mirror of
https://github.com/internetarchive/heritrix3.git
synced 2026-09-26 15:46:31 +00:00
[HER-1641] migration tool to convert Heritrix 1.14.x order.xml to H3 crawler-beans.cxml
* H1toH3.map
order-XPath-to-override-key map for translating simple H1 settings to H3 overrides
This commit is contained in:
@@ -26,9 +26,9 @@ seeds.textSource.path //controller/*[@name="scope"]/*[@name="seedsfile"] seeds.t
|
||||
?scope.rules[3].maxSpeculativeHops //controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfTranscluded"]/*[@name="max-speculative-hops"] 1
|
||||
?scope.rules[6].maxRepetitions //controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="rejectIfPathological"]/*[@name="max-repetitions"] 2
|
||||
?scope.rules[7].maxPathDepth //controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="rejectIfTooManyPathSegs"]/*[@name="max-path-depth"] 20
|
||||
//controller/*[@name="http-headers"]/*[@name="user-agent"] Mozilla/5.0 (compatible; heritrix/@VERSION@ +PROJECT_URL_HERE)
|
||||
//controller/*[@name="http-headers"]/*[@name="from"] CONTACT_EMAIL_ADDRESS_HERE
|
||||
//controller/*[@name="robots-honoring-policy"]/*[@name="type"] classic
|
||||
*metadata.userAgentTemplate //controller/*[@name="http-headers"]/*[@name="user-agent"] Mozilla/5.0 (compatible; heritrix/@VERSION@ +PROJECT_URL_HERE)
|
||||
metadata.operatorFrom //controller/*[@name="http-headers"]/*[@name="from"] CONTACT_EMAIL_ADDRESS_HERE
|
||||
//controller/*[@name="robots-honoring-policy"]/*[@name="type"] classic
|
||||
//controller/*[@name="robots-honoring-policy"]/*[@name="masquerade"] false
|
||||
//controller/*[@name="frontier"]/*[@name="delay-factor"] 4.0
|
||||
//controller/*[@name="frontier"]/*[@name="max-delay-ms"] 20000
|
||||
|
||||
Reference in New Issue
Block a user