Archives/bathyscaphe
2
0
Fork 0
mirror of https://github.com/creekorful/bathyscaphe synced 2024-11-19 15:25:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Some cleanup

Browse Source
This commit is contained in:
Aloïs Micard 2020-09-22 17:08:24 +02:00
parent fa348dca5d
commit e61dc42d3c
No known key found for this signature in database
GPG Key ID: 1A0EB82F071F5EFE
3 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -32,7 +32,7 @@ Ensure you have at least 3GB of memory as the Elasticsearch stack docker will re
# How to start the crawling process
Since the API is explosed on localhost:15005, one can use it to start the crawling process:
Since the API is exposed on localhost:15005, one can use it to start the crawling process:
using trandoshanctl executable:

3
internal/extractor/extractor.go
View File

@ -84,7 +84,7 @@ func handleMessage(apiClient api.Client) natsutil.MsgHandler {
// Extract & process resource
resDto, urls, err := extractResource(resMsg)
if err != nil {
log.Err(err).Msg("Ersror while extracting resource")
log.Err(err).Msg("Error while extracting resource")
return err
}
@ -148,7 +148,6 @@ func extractTitle(body string) string {
return ""
}
// TODO improve
startPos := strings.Index(cleanBody, "<title>") + len("<title>")
endPos := strings.Index(cleanBody, "</title>")

4
internal/trandoshanctl/trandoshanctl.go
View File

@ -73,6 +73,10 @@ func search(c *cli.Context) error {
return err
}
if len(res) == 0 {
fmt.Println("No resources crawled (yet).")
}
for _, r := range res {
fmt.Printf("%s - %s\n", r.URL, r.Title)
}