This commit is contained in:
Peter Kleiweg
2026-06-10 13:31:55 +02:00
parent d7adc17d4b
commit a8bea0ab44
4 changed files with 10 additions and 10 deletions

View File

@@ -278,8 +278,8 @@ func doArticle(filename string, url string, title string, timestamp time.Time, n
specials, err := article.Search(`.//*[@data-content-type="GROUP"]`)
p(err)
for _, special := range specials {
special.Remove()
for i := len(specials) - 1; i >= 0; i-- {
specials[i].Remove()
}
other, err := article.Search(`.//*[@data-content-type="PODCAST"]`)

View File

@@ -313,10 +313,10 @@ func doArticle(filename string, url string, title string, timestamp time.Time, n
_ = w(fmt.Errorf("no intro: %s", url))
}
specials, err := article.Search(`.//section//aside | .//section//figure | .//section//b`)
specials, err := article.Search(`.//aside | .//figure | .//figcaption | .//section//b`)
p(err)
for _, special := range specials {
special.Remove()
for i := len(specials) - 1; i >= 0; i-- {
specials[i].Remove()
}
ell, err = article.Search(`.//section//*[@data-article-element-index]`)

View File

@@ -69,8 +69,8 @@ func main() {
root := doc.Root()
divs, err := root.Search(`//div[@class="donatieformlinks"]`)
x(err)
for _, div := range divs {
div.Remove()
for i := len(divs) - 1; i >= 0; i-- {
divs[i].Remove()
}
pp, err := root.Search(`//body//p[not(.//a[contains(@href,"reportersonline.nl/support")])]`)
x(err)

View File

@@ -315,10 +315,10 @@ func doArticle(filename string, url string, title string, timestamp time.Time, n
_ = w(fmt.Errorf("no intro: %s", url))
}
specials, err := article.Search(`.//section//aside | .//section//figure | .//section//b`)
specials, err := article.Search(`.//aside | .//figure | .//figcaption | .//section//b`)
p(err)
for _, special := range specials {
special.Remove()
for i := len(specials) - 1; i >= 0; i-- {
specials[i].Remove()
}
ell, err = article.Search(`.//section//*[@data-article-element-index]`)