Kaltura API Python Script for adding tags to all entries in the account

addTagsToAllKalturaEntries.py

# This script loops through all media entries in a given Kaltura account
# and sets tags to all entries (it also checks if a list of tags is not already set on the entry before adding)
# this script requires the Kaltura Python 2.7 client library: http://www.kaltura.com/api_v3/testme/client-libs.php

import sys
import os

sys.path.append(os.path.join(os.path.dirname(__file__), '..'))

from KalturaClient import *
from KalturaClient.Base import *
from KalturaClient.Plugins.Core import *

# set the tags (comma seperated string) and list of tags to check (if exist on the entry, will not add the tagsToAdd)
tagsToAdd = "captionasr"
tagsToCheck = [tagsToAdd,'processing','caption complete']

# Kaltura Account credentials (make sure to replace partner_id and admin_secret)
# from: http://kmc.kaltura.com/index.php/kmc/kmc4#account|integration
PARTNER_ID = 000000
ADMIN_SECRET = "your-Kaltura-API-Admin-Secret"
SERVICE_URL = "http://www.kaltura.com"
USER_NAME = "taggerUser"
PAGE_SIZE = 100
METADATA_PROFILE_COUNT = 1

# client setup
class KalturaLogger(IKalturaLogger):
    def log(self, msg):
        pass

def GetConfig():
    config = KalturaConfiguration(PARTNER_ID)
    config.serviceUrl = SERVICE_URL
    config.setLogger(KalturaLogger())
    return config

# create session
client = KalturaClient(GetConfig())

ks = client.generateSession(ADMIN_SECRET, USER_NAME, KalturaSessionType.ADMIN, PARTNER_ID, 86400, "")
client.setKs(ks)

# initialize state
lastUpdatedAt = None
lastEntryIds = []

# template entry to update with:
templateMediaEntry = KalturaMediaEntry()

while True:
    # build the filter
    filter = KalturaMediaEntryFilter(
        orderBy=KalturaMediaEntryOrderBy.UPDATED_AT_DESC)
    if lastUpdatedAt != None:
        filter.setUpdatedAtLessThanOrEqual(lastUpdatedAt)
    if lastEntryIds != []:
        filter.setIdNotIn(','.join(lastEntryIds))

    # get the entries        
    results = client.media.list(filter, KalturaFilterPager(pageSize=PAGE_SIZE))
    print 'got %d entries' % len(results.objects)

    # update state (prepare all updates in one multirequest batch)
    client.startMultiRequest()
    for curEntry in results.objects:
        if max(map(lambda x: curEntry.tags.find(x), tagsToCheck)) < 0:
            templateMediaEntry.tags = curEntry.tags + ',' + tagsToAdd
            updatedEntry = client.media.update(curEntry.id, templateMediaEntry)
            print 'updated entry: %s with tags: %s' % (curEntry.id, templateMediaEntry.tags)
        if lastUpdatedAt != curEntry.getUpdatedAt():
            lastEntryIds = []       # clear the last ids, the entries will not be returned anyway due to the updatedAt<= condition
        lastEntryIds.append(curEntry.id)
        lastUpdatedAt = curEntry.getUpdatedAt()
    # execute the update multirequest batch
    updatedEntries = client.doMultiRequest()

    if len(results.objects) < PAGE_SIZE:
        break

So, the way to get the next page of results is to build a list of object IDs that were already seen, then do the same search with those IDs excluded?

Doesn't Kaltura offer something like a results.getNextPage() method‽

If not, wouldn't it be better to just update the pageIndex property of an instance of KalturaFilterPager to get the next page?