ext_conf_template.txt

# cat=basic//10; type=int [0-10000]; label= Sleep time between requests: Time in milliseconds the crawler should sleep beetween requesting urls: low = faster / high = less stress for the server
sleepTime = 1000

# cat=basic//10; type=int [0-100]; label= Sleep time after finishing: Time in seconds the crawler should sleep before finishing
sleepAfterFinish=10

# cat=basic//10; type=int [1-10000]; label= Entries per run: How many queue entries should be processed in a run
countInARun=100

# cat=basic//10; type=int [1-365]; label= Delete processed items: Delete processed items from the queue after n days (0 will keep the entries forever - the database may grow very large over time!)
purgeQueueDays=14

# cat=basic//10; type=int [1-99]; label= Maximum processes
processLimit=1

# cat=basic//10; type=int [1- 86400]; label= Maximal process runtime: in secounds - only necessary if processLimit > 1
processMaxRunTime=300

# cat=basic//10; type=int [1- 86400]; label= Maximal number of URLs, which can be added to the queue at one time
maxCompileUrls=10000

# cat=basic//10; type=boolean; label= Debug: Print Multiprocess- processing informations - prints some information whether a process was really executed and which status it has
processDebug=0

# cat=basic//10; type=boolean; label= Crawl hidden pages: Crawl hidden pages (By default they won't be crawled)
crawlHiddenPages=0

# cat=basic//10; type=string; label= PHP Path: Local path to php binary file (e.g. "/usr/bin/php")
phpPath=/usr/bin/php

# cat=basic//10; type=boolean; label= Enabled Timeslot for Duplicationcheck: When this option is active items will not be queue twice for the past if theire schedule time is the currenttime +-100 seconds.
enableTimeslot=1

# cat=basic//10; type=string; label= Log Filename:
logFileName=

# cat=basic//10; type=boolean; label= Follow 301 and 302: If checked the crawler will follow the URLs (Location) given in a HTTP 301 and 302 response.
follow30x=

# cat=basic//10; type=boolean; label= Make direct requests: If checked the crawler will make direct requests by including the index.php file instead of getting the page content via http(s)
makeDirectRequests=0

# cat=basic//10; type=string; label=Frontend website base path: Base path of the website frontend (e.g. if you call http://mydomain.com/cms/index.php in the browser the base path is "/cms/"). Leave empty to use the value of config.absRefPrefix instead.
frontendBasePath=/

# cat=basic//10; type=boolean; label=Clean up old queue entries: If checked the older queue entries will be deleted when adding new crawler configurations from CLI.
cleanUpOldQueueEntries=1

# cat=basic//10; type=int [1- 99]; label=Processed Age: If Clean up old queue entries is checked, then processed entries older than X days are deleted.
cleanUpProcessedAge=2

# cat=basic//10; type=int [1- 99]; label=Scheduled Age: If Clean up old queue entries is checked, then scheduled entries older than X days are deleted.
cleanUpScheduledAge=7