Created
September 11, 2016 15:27
-
-
Save t-kashima/38d09b1851461a283b344827c55efd25 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" | |
"regexp" | |
"strings" | |
) | |
const url = "https://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E9%AB%98%E7%AD%89%E5%AD%A6%E6%A0%A1%E4%B8%80%E8%A6%A7" | |
type Pref struct { | |
name string | |
link string | |
} | |
type School struct { | |
name string | |
yomigana string | |
link string | |
pref *Pref | |
} | |
func (school School) toString() string { | |
return "name=" + school.name + ", yomigana=" + school.yomigana + ", pref=" + school.pref.name + ", link=" + school.link | |
} | |
func (pref Pref) Get(url string) []*Pref { | |
prefs := []*Pref{} | |
doc, _ := goquery.NewDocument(url) | |
prefRegexp := regexp.MustCompile(`^(.+[県道都])高等学校一覧$`) | |
doc.Find(".navbox a[title$='高等学校一覧']").Each(func(_ int, s *goquery.Selection) { | |
title, _ := s.Attr("title") | |
href, _ := s.Attr("href") | |
if prefRegexp.MatchString(title) { | |
pref := Pref{name: prefRegexp.ReplaceAllString(title, "$1"), link: "https://ja.wikipedia.org" + href} | |
prefs = append(prefs, &pref) | |
} | |
}) | |
return prefs | |
} | |
func (pref Pref) getSchools() []*School { | |
schools := []*School{} | |
notSchoolRegexp := regexp.MustCompile(`^.+?:.+?$|^高等学校$`) | |
doc, _ := goquery.NewDocument(pref.link) | |
doc.Find("a[title$='高等学校']").Each(func(_ int, s *goquery.Selection) { | |
title, _ := s.Attr("title") | |
href, _ := s.Attr("href") | |
if !notSchoolRegexp.MatchString(title) { | |
school := School{name: title, link: "https://ja.wikipedia.org" + href, pref: &pref} | |
schools = append(schools, &school) | |
} | |
}) | |
return schools | |
} | |
func (school School) getDetail() *School { | |
spaceRegexp := strings.NewReplacer(" ", "") | |
yomiganaRegexp := regexp.MustCompile(`((.+?))`) | |
doc, _ := goquery.NewDocument(school.link) | |
doc.Find("#mw-content-text > p").First().Each(func(_ int, s *goquery.Selection) { | |
paragraph := s.Text() | |
if yomiganaRegexp.MatchString(paragraph) { | |
result := yomiganaRegexp.FindAllStringSubmatch(paragraph, -1) | |
yomigana := spaceRegexp.Replace(strings.Split(result[0][1], "、")[0]) | |
school.yomigana = yomigana | |
} | |
}) | |
return &school | |
} | |
func main() { | |
prefs := Pref{}.Get(url) | |
for _, pref := range prefs { | |
schools := pref.getSchools() | |
for _, school := range schools { | |
fmt.Printf(school.toString()) | |
fmt.Println() | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment