Go语言实现自动填写古诗词实例代码

 baseUrl := "http://hanyu.baidu.com/hanyu/ajax/sugs?"
 client := &http.Client{
 }
 u, _ := url.Parse(baseUrl)
 q := u.Query()
 q.Set("mainkey", name)
 u.RawQuery = q.Encode()

 //添加Header
 req, _ := http.NewRequest("GET", u.String(), nil)
 req.Header.Add("User-Agent", `Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36`)
 req.Header.Add("DNT", "1")
 req.Header.Add("Host", "hanyu.baidu.com")
 req.Header.Add("Accept-Language", "zh-CN,zh;q=0.8")
 req.Header.Add("Referer", "http://hanyu.baidu.com/shici/detail?pid=be520db056da43238035dc18bb1e1798&tn=sug_click")
 
 resp, errDo := client.Do(req)

//如果有多个搜索结果，比对author是否正确
 respJson.ForEach(func(key, value gjson.Result) bool {
 //先看看有没有display_name
 displayName := value.Get("display_name.0").String()
 sid := value.Get("sid.0").String()
 if len(displayName) == 0 {
 //不是这条记录
 return true
 }

 //看看type
 typeStr := value.Get("type.0").String()
 if typeStr == "poemline"{
 //取Source
 displayName = value.Get("source_poem.0").String()
 sid = value.Get("source_poem_sid.0").String()
 }

 literatureAuthor := value.Get("literature_author.0").String()
 //author是否一致
 if literatureAuthor == author {
 searchResult.Sid = sid
 searchResult.DisplayName = displayName
 searchResult.Author = literatureAuthor
 return false
 }
 return true // keep iterating
 })

func GetContent(sid string) (content string, err error) {
 baseUrl := "http://hanyu.baidu.com/shici/detail"

 result := make([]string, 0, 0)
 client := &http.Client{
 }

 u, _ := url.Parse(baseUrl)
 q := u.Query()
 q.Set("pid", sid)
 u.RawQuery = q.Encode()

 req, _ := http.NewRequest("GET", u.String(), nil)
 req.Header.Add("User-Agent", `Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36`)
 req.Header.Add("DNT", "1")
 req.Header.Add("Host", "hanyu.baidu.com")
 req.Header.Add("Accept-Language", "zh-CN,zh;q=0.8")
 req.Header.Add("Referer", "http://hanyu.baidu.com/shici/detail?pid=be520db056da43238035dc18bb1e1798&tn=sug_click")

 resp, errDo := client.Do(req)

 if errDo != nil || resp.StatusCode != 200 {
 err = errors.New("无法连接百度汉语 " + errDo.Error())
 return
 }

 docm, errDoc := goquery.NewDocumentFromResponse(resp)

 if errDoc != nil {
 err = errors.New("解析Doc错误 " + errDoc.Error())
 return
 }

 //诗词信息都保存在 body_p 的div中，可以通过PuerkitoBio/goquery库获取
 pSelect := docm.Find("#body_p")
 pSelect.Each(func(pos int, selection *goquery.Selection) {
 content := strings.TrimSpace(selection.Text())
 result = append(result, content)
 })

 content = strings.Join(result, "")
 return
}

type Spider interface {
 GetContent(SearchResult) (string, error)
 FindContent(string, string) (SearchResult, error)
}

func MapSpiderManifest() map[string]Spider {
 //初始化并且注册所有的Spider
 spiderMap := make(map[string]Spider)

 //百度
 baiduSpider := new(BaiduSpider)
 spiderMap["baiduSpider"] = baiduSpider

 //古诗文网
 gushiwenSpider := new(GushiwenSpider)
 spiderMap["gushiwenSpider"] = gushiwenSpider
 return spiderMap
}

//已知newFind的PreString，求BlankString和PostString
func makeWithPreContent(contentsSplit []string, newFind *Find) {
 for l := range contentsSplit {
 if isEqual(contentsSplit[l], newFind.PreString) && l < len(contentsSplit)-1 {
 newFind.BlankString = contentsSplit[l+1]
 if l < len(contentsSplit)-2 {
 newFind.PostString = contentsSplit[l+2]
 }
 newFind.BlankFinish = true
 }
 }
}

//已知newFind的PostString，求BlankString和PreString
func makeWithPostContent(contentsSplit []string, newFind *Find) {
 for l := range contentsSplit {
 if isEqual(contentsSplit[l], newFind.PostString) && l > 0 {
 newFind.BlankString = contentsSplit[l-1]
 if l-1 > 0 {
 newFind.PreString = contentsSplit[l-2]
 }
 newFind.BlankFinish = true
 }
 }
}

// 按标点符号分隔内容
func SplitByPunctuation(s string) ([]string, []string) {
 regPunctuation, _ := regexp.Compile(`[,，。.?？！!;；：:]`)
 //匹配标点符号，保存下来。 然后分割字符串
 toPun := regPunctuation.FindAllString(s, -1)
 result := regPunctuation.Split(s, -1)

 if len(result[len(result)-1]) == 0 {
 result = result[:len(result)-1]
 }

 //去掉前后空格，去掉引号
 for i := range result {
 result[i] = strings.TrimSpace(result[i])
 regQuoting := regexp.MustCompile("[“”‘'']")
 result[i] = regQuoting.ReplaceAllString(result[i], "")
 }
 return result, toPun
}