noham/papeer
1
0
Fork 0
mirror of https://github.com/NohamR/papeer.git synced 2026-05-25 20:00:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

[list] print absolute url in json output

Browse Source
This commit is contained in:
lapwat
2023-02-18 00:01:48 +01:00
parent efcc45316b
commit 8fd0a12620
4 changed files with 15 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
book/scraper.go
View File

@@ -365,7 +365,12 @@ func GetLinks(url *urllib.URL, selector string, limit, offset int, reverse, incl
// RSS feed
for _, item := range feed.Items {
links = append(links, NewLink(item.Link, item.Title))
u, err := url.Parse(item.Link)
if err != nil {
log.Fatal(err)
}
links = append(links, NewLink(u.String(), item.Title))
}
pathMax = "RSS"
@@ -385,11 +390,16 @@ func GetLinks(url *urllib.URL, selector string, limit, offset int, reverse, incl
// visit and count link classes
c := colly.NewCollector()
c.OnHTML(selector, func(e *colly.HTMLElement) {
href := e.Attr("href")
text := strings.TrimSpace(e.Text)
path := GetPath(e.DOM)
key := path
u, err := url.Parse(e.Attr("href"))
if err != nil {
log.Fatal(err)
}
href := u.String()
if selectorSet {
// if selector is set, we use the selector specified by the user