mirror of
https://github.com/MarginaliaSearch/MarginaliaSearch.git
synced 2025-02-24 13:19:02 +00:00
(crawler) Send "Accept"-headers when fetching documents, also indicate we prefer English results
This commit is contained in:
parent
206a7ce6c1
commit
b4eac2516e
@ -183,6 +183,8 @@ public class HttpFetcherImpl implements HttpFetcher {
|
|||||||
|
|
||||||
getBuilder.url(url.toString())
|
getBuilder.url(url.toString())
|
||||||
.addHeader("Accept-Encoding", "gzip")
|
.addHeader("Accept-Encoding", "gzip")
|
||||||
|
.addHeader("Accept-Language", "en,*;q=0.5")
|
||||||
|
.addHeader("Accept", "text/html, application/xhtml+xml, */*;q=0.8")
|
||||||
.addHeader("User-agent", userAgentString);
|
.addHeader("User-agent", userAgentString);
|
||||||
|
|
||||||
contentTags.paint(getBuilder);
|
contentTags.paint(getBuilder);
|
||||||
@ -225,6 +227,7 @@ public class HttpFetcherImpl implements HttpFetcher {
|
|||||||
|
|
||||||
getBuilder.url(url.toString())
|
getBuilder.url(url.toString())
|
||||||
.addHeader("Accept-Encoding", "gzip")
|
.addHeader("Accept-Encoding", "gzip")
|
||||||
|
.addHeader("Accept", "text/*, */*;q=0.9")
|
||||||
.addHeader("User-agent", userAgentString);
|
.addHeader("User-agent", userAgentString);
|
||||||
|
|
||||||
HttpFetchResult result = recorder.fetch(client, getBuilder.build());
|
HttpFetchResult result = recorder.fetch(client, getBuilder.build());
|
||||||
|
Loading…
Reference in New Issue
Block a user