Parool: dubbele <header>

This commit is contained in:
Peter Kleiweg
2026-05-23 13:50:14 +02:00
parent c0335f5b57
commit 81cc653ee7

View File

@@ -189,8 +189,30 @@ func doArticle(filename string, url string, timestamp time.Time, needUpdate bool
return true
}
headers, err := article.Search(`//header`)
p(err)
if len(headers) == 0 {
_ = w(fmt.Errorf("no header: %s", url))
fp, err := os.Create(filename + ".err")
p(err)
p(fmt.Fprintf(fp, "no elements: %s\n", url))
p(fp.Close())
p(os.Chtimes(filename+".err", timestamp, timestamp))
fp, err = os.Create(filename + ".html")
p(err)
p(fp.Write(body))
p(fp.Close())
p(os.Chtimes(filename+".html", timestamp, timestamp))
return false
}
header := headers[0]
tags := make([]string, 0)
ell, err := article.Search(`//header//*[@data-test-id="article-label"]`)
ell, err := header.Search(`//*[@data-test-id="article-label"]`)
p(err)
if len(ell) == 0 {
_ = w(fmt.Errorf("no labels: %s", url))
@@ -204,7 +226,7 @@ func doArticle(filename string, url string, timestamp time.Time, needUpdate bool
pars := make([]string, 0)
ell, err = article.Search(`//header//*[@data-test-id="article-title"]`)
ell, err = header.Search(`//*[@data-test-id="article-title"]`)
p(err)
if len(ell) != 1 {
_ = w(fmt.Errorf("found %d titles: %s", len(ell), url))
@@ -217,7 +239,7 @@ func doArticle(filename string, url string, timestamp time.Time, needUpdate bool
}
found := false
ell, err = article.Search(`//header//*[@data-test-id="header-intro"]`)
ell, err = header.Search(`//*[@data-test-id="header-intro"]`)
p(err)
for _, el := range ell {
s := strings.TrimSpace(el.Content())