Skip to content

Commit

Permalink
2. Site Eklendi
Browse files Browse the repository at this point in the history
  • Loading branch information
muratozylmz committed Dec 17, 2024
1 parent a1f4319 commit f1ff552
Showing 1 changed file with 43 additions and 14 deletions.
57 changes: 43 additions & 14 deletions TASK_7_WEB_SCRAPER/main.go
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ func main() {
flag.Parse()

if *siteSelection == "" {
log.Fatal("Eksik parametre gönderildi.")
log.Fatal("Eksik parametre gönderildi. Açıklamalar ve örnek kullanım için lütfen '-h' parametresini kullanın.")
}
sites := strings.Split(*siteSelection, ",")

Expand All @@ -38,31 +38,60 @@ func getNews1(url string, dateFilter bool, descriptionFilter bool) {
c := colly.NewCollector(colly.AllowedDomains("thehackernews.com"))

c.OnError(func(r *colly.Response, err error) {
fmt.Printf("Error: %s\n", err.Error))
fmt.Printf("Error: %s\n", err.Error())
})

c.OnHTML("div.body-post", func(e *colly.HTMLElement) {
selection := h.DOMerr
c.OnHTML("div.body-post", func(h *colly.HTMLElement) {
selection := h.DOM

title := selection.Find("h2.home-title").Text()
date := selection.Find("span.h-datetime").Text()
trimmedDate := date[3:]
description := selection.Find("div.home-desc").Text()
newsLink := selection.Find("a.story-link").AttrOr("href", "")
if !dateFilter && !descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n, title, trimmedDate, description, newsLink)
}
else if dateFilter && !descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Haber Linki: %s\n\n, title, trimmedDate, newsLink)
}
else if !dateFilter && descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n, title, description, newsLink)
}
else {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n, title, trimmedDate, description, newsLink)
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n", title, trimmedDate, description, newsLink)
} else if dateFilter && !descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Haber Linki: %s\n\n", title, trimmedDate, newsLink)
} else if !dateFilter && descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n", title, description, newsLink)
} else {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n", title, trimmedDate, description, newsLink)
}
})

c.Visit(url)
}

func getNews2(scrapeURL string, dateFilter bool, descriptionFilter bool) {
c := colly.NewCollector(colly.AllowedDomains("ajansspor.com"))

c.OnError(func(r *colly.Response, err error) {
fmt.Printf("Error: %s\n", err.Error())
})

c.OnHTML("div.card", func(h *colly.HTMLElement) {
selection := h.DOM

title := selection.Find("div.news-title").Text()

date := selection.Find("div.news-date-bottom").Text()
trimmedDate := date

description := selection.Find("div.post-content").Text()

newsLink := selection.Find("a").AttrOr("href", "")

if !dateFilter && !descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n Açıklama: %s...\n\n Haber Linki: %s\n\n", title, trimmedDate, description, newsLink)
} else if dateFilter && !descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Haber Linki: %s\n\n", title, newsLink)
} else if !dateFilter && descriptionFilter {
fmt.Printf("Haber Başlığı: %s\n\n Tarih: %s\n\n ", title, trimmedDate)
} else {
fmt.Printf("Haber Başlığı: %s\n\n", title)
}
})

c.Visit(scrapeURL)
}

0 comments on commit f1ff552

Please sign in to comment.