie_search_str + '.s%02d' % season_num + 'e%02d' % ep_num
		else:	
			serie_search_str = serie_search_str + '.s%02d' % season_num 
		self.typesearch = 1
		self.searchstring = serie_search_str
		#~ compile results				
		results = SearchModule.performSearch(serie_search_str, self.cfg )		
		#~ flatten and summarize them
		cleaned_results = megasearch.summary_results(results,serie_search_str)
		#~ render XML
		return self.cleanUpResultsXML(cleaned_results)

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
def summary_results(rawResults, strsearch, logic_items=[], results_stats={}):
    results = []
    titles = []
    sptitle_collection = []

    # ~ stats for each provider
    for provid in xrange(len(rawResults)):
        if (len(rawResults[provid])):
            results_stats[str(rawResults[provid][0]['providertitle'])] = [len(rawResults[provid]), 0]

    # ~ all in one array
    for provid in xrange(len(rawResults)):
        for z in xrange(len(rawResults[provid])):
            if (rawResults[provid][z]['title'] != None):
                rawResults[provid][z]['title'] = SearchModule.sanitize_html(rawResults[provid][z]['title'])
                rawResults[provid][z]['provid'] = provid
                title = SearchModule.sanitize_strings(rawResults[provid][z]['title'])
                titles.append(title)
                sptitle_collection.append(Set(title.split(".")))
                results.append(rawResults[provid][z])

    strsearch1 = SearchModule.sanitize_strings(strsearch)
    strsearch1_collection = Set(strsearch1.split("."))

    rcount = [0] * 3
    for z in xrange(len(results)):
        findone = 0
        results[z]['ignore'] = 0
        intrs = strsearch1_collection.intersection(sptitle_collection[z])
        if (len(intrs) == len(strsearch1_collection)):
            findone = 1
        else:
            results[z]['ignore'] = 2
            # ~ relax the search ~ 0.45
            unmatched_terms_search = strsearch1_collection.difference(intrs)
            unmatched_count = 0
            for mst in unmatched_terms_search:
                my_list = [i for i in sptitle_collection[z] if i.find(mst) == 0]
                if (len(my_list)):
                    unmatched_count = unmatched_count + 1
                if (unmatched_count == len(unmatched_terms_search)):
                    findone = 1
                    results[z]['ignore'] = 0
                # ~ print unmatched_terms_search
                # ~ print unmatched_count
                # ~ print unmatched_terms_search


        # ~ print strsearch1_collection
        # ~ print intrs
        # ~ print findone
        # ~ print '------------------'

        if (findone and results[z]['ignore'] == 0):
            # ~ print titles[z]
            for v in xrange(z + 1, len(results)):
                if (titles[z] == titles[v]):
                    sz1 = float(results[z]['size'])
                    sz2 = float(results[v]['size'])
                    if (abs(sz1 - sz2) < 5000000):
                        results[z]['ignore'] = 1
        # ~ stats
        rcount[results[z]['ignore']] += 1

    # ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~
    # ~ logic params
    exclude_coll = Set([])
    include_coll = Set([])
    # ~ print '*'+logic_items[0][1]+'*'
    for i in xrange(len(logic_items)):
        if (logic_items[i][0] == '-'):
            exclude_coll.add(logic_items[i][1])
        if (logic_items[i][0] == '+'):
            include_coll.add(logic_items[i][1])
    if (len(include_coll)):
        for z in xrange(len(results)):
            if (results[z]['ignore'] < 2):
                intrs_i = include_coll.intersection(sptitle_collection[z])
                if (len(intrs_i) == 0):
                    results[z]['ignore'] = 2
    if (len(exclude_coll)):
        for z in xrange(len(results)):
            if (results[z]['ignore'] < 2):
                intrs_e = exclude_coll.intersection(sptitle_collection[z])
                if (len(intrs_e) > 0):
                    results[z]['ignore'] = 2
    # ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~

    mssg = 'Overall search stats: [' + strsearch1 + ']' + ' [' + strsearch + '] ' + str(rcount[0]) + ' ' + str(
        rcount[1]) + ' ' + str(rcount[2])
    log.info(mssg)

    for z in xrange(len(results)):
        if (results[z]['ignore'] != 2):
            results_stats[str(results[z]['providertitle'])][1] = results_stats[str(results[z]['providertitle'])][1] + 1
    return results

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]

#.........这里部分代码省略.........
                continue

            if (results[i]['ignore'] == 1):
                existduplicates = 1

            # Convert sized to smallest SI unit (note that these are powers of 10, not powers of 2, i.e. OS X file sizes rather than Windows/Linux file sizes)
            szf = float(results[i]['size'] / 1000000.0)
            mgsz = ' MB '
            if (szf > 1000.0):
                szf = szf / 1000
                mgsz = ' GB '
            fsze1 = str(round(szf, 1)) + mgsz

            if (results[i]['size'] == -1):
                fsze1 = 'N/A'
            totdays = results[i]['posting_date_timestamp_refined']
            if (totdays < 1):
                totdays = str(int(totdays * 100)) + "h"
            else:
                totdays = str(int(totdays)) + "d"

            category_str = ''
            keynum = len(results[i]['categ'])
            keycount = 0
            for key in results[i]['categ'].keys():
                category_str = category_str + key
                keycount = keycount + 1
                if (keycount < keynum):
                    category_str = category_str + ' - '
            if (results[i]['url'] is None):
                results[i]['url'] = ""

            qryforwarp = self.wrp.chash64_encode(results[i]['url'])
            if ('req_pwd' in results[i]):
                qryforwarp += '&m=' + results[i]['req_pwd']
            niceResults.append({
                'id': i,
                'url': results[i]['url'],
                'url_encr': 'warp?x=' + qryforwarp,
                'title': results[i]['title'],
                'filesize': fsze1,
                'cat': category_str.upper(),
                'age': totdays,
                'details': results[i]['release_comments'],
                'details_deref': 'http://www.derefer.me/?' + results[i]['release_comments'],
                'providerurl': results[i]['provider'],
                'providertitle': results[i]['providertitle'],
                'ignore': results[i]['ignore'],
                'predb': results[i]['predb'],
                'predb_lnk': results[i]['predb_lnk']
            })
        send2nzbget_exist = None
        if ('nzbget_url' in self.cgen):
            if (len(self.cgen['nzbget_url'])):
                send2nzbget_exist = self.sckname

        send2sab_exist = None
        if ('sabnzbd_url' in self.cgen):
            if (len(self.cgen['sabnzbd_url'])):
                send2sab_exist = self.sckname
        speed_class_sel = 1
        if ('tm' in args):
            speed_class_sel = int(args['tm'])

        # ~ save for caching
        if (self.resultsraw is not None):
            if (self.cgen['cache_active'] == 1 and len(self.resultsraw) > 0):
                if (len(self.collect_info) < self.cgen['max_cache_qty']):
                    if (self.chkforcache(self.wrp.chash64_encode(SearchModule.sanitize_strings(self.qry_nologic)),
                                         speed_class_sel) is None):
                        collect_all = {}
                        collect_all['searchstr'] = self.wrp.chash64_encode(
                            SearchModule.sanitize_strings(self.qry_nologic))
                        collect_all['tstamp'] = time.time()
                        collect_all['resultsraw'] = self.resultsraw
                        collect_all['speedclass'] = speed_class_sel
                        self.collect_info.append(collect_all)
                    # ~ print 'Result added to the cache list'
        # ~ ~ ~ ~ ~ ~ ~ ~ ~
        scat = ''
        if ('selcat' in params['args']):
            scat = params['args']['selcat']

        return render_template('main_page.html', results=niceResults, exist=existduplicates,
                               vr=ver_notify, args=args, nc=svalid, sugg=sugg_list,
                               speed_class_sel=speed_class_sel,
                               send2sab_exist=send2sab_exist,
                               send2nzbget_exist=send2nzbget_exist,
                               cgen=self.cgen,
                               trend_show=params['trend_show'],
                               trend_movie=params['trend_movie'],
                               debug_flag=params['debugflag'],
                               sstring=params['args']['q'],
                               scat=scat,
                               selectable_opt=params['selectable_opt'],
                               search_opt=params['search_opt'],
                               sid=params['sid'],
                               servercode_return=self.returncode_fine,
                               large_server=self.cgen['large_server'],
                               motd=params['motd'])

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
    def dosearch(self, args):
        # ~ restore originals
        self.cfg = copy.deepcopy(self.cfg_cpy)

        if ('q' not in args):
            self.results = []
            return self.results
        nuqry = args['q'] + ' ' + self.cgen['searchaddontxt']
        self.logic_items = self.logic_expr.findall(nuqry)
        self.qry_nologic = self.logic_expr.sub(" ", nuqry)
        if ('selcat' in args):
            if (args['selcat'] != ""):
                self.qry_nologic += " " + args['selcat']

        # ~ speed class
        speed_class_sel = 1
        if ('tm' in args):
            speed_class_sel = int(args['tm'])

        # ~ speed class deepsearch
        self.ds.set_extraopt(speed_class_sel, 'manual')
        # ~ speed class Nabbased
        self.set_timeout_speedclass(speed_class_sel)
        # ~ manual search Nabbased
        self.set_extraopt()

        if (len(args['q']) == 0):
            if ('selcat' in args):
                if (len(args['selcat']) == 0):
                    self.results = []
                    return self.results
            else:
                self.results = []
                return self.results
        if (self.qry_nologic.replace(" ", "") == ""):
            self.results = []
            return self.results

        log.info('TYPE OF SEARCH: ' + str(speed_class_sel))

        self.cleancache()
        # ~ cache hit, no server report
        cachehit = True
        self.returncode_fine['code'] = 2
        self.resultsraw = self.chkforcache(self.wrp.chash64_encode(SearchModule.sanitize_strings(self.qry_nologic)),
                                           speed_class_sel)
        if (self.resultsraw is None):
            self.resultsraw = SearchModule.performSearch(self.qry_nologic, self.cfg, self.ds)
            cachehit = False

        if (self.cgen['smartsearch'] == 1):
            # ~ smartsearch
            self.res_results = {}
            self.results = summary_results(self.resultsraw, self.qry_nologic, self.logic_items, self.res_results)
        else:
            # ~ no cleaning just flatten in one array
            self.results = []
            self.res_results = {}
            for provid in xrange(len(self.resultsraw)):
                if (len(self.resultsraw[provid])):
                    self.res_results[str(self.resultsraw[provid][0]['providertitle'])] = [len(self.resultsraw[provid]),
                                                                                          0]
            for provid in xrange(len(self.resultsraw)):
                for z in xrange(len(self.resultsraw[provid])):
                    if (self.resultsraw[provid][z]['title'] != None):
                        self.results.append(self.resultsraw[provid][z])

        # ~ server status output
        if (cachehit == False):
            self.prepareretcode();

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
	def ask(self, arguments):
		self.args = arguments
		self.search_str = SearchModule.sanitize_strings(self.args['q']).replace(".", " ") 
		movieinfo = self.imdb_titlemovieinfo()
		sugg_info_raw = self.movie_bestmatch(movieinfo)
		self.sugg_info = self.prepareforquery(sugg_info_raw)

# 需要导入模块: import SearchModule [as 别名]
# 或者: from SearchModule import sanitize_strings [as 别名]
def summary_results(rawResults, strsearch, logic_items=[]):

    results = []
    titles = []
    sptitle_collection = []

    # ~ all in one array
    for provid in xrange(len(rawResults)):
        for z in xrange(len(rawResults[provid])):
            rawResults[provid][z]["title"] = SearchModule.sanitize_html(rawResults[provid][z]["title"])
            title = SearchModule.sanitize_strings(rawResults[provid][z]["title"])
            titles.append(title)
            sptitle_collection.append(Set(title.split(".")))
            results.append(rawResults[provid][z])

    strsearch1 = SearchModule.sanitize_strings(strsearch)
    strsearch1_collection = Set(strsearch1.split("."))

    rcount = [0] * 3
    for z in xrange(len(results)):
        findone = 0
        results[z]["ignore"] = 0
        intrs = strsearch1_collection.intersection(sptitle_collection[z])
        if len(intrs) == len(strsearch1_collection):
            findone = 1
        else:
            results[z]["ignore"] = 2

            # ~ print strsearch1_collection
            # ~ print intrs
            # ~ print findone
            # ~ print '------------------'

        if findone and results[z]["ignore"] == 0:
            # ~ print titles[z]
            for v in xrange(z + 1, len(results)):
                if titles[z] == titles[v]:
                    sz1 = float(results[z]["size"])
                    sz2 = float(results[v]["size"])
                    if abs(sz1 - sz2) < 5000000:
                        results[z]["ignore"] = 1
                        # ~ stats
        rcount[results[z]["ignore"]] += 1

        # ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~
        # ~ logic params
    exclude_coll = Set([])
    include_coll = Set([])
    # ~ print '*'+logic_items[0][1]+'*'
    for i in xrange(len(logic_items)):
        if logic_items[i][0] == "-":
            exclude_coll.add(logic_items[i][1])
        if logic_items[i][0] == "+":
            include_coll.add(logic_items[i][1])
    if len(include_coll):
        for z in xrange(len(results)):
            if results[z]["ignore"] < 2:
                intrs_i = include_coll.intersection(sptitle_collection[z])
                if len(intrs_i) == 0:
                    results[z]["ignore"] = 2
    if len(exclude_coll):
        for z in xrange(len(results)):
            if results[z]["ignore"] < 2:
                intrs_e = exclude_coll.intersection(sptitle_collection[z])
                if len(intrs_e) > 0:
                    results[z]["ignore"] = 2
                # ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~

    mssg = (
        "[" + strsearch1 + "]" + " [" + strsearch + "] " + str(rcount[0]) + " " + str(rcount[1]) + " " + str(rcount[2])
    )
    print mssg
    log.info(mssg)

    return results