func main() {
xml := `<?xml version="1.0"?>
<!DOCTYPE doc [
<!ELEMENT doc (src | dest)*>
<!ELEMENT src EMPTY>
<!ELEMENT dest EMPTY>
<!ATTLIST src ref IDREF #IMPLIED>
<!ATTLIST dest id ID #IMPLIED>
]>
<doc>
<src ref="foo"/>
<dest id="foo"/>
<src ref="foo"/>
<employee>
<firstname>John</firstname>
<lastname>Smith</lastname>
<food type="dessert">Ice cream</food>
<description>
Born on <date lang="norwegian">03.03.99</date> ....
</description>
</employee>
</doc>
`
doc, _ := gokogiri.ParseXml([]byte(xml))
defer doc.Free()
rootElement := doc.Root()
printElementNames(rootElement)
}
func fetchAndFormatArticles(sem *chan int, sub *Subscription, articleChannel *chan *[]Article, waitGroup *sync.WaitGroup) {
resp, err := http.Get(sub.Url)
if err != nil {
log.Printf("Unable to fetch articles from %v | Error: %v ", sub.Url, err.Error()) // TODO: Manage error. How?
*sem <- 1
waitGroup.Done()
return
}
body, _ := ioutil.ReadAll(resp.Body)
resp.Body.Close()
doc, err := gokogiri.ParseXml(body)
if err != nil {
log.Println("Error parsing XML on feed with URL " + sub.Url)
return
}
defer doc.Free()
doc.RecursivelyRemoveNamespaces()
var articles []Article
if doc.Root().Name() == "rss" {
formatRSS(sub, doc, &articles)
} else if doc.Root().Name() == "feed" {
formatAtom(sub, doc, &articles)
}
*articleChannel <- &articles
*sem <- 1
waitGroup.Done()
}
func parseContainer(ef *epubFile) (*container, error) {
c := &container{}
rootpath := "META-INF/container.xml"
rootfile := findZipFile(ef.r, rootpath)
if rootfile == nil {
return nil, NoEPUBError
}
fr, err := rootfile.Open()
if err != nil {
return nil, fmt.Errorf("could not open %s, %s", rootpath, err)
}
defer fr.Close()
data, err := ioutil.ReadAll(fr)
if err != nil {
return nil, UnexpectedError
}
doc, err := gokogiri.ParseXml(data)
if err != nil {
return nil, InvalidXMLError
}
defer doc.Free()
doc.RecursivelyRemoveNamespaces()
res, _ := doc.Search("/container/rootfiles/rootfile")
for _, node := range res {
if node.Attr("media-type") == "application/oebps-package+xml" {
c.OEBPSPackagePath = node.Attr("full-path")
}
}
return c, nil
}
func main() {
// content, _ := ioutil.ReadFile("index.html")
//doc, _ := gokogiri.ParseHtml(content)
content := `<?xml version="1.0"?>
<?xml-stylesheet href="catalog.xsl" type="text/xsl"?>
<!DOCTYPE catalog SYSTEM "catalog.dtd">
<catalog>
<product description="Cardigan Sweater" product_image="cardigan.jpg">
<catalog_item gender="Men's">
<item_number>QWZ5671</item_number>
<price>39.95</price>
<size description="Medium">
<color_swatch image="red_cardigan.jpg">Red</color_swatch>
<color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
</size>
<size description="Large">
<color_swatch image="red_cardigan.jpg">Red</color_swatch>
<color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
</size>
</catalog_item>
<catalog_item gender="Women's">
<item_number>RRX9856</item_number>
<price>42.50</price>
<size description="Small">
<color_swatch image="red_cardigan.jpg">Red</color_swatch>
<color_swatch image="navy_cardigan.jpg">Navy</color_swatch>
<color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
</size>
<size description="Medium">
<color_swatch image="red_cardigan.jpg">Red</color_swatch>
<color_swatch image="navy_cardigan.jpg">Navy</color_swatch>
<color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
<color_swatch image="black_cardigan.jpg">Black</color_swatch>
</size>
<size description="Large">
<color_swatch image="navy_cardigan.jpg">Navy</color_swatch>
<color_swatch image="black_cardigan.jpg">Black</color_swatch>
</size>
<size description="Extra Large">
<color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch>
<color_swatch image="black_cardigan.jpg">Black</color_swatch>
</size>
</catalog_item>
</product>
</catalog>`
doc, _ := gokogiri.ParseXml([]byte(content))
defer doc.Free()
if len(os.Args) <= 1 {
fmt.Println(doc.String())
} else if len(os.Args) == 3 {
example4(os.Args[1], os.Args[2])
} else {
fmt.Println("Usage: lx2_xpath-search1 xpath-expr new-value")
}
}
func processXmlString(unparsedXml []byte) {
doc, err := gokogiri.ParseXml(unparsedXml)
if err != nil {
log.Println("Error parsing file:", err)
return
}
firstNode, err := doc.Node.Search("//node")
row := "|" // empty pipe separated row, starter
processNode(firstNode[0], row)
}
func parseOEBPSPackage(ef *epubFile, c *container) error {
epub := ef.data
file := findZipFile(ef.r, c.OEBPSPackagePath)
if file == nil {
return UnexpectedError
}
fr, err := file.Open()
if err != nil {
return fmt.Errorf("could not open %s, %s", c.OEBPSPackagePath, err)
}
defer fr.Close()
data, err := ioutil.ReadAll(fr)
if err != nil {
return UnexpectedError
}
doc, err := gokogiri.ParseXml(data)
if err != nil {
return InvalidXMLError
}
defer doc.Free()
doc.RecursivelyRemoveNamespaces()
epub.Version = doc.Root().Attr("version")
res, _ := doc.Search("/package/metadata")
if len(res) != 1 {
return NoEPUBError
}
mn := res[0]
creators, _ := mn.Search("creator")
contributors, _ := mn.Search("contributor")
epub.Titles = parseTitles(mn)
epub.Creators = parsePeople(creators)
epub.Contributors = parsePeople(contributors)
epub.Subjects = parseSubjects(mn)
epub.Description = parseDescription(mn)
epub.Publisher = parsePublisher(mn)
epub.Dates = parseDates(mn)
epub.Identifiers = parseIdentifiers(mn)
epub.Source = parseSource(mn)
epub.Languages = parseLanguages(mn)
epub.Rights = parseRights(mn)
return nil
}
func main() {
doc, _ := gokogiri.ParseXml([]byte(a))
defer doc.Free()
xp := doc.DocXPathCtx()
xp.RegisterNamespace("ns", "http://example.com/this")
x := xpath.Compile("/ns:NodeA/ns:NodeB")
groups, err := doc.Search(x)
if err != nil {
fmt.Println(err)
}
for i, group := range groups {
fmt.Println(i, group.Content())
}
}
func extract(file string, xpath string) {
xml, err := ioutil.ReadFile(file)
if err != nil {
fmt.Fprintf(os.Stderr, "gox: Could not read %s\n", file)
}
doc, err := gokogiri.ParseXml(xml)
defer doc.Free()
if err != nil {
fmt.Fprintf(os.Stderr, "gox: Could not parse %s\n", file)
}
nodes, _ := doc.Search(xpath)
for n := range nodes {
fmt.Println(nodes[n].String())
}
}
func main() {
doc, _ := gokogiri.ParseXml([]byte(file))
nodes, _ := doc.Search("/foo")
for n := range nodes {
fmt.Println(nodes[n].Name())
subnodes, _ := nodes[n].Search("bar")
for s := range subnodes {
fmt.Println(subnodes[s].Name())
}
}
fmt.Println("---")
nodes, _ = doc.Search("bar")
for n := range nodes {
fmt.Println(nodes[n].Name())
}
}
func findRSSTitle(rssUrl string) (string, error) {
res, err := http.Get(rssUrl)
if err != nil {
return "", err
}
body, err := ioutil.ReadAll(res.Body)
if err != nil {
return "", err
}
res.Body.Close()
doc, err := gokogiri.ParseXml(body)
defer doc.Free()
doc.RecursivelyRemoveNamespaces()
nodes, err := doc.Search("//title")
if err != nil {
return "", err
}
if len(nodes) > 0 {
return nodes[0].Content(), nil
}
return "", nil
}
func findRSSURL(rawurl string) (string, error) {
res, err := http.Get(rawurl)
if err != nil {
return "", err
}
body, err := ioutil.ReadAll(res.Body)
if err != nil {
return "", err
}
res.Body.Close()
doc, err := gokogiri.ParseXml(body)
defer doc.Free()
if (doc.Root().Name() != "rss" && doc.Root().Name() != "feed") || err != nil {
doc, _ := gokogiri.ParseHtml(body)
defer doc.Free()
doc.RecursivelyRemoveNamespaces()
nodes, err := doc.Search("//link")
if err != nil {
return "", err
}
for _, v := range nodes {
if v.Attribute("rel").Value() == "alternate" || v.Attribute("rel").Value() == "feed" {
u, _ := url.Parse(v.Attribute("href").Value())
if u.IsAbs() {
return u.String(), nil
} else {
baseU, _ := url.Parse(rawurl)
u.Scheme = baseU.Scheme
u.Host = baseU.Host
return u.String(), nil
}
}
}
} else {
return res.Request.URL.String(), nil
}
return "", errors.New("Feed URL not found")
}
func (s *EposServer) ServeHTTP(rw http.ResponseWriter, req *http.Request) {
// send origin headers
if origin := req.Header.Get("Origin"); origin != "" {
rw.Header().Set("Access-Control-Allow-Origin", origin)
rw.Header().Set("Access-Control-Allow-Methods", "POST, GET, OPTIONS, PUT, DELETE")
rw.Header().Set("Access-Control-Allow-Headers", "Accept, Content-Type, Content-Length, Accept-Encoding, X-CSRF-Token, Authorization, If-Modified-Since, SOAPAction")
}
// stop if its options
if req.Method == "OPTIONS" {
log.Println("OPTIONS %s", req.URL)
return
}
// handle crappy soap action
if req.Method == "POST" {
// grab posted body
data, _ := ioutil.ReadAll(req.Body)
log.Printf("POST %s:\n%s\n\n", req.URL, string(data))
// parse xml with gokogiri
doc, _ := gokogiri.ParseXml(data)
defer doc.Free()
// load print nodes from xml doc
epos_nodes, err := getEposNodes(doc)
if err != nil {
rw.WriteHeader(503)
log.Fatal(err)
return
}
// init printer
s.printer.Init()
// loop over nodes
for _, en := range epos_nodes {
// grab name and inner text
name := en.Name()
content := en.Content()
// grab parameters
params := make(map[string]string)
for _, attr := range en.Attributes() {
params[attr.Name()] = attr.Value()
}
// write data to printer
s.printer.WriteNode(name, params, content)
}
// end
s.printer.End()
// flush writer
s.printerWriter.Flush()
//rw.WriteHeader(402)
// write soap response
writeSoapResponse(rw, req, "")
return
}
// force an error for everything else
rw.WriteHeader(403)
// Lets Gorilla work
s.r.ServeHTTP(rw, req)
}
func rssCloud(w http.ResponseWriter, r *http.Request) {
logr.Debugln("Yay a cloud request!")
if r.Method != "POST" {
w.Header().Set("Allow", "POST")
http.Error(w, "POST is required", http.StatusMethodNotAllowed)
return
}
bodyBytes := make([]byte, r.ContentLength)
_, err := r.Body.Read(bodyBytes)
if err != nil {
logr.Errln("Could not read request body:", err.Error())
http.Error(w, "Could not read body: "+err.Error(), http.StatusInternalServerError)
return
}
requestDoc, err := gokogiri.ParseXml(bodyBytes)
if err != nil {
writeXmlRpcError(w, err)
return
}
request := new(RssCloudRequest)
err = request.Unpack(requestDoc)
if err != nil {
writeXmlRpcError(w, err)
return
}
hostname := r.Header.Get("X-Forwarded-For")
if hostname == "" {
hostname = r.RemoteAddr
} else {
hostnames := strings.SplitN(hostname, ",", 2)
hostname = hostnames[0]
}
host, _, err := net.SplitHostPort(hostname)
request.Host = host
if request.RequestMethodName != "cloud.notify" {
writeXmlRpcError(w, fmt.Errorf("Unknown method %s", request.RequestMethodName))
return
}
if !request.IsXmlRpc {
writeXmlRpcError(w, fmt.Errorf("Only XML-RPC is supported"))
return
}
// TODO: use https as appropriate here? er, does river2 support cloud endpoints on HTTPS?
if request.FeedURL != fmt.Sprintf("http://%s/rss", r.Host) {
writeXmlRpcError(w, fmt.Errorf("RSS URL %s is not a feed managed here", request.FeedURL))
return
}
logr.Debugln("Yay, asked to call back to http://", request.Host, ":", request.Port, request.Path,
"with method", request.MethodName, "!")
url, _ := url.Parse("/")
if request.Port == 443 {
url.Scheme = "https"
} else {
url.Scheme = "http"
}
if request.Port == 80 || request.Port == 443 {
url.Host = request.Host
} else {
url.Host = net.JoinHostPort(request.Host, strconv.Itoa(int(request.Port)))
}
url.Path = request.Path
urlString := url.String()
rssCloud, err := RssCloudByURL(urlString)
if err == sql.ErrNoRows {
// That's cool.
} else if err != nil {
logr.Errln("Error loading rsscloud for URL", urlString, ":", err.Error())
http.Error(w, "error looking for rsscloud for URL "+urlString, http.StatusInternalServerError)
return
}
if rssCloud == nil {
rssCloud = NewRssCloud()
rssCloud.URL = urlString
}
rssCloud.Method = request.MethodName
// Subscribe until 25 hours from now.
rssCloud.SubscribedUntil = time.Now().Add(time.Duration(25) * time.Hour).UTC()
err = rssCloud.Save()
if err != nil {
logr.Errln("Error saving rsscloud for URL", urlString, ":", err.Error())
http.Error(w, "error saving rsscloud for URL "+urlString, http.StatusInternalServerError)
return
}
output := `<?xml version="1.0" encoding="UTF-8"?>
<methodResponse>
<params>
<param>
<value><boolean>1</boolean></value>
</param>
</params>
</methodResponse>`
w.Header().Set("Content-Type", "text/xml")
w.Header().Set("Content-Length", strconv.Itoa(len(output)))
w.Write([]byte(output))
}
