Golang Document.SelectNodes方法代码示例

func readAtom(doc *xmlx.Document) (foundChannels []*Channel, err error) {
	const ns = "http://www.w3.org/2005/Atom"

	for _, node := range doc.SelectNodes(ns, "feed") {
		foundChannels = append(foundChannels, readAtomChannel(ns, node))
	}

	return foundChannels, err
}

func (this *Feed) readRss2(doc *xmlx.Document) (err error) {
	var foundChannels []*Channel
	var ch *Channel
	var i *Item
	var n *xmlx.Node
	var list, tl []*xmlx.Node
	const ns = "*"

	root := doc.SelectNode(ns, "rss")
	if root == nil {
		root = doc.SelectNode(ns, "RDF")
	}

	if root == nil {
		return errors.New("Failed to find rss/rdf node in XML.")
	}

	channels := root.SelectNodes(ns, "channel")
	for _, node := range channels {
		ch = new(Channel)
		foundChannels = append(foundChannels, ch)

		ch.Title = node.S(ns, "title")
		list = node.SelectNodes(ns, "link")
		ch.Links = make([]Link, len(list))

		for i, v := range list {
			if v.Name.Space == "http://www.w3.org/2005/Atom" && v.Name.Local == "link" {
				ch.Links[i].Href = v.As("", "href")
				ch.Links[i].Rel = v.As("", "rel")
				ch.Links[i].Type = v.As("", "type")
				ch.Links[i].HrefLang = v.As("", "hreflang")
			} else {
				ch.Links[i].Href = v.GetValue()
			}
		}

		ch.Description = node.S(ns, "description")
		ch.Language = node.S(ns, "language")
		ch.Copyright = node.S(ns, "copyright")
		ch.ManagingEditor = node.S(ns, "managingEditor")
		ch.WebMaster = node.S(ns, "webMaster")
		ch.PubDate = node.S(ns, "pubDate")
		ch.LastBuildDate = node.S(ns, "lastBuildDate")
		ch.Docs = node.S(ns, "docs")

		list = node.SelectNodes(ns, "category")
		ch.Categories = make([]*Category, len(list))
		for i, v := range list {
			ch.Categories[i] = new(Category)
			ch.Categories[i].Domain = v.As(ns, "domain")
			ch.Categories[i].Text = v.GetValue()
		}

		if n = node.SelectNode(ns, "generator"); n != nil {
			ch.Generator = Generator{}
			ch.Generator.Text = n.GetValue()
		}

		ch.TTL = node.I(ns, "ttl")
		ch.Rating = node.S(ns, "rating")

		list = node.SelectNodes(ns, "hour")
		ch.SkipHours = make([]int, len(list))
		for i, v := range list {
			ch.SkipHours[i] = v.I(ns, "hour")
		}

		list = node.SelectNodes(ns, "days")
		ch.SkipDays = make([]int, len(list))
		for i, v := range list {
			ch.SkipDays[i] = days[v.GetValue()]
		}

		if n = node.SelectNode(ns, "image"); n != nil {
			ch.Image.Title = n.S(ns, "title")
			ch.Image.Url = n.S(ns, "url")
			ch.Image.Link = n.S(ns, "link")
			ch.Image.Width = n.I(ns, "width")
			ch.Image.Height = n.I(ns, "height")
			ch.Image.Description = n.S(ns, "description")
		}

		if n = node.SelectNode(ns, "cloud"); n != nil {
			ch.Cloud = Cloud{}
			ch.Cloud.Domain = n.As(ns, "domain")
			ch.Cloud.Port = n.Ai(ns, "port")
			ch.Cloud.Path = n.As(ns, "path")
			ch.Cloud.RegisterProcedure = n.As(ns, "registerProcedure")
			ch.Cloud.Protocol = n.As(ns, "protocol")
		}

		if n = node.SelectNode(ns, "textInput"); n != nil {
			ch.TextInput = Input{}
			ch.TextInput.Title = n.S(ns, "title")
			ch.TextInput.Description = n.S(ns, "description")
			ch.TextInput.Name = n.S(ns, "name")
			ch.TextInput.Link = n.S(ns, "link")
		}

//.........这里部分代码省略.........

func (this *Feed) readAtom(doc *xmlx.Document) (err error) {
	ns := "http://www.w3.org/2005/Atom"
	channels := doc.SelectNodes(ns, "feed")

	var foundChannels []*Channel
	var ch *Channel
	var i *Item
	var tn *xmlx.Node
	var list []*xmlx.Node

	for _, node := range channels {
		ch = new(Channel)
		foundChannels = append(foundChannels, ch)

		ch.Title = node.S(ns, "title")
		ch.LastBuildDate = node.S(ns, "updated")
		ch.Id = node.S(ns, "id")
		ch.Rights = node.S(ns, "rights")

		list = node.SelectNodes(ns, "link")
		ch.Links = make([]Link, len(list))
		for i, v := range list {
			ch.Links[i].Href = v.As("", "href")
			ch.Links[i].Rel = v.As("", "rel")
			ch.Links[i].Type = v.As("", "type")
			ch.Links[i].HrefLang = v.As("", "hreflang")
		}

		if tn = node.SelectNode(ns, "subtitle"); tn != nil {
			ch.SubTitle = SubTitle{}
			ch.SubTitle.Type = tn.As("", "type")
			ch.SubTitle.Text = tn.GetValue()
		}

		if tn = node.SelectNode(ns, "generator"); tn != nil {
			ch.Generator = Generator{}
			ch.Generator.Uri = tn.As("", "uri")
			ch.Generator.Version = tn.As("", "version")
			ch.Generator.Text = tn.GetValue()
		}

		if tn = node.SelectNode(ns, "author"); tn != nil {
			ch.Author = Author{}
			ch.Author.Name = tn.S("", "name")
			ch.Author.Uri = tn.S("", "uri")
			ch.Author.Email = tn.S("", "email")
		}

		list = node.SelectNodes(ns, "entry")

		for _, item := range list {
			i = new(Item)
			i.Title = item.S(ns, "title")
			i.Id = item.S(ns, "id")
			i.PubDate = item.S(ns, "updated")
			i.Description = item.S(ns, "summary")

			links := item.SelectNodes(ns, "link")
			for _, lv := range links {
				if lv.As(ns, "rel") == "enclosure" {
					enc := new(Enclosure)
					enc.Url = lv.As("", "href")
					enc.Type = lv.As("", "type")
					i.Enclosures = append(i.Enclosures, enc)
				} else {
					lnk := new(Link)
					lnk.Href = lv.As("", "href")
					lnk.Rel = lv.As("", "rel")
					lnk.Type = lv.As("", "type")
					lnk.HrefLang = lv.As("", "hreflang")
					i.Links = append(i.Links, lnk)
				}
			}

			list = item.SelectNodes(ns, "contributor")
			for _, cv := range list {
				i.Contributors = append(i.Contributors, cv.S("", "name"))
			}

			list = item.SelectNodes(ns, "category")
			for _, cv := range list {
				cat := new(Category)
				cat.Domain = ""
				cat.Text = cv.As("", "term")
				i.Categories = append(i.Categories, cat)
			}

			if tn = item.SelectNode(ns, "content"); tn != nil {
				i.Content = new(Content)
				i.Content.Type = tn.As("", "type")
				i.Content.Lang = tn.S("xml", "lang")
				i.Content.Base = tn.S("xml", "base")
				i.Content.Text = tn.GetValue()
			}

			if tn = item.SelectNode(ns, "author"); tn != nil {
				i.Author = Author{}
				i.Author.Name = tn.S(ns, "name")
				i.Author.Uri = tn.S(ns, "uri")
				i.Author.Email = tn.S(ns, "email")
//.........这里部分代码省略.........

func (this *Feed) readAtom(doc *xmlx.Document) (err error) {
	ns := "http://www.w3.org/2005/Atom"
	channels := doc.SelectNodes(ns, "feed")

	getChan := func(id, title string) *Channel {
		for _, c := range this.Channels {
			switch {
			case len(id) > 0:
				if c.Id == id {
					return c
				}
			case len(title) > 0:
				if c.Title == title {
					return c
				}
			}
		}
		return nil
	}

	haveItem := func(ch *Channel, id, title, desc string) bool {
		for _, item := range ch.Items {
			switch {
			case len(id) > 0:
				if item.Id == id {
					return true
				}
			case len(title) > 0:
				if item.Title == title {
					return true
				}
			case len(desc) > 0:
				if item.Description == desc {
					return true
				}
			}
		}
		return false
	}

	var ch *Channel
	var i *Item
	var tn *xmlx.Node
	var list []*xmlx.Node

	for _, node := range channels {
		if ch = getChan(node.S(ns, "id"), node.S(ns, "title")); ch == nil {
			ch = new(Channel)
			this.Channels = append(this.Channels, ch)
		}

		ch.Title = node.S(ns, "title")
		ch.LastBuildDate = node.S(ns, "updated")
		ch.Id = node.S(ns, "id")
		ch.Rights = node.S(ns, "rights")

		list = node.SelectNodes(ns, "link")
		ch.Links = make([]Link, len(list))
		for i, v := range list {
			ch.Links[i].Href = v.As("", "href")
			ch.Links[i].Rel = v.As("", "rel")
			ch.Links[i].Type = v.As("", "type")
			ch.Links[i].HrefLang = v.As("", "hreflang")
		}

		if tn = node.SelectNode(ns, "subtitle"); tn != nil {
			ch.SubTitle = SubTitle{}
			ch.SubTitle.Type = tn.As("", "type")
			ch.SubTitle.Text = tn.Value
		}

		if tn = node.SelectNode(ns, "generator"); tn != nil {
			ch.Generator = Generator{}
			ch.Generator.Uri = tn.As("", "uri")
			ch.Generator.Version = tn.As("", "version")
			ch.Generator.Text = tn.Value
		}

		if tn = node.SelectNode(ns, "author"); tn != nil {
			ch.Author = Author{}
			ch.Author.Name = tn.S("", "name")
			ch.Author.Uri = tn.S("", "uri")
			ch.Author.Email = tn.S("", "email")
		}

		itemcount := len(ch.Items)
		list = node.SelectNodes(ns, "entry")

		for _, item := range list {
			if haveItem(ch, item.S(ns, "id"), item.S(ns, "title"), item.S(ns, "summary")) {
				continue
			}

			i = new(Item)
			i.Title = item.S(ns, "title")
			i.Id = item.S(ns, "id")
			i.PubDate = item.S(ns, "updated")
			i.Description = item.S(ns, "summary")

			links := item.SelectNodes(ns, "link")
//.........这里部分代码省略.........

func (this *Feed) readRss2(doc *xmlx.Document) (err error) {
	days := make(map[string]int)
	days["Monday"] = 1
	days["Tuesday"] = 2
	days["Wednesday"] = 3
	days["Thursday"] = 4
	days["Friday"] = 5
	days["Saturday"] = 6
	days["Sunday"] = 7

	getChan := func(pubdate, title string) *Channel {
		for _, c := range this.Channels {
			switch {
			case len(pubdate) > 0:
				if c.PubDate == pubdate {
					return c
				}
			case len(title) > 0:
				if c.Title == title {
					return c
				}
			}
		}
		return nil
	}

	var ch *Channel
	var i *Item
	var n *xmlx.Node
	var list, tl []*xmlx.Node
	const ns = "*"

	root := doc.SelectNode(ns, "rss")
	if root == nil {
		root = doc.SelectNode(ns, "RDF")
	}

	if root == nil {
		return errors.New("Failed to find rss/rdf node in XML.")
	}

	channels := root.SelectNodes(ns, "channel")
	for _, node := range channels {
		if ch = getChan(node.S(ns, "pubDate"), node.S(ns, "title")); ch == nil {
			ch = new(Channel)
			this.Channels = append(this.Channels, ch)
		}

		ch.Title = node.S(ns, "title")
		list = node.SelectNodes(ns, "link")
		ch.Links = make([]Link, len(list))

		for i, v := range list {
			ch.Links[i].Href = v.GetValue()
		}

		ch.Description = node.S(ns, "description")
		ch.Language = node.S(ns, "language")
		ch.Copyright = node.S(ns, "copyright")
		ch.ManagingEditor = node.S(ns, "managingEditor")
		ch.WebMaster = node.S(ns, "webMaster")
		ch.PubDate = node.S(ns, "pubDate")
		ch.LastBuildDate = node.S(ns, "lastBuildDate")
		ch.Docs = node.S(ns, "docs")

		list = node.SelectNodes(ns, "category")
		ch.Categories = make([]*Category, len(list))
		for i, v := range list {
			ch.Categories[i] = new(Category)
			ch.Categories[i].Domain = v.As(ns, "domain")
			ch.Categories[i].Text = v.GetValue()
		}

		if n = node.SelectNode(ns, "generator"); n != nil {
			ch.Generator = Generator{}
			ch.Generator.Text = n.GetValue()
		}

		ch.TTL = node.I(ns, "ttl")
		ch.Rating = node.S(ns, "rating")

		list = node.SelectNodes(ns, "hour")
		ch.SkipHours = make([]int, len(list))
		for i, v := range list {
			ch.SkipHours[i] = v.I(ns, "hour")
		}

		list = node.SelectNodes(ns, "days")
		ch.SkipDays = make([]int, len(list))
		for i, v := range list {
			ch.SkipDays[i] = days[v.GetValue()]
		}

		if n = node.SelectNode(ns, "image"); n != nil {
			ch.Image.Title = n.S(ns, "title")
			ch.Image.Url = n.S(ns, "url")
			ch.Image.Link = n.S(ns, "link")
			ch.Image.Width = n.I(ns, "width")
			ch.Image.Height = n.I(ns, "height")
			ch.Image.Description = n.S(ns, "description")
//.........这里部分代码省略.........

func readRssChannel(ns string, doc *xmlx.Document, node *xmlx.Node) *Channel {
	ch := &Channel{
		Title:          node.S(ns, "title"),
		Description:    node.S(ns, "description"),
		Language:       node.S(ns, "language"),
		Copyright:      node.S(ns, "copyright"),
		ManagingEditor: node.S(ns, "managingEditor"),
		WebMaster:      node.S(ns, "webMaster"),
		PubDate:        node.S(ns, "pubDate"),
		LastBuildDate:  node.S(ns, "lastBuildDate"),
		Docs:           node.S(ns, "docs"),
		TTL:            node.I(ns, "ttl"),
		Rating:         node.S(ns, "rating"),
	}

	for _, v := range node.SelectNodes(ns, "link") {
		lnk := Link{}
		if v.Name.Space == "http://www.w3.org/2005/Atom" && v.Name.Local == "link" {
			lnk.Href = v.As("", "href")
			lnk.Rel = v.As("", "rel")
			lnk.Type = v.As("", "type")
			lnk.HrefLang = v.As("", "hreflang")
		} else {
			lnk.Href = v.GetValue()
		}

		ch.Links = append(ch.Links, lnk)
	}

	for _, v := range node.SelectNodes(ns, "category") {
		ch.Categories = append(ch.Categories, Category{
			Domain: v.As(ns, "domain"),
			Text:   v.GetValue(),
		})
	}

	if n := node.SelectNode(ns, "generator"); n != nil {
		ch.Generator = Generator{
			Text: n.GetValue(),
		}
	}

	for _, v := range node.SelectNodes(ns, "hour") {
		ch.SkipHours = append(ch.SkipHours, v.I(ns, "hour"))
	}

	for _, v := range node.SelectNodes(ns, "days") {
		ch.SkipDays = append(ch.SkipDays, days[v.GetValue()])
	}

	if n := node.SelectNode(ns, "image"); n != nil {
		ch.Image = Image{
			Title:       n.S(ns, "title"),
			Url:         n.S(ns, "url"),
			Link:        n.S(ns, "link"),
			Width:       n.I(ns, "width"),
			Height:      n.I(ns, "height"),
			Description: n.S(ns, "description"),
		}
	}

	if n := node.SelectNode(ns, "cloud"); n != nil {
		ch.Cloud = Cloud{
			Domain:            n.As(ns, "domain"),
			Port:              n.Ai(ns, "port"),
			Path:              n.As(ns, "path"),
			RegisterProcedure: n.As(ns, "registerProcedure"),
			Protocol:          n.As(ns, "protocol"),
		}
	}

	if n := node.SelectNode(ns, "textInput"); n != nil {
		ch.TextInput = Input{
			Title:       n.S(ns, "title"),
			Description: n.S(ns, "description"),
			Name:        n.S(ns, "name"),
			Link:        n.S(ns, "link"),
		}
	}

	list := node.SelectNodes(ns, "item")
	if len(list) == 0 {
		list = doc.SelectNodes(ns, "item")
	}

	for _, item := range list {
		ch.Items = append(ch.Items, readRssItem(ns, item))
	}

	ch.Extensions = make(map[string]map[string][]Extension)
	for _, v := range node.Children {
		getExtensions(&ch.Extensions, v)
	}

	return ch
}