Created
July 5, 2018 11:57
-
-
Save matsumoto-k4zuki/76439737e73104502cc33222ccea47c4 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package main | |
| import ( | |
| "fmt" | |
| "github.com/PuerkitoBio/goquery" | |
| "unicode/utf8" | |
| ) | |
| func main() { | |
| // 投稿した記事の一覧ページのリンクから、記事のリンクを取得 | |
| doc, err := goquery.NewDocument("https://www.fox-hound.tech/author/kazuki-matsumoto/") | |
| if err != nil { | |
| fmt.Println(err) | |
| } | |
| // 投稿した記事のリンクのurlを配列に格納 | |
| var urls []string | |
| doc.Find(".title a").Each(func(_ int, s *goquery.Selection) { | |
| url, _ := s.Attr("href") | |
| urls = append(urls, url) | |
| }) | |
| //fmt.Println(urls) | |
| for i := 0; i < len(urls); i++ { | |
| fmt.Println(urls[i]) | |
| doc, err := goquery.NewDocument(urls[i]) | |
| if err != nil { | |
| fmt.Print("url scarapping failed") | |
| } | |
| title := doc.Find(".post--item .title h2").Text() | |
| fmt.Println(title) | |
| text := doc.Find(".post--item > div.post--content").Text() | |
| // 文字数をカウント(日本語を含むため、utf8.RuneCountInStringを利用) | |
| fmt.Printf("文字数: %d 字\n\n", utf8.RuneCountInString(text)) | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment