Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 21:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

(crawler, EXPERIMENT) Disable content type probing and use Accept header instead

Browse Source 
There's reason to think this may speed up crawling quite significantly, and the benefits of the probing aren't quite there.
This commit is contained in:
Viktor Lofgren 2024-09-30 14:53:01 +02:00
parent 90a2d4ae38
commit ecb5eedeae
2 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
code/processes/crawling-process/java/nu/marginalia/crawl/fetcher/HttpFetcherImpl.java
View File

@ -218,7 +218,7 @@ public class HttpFetcherImpl implements HttpFetcher {
getBuilder.url(url.toString())
.addHeader("Accept-Encoding", "gzip")
.addHeader("Accept-Language", "en,*;q=0.5")
.addHeader("Accept", "text/html, application/xhtml+xml, */*;q=0.8")
.addHeader("Accept", "text/html, application/xhtml+xml, text/*;q=0.8")
.addHeader("User-agent", userAgentString);
contentTags.paint(getBuilder);

6
code/processes/crawling-process/java/nu/marginalia/crawl/retreival/CrawlerRetreiver.java
View File

@ -321,6 +321,9 @@ public class CrawlerRetreiver implements AutoCloseable {
long probeStart = System.currentTimeMillis();
/*
probing is on probation for now while we evaluate how much the added delays slows down the crawler
if (probeType == HttpFetcher.ProbeType.FULL) {
for (int i = 0; i <= HTTP_429_RETRY_LIMIT; i++) {
try {
@ -348,9 +351,10 @@ public class CrawlerRetreiver implements AutoCloseable {
return new HttpFetchResult.ResultException(ex);
}
}
}
timer.waitFetchDelay(System.currentTimeMillis() - probeStart);
}*/
for (int i = 0; i <= HTTP_429_RETRY_LIMIT; i++) {
try {