Request callbacks added.

Recover from all panics and continue scraping.
Only parse HTML if response is HTML.
This commit is contained in:
Musab Gültekin 2019-06-09 21:13:30 +03:00
parent 7abc7a370d
commit ca2414c5c8
5 changed files with 48 additions and 18 deletions

View File

@ -11,6 +11,7 @@ import (
"net/http"
"net/url"
"os"
"runtime/debug"
"sync"
"time"
)
@ -80,29 +81,34 @@ func (g *Geziyor) Start() {
}
// Get issues a GET to the specified URL.
func (g *Geziyor) Get(url string) {
func (g *Geziyor) Get(url string, callbacks ...func(resp *Response)) {
req, err := http.NewRequest("GET", url, nil)
if err != nil {
log.Printf("Request creating error %v\n", err)
return
}
g.Do(req)
g.Do(req, callbacks...)
}
// Head issues a HEAD to the specified URL
func (g *Geziyor) Head(url string) {
func (g *Geziyor) Head(url string, callbacks ...func(resp *Response)) {
req, err := http.NewRequest("HEAD", url, nil)
if err != nil {
log.Printf("Request creating error %v\n", err)
return
}
g.Do(req)
g.Do(req, callbacks...)
}
// Do sends an HTTP request
func (g *Geziyor) Do(req *http.Request) {
func (g *Geziyor) Do(req *http.Request, callbacks ...func(resp *Response)) {
g.wg.Add(1)
defer g.wg.Done()
defer func() {
if r := recover(); r != nil {
log.Println(string(debug.Stack()))
}
}()
if !g.checkURL(req.URL) {
return
@ -157,23 +163,30 @@ func (g *Geziyor) Do(req *http.Request) {
// Release Semaphore
g.releaseSem(req)
// Create Document
doc, _ := goquery.NewDocumentFromReader(bytes.NewReader(body))
// Create response
response := Response{
Response: resp,
Body: body,
Doc: doc,
Geziyor: g,
Exports: make(chan interface{}, 1),
}
// Create HTML Document
if response.isHTML() {
response.DocHTML, _ = goquery.NewDocumentFromReader(bytes.NewReader(body))
}
// Export Function
go Export(&response)
// ParseFunc response
if len(callbacks) == 0 && g.opt.ParseFunc != nil {
g.opt.ParseFunc(&response)
} else {
for _, callback := range callbacks {
callback(&response)
}
}
time.Sleep(time.Millisecond)
}

View File

@ -14,7 +14,7 @@ func TestGeziyor_Simple(t *testing.T) {
geziyor.NewGeziyor(geziyor.Options{
StartURLs: []string{"http://api.ipify.org"},
ParseFunc: func(r *geziyor.Response) {
fmt.Println(r.Doc.Text())
fmt.Println(string(r.Body))
},
}).Start()
}
@ -24,8 +24,8 @@ func TestGeziyor_IP(t *testing.T) {
StartURLs: []string{"http://api.ipify.org"},
Cache: httpcache.NewMemoryCache(),
ParseFunc: func(r *geziyor.Response) {
fmt.Println(r.Doc.Text())
r.Exports <- r.Doc.Text()
fmt.Println(string(r.Body))
r.Exports <- string(r.Body)
r.Geziyor.Get("http://api.ipify.org")
},
})
@ -36,7 +36,7 @@ func TestGeziyor_HTML(t *testing.T) {
gez := geziyor.NewGeziyor(geziyor.Options{
StartURLs: []string{"http://quotes.toscrape.com/"},
ParseFunc: func(r *geziyor.Response) {
r.Doc.Find("div.quote").Each(func(i int, s *goquery.Selection) {
r.DocHTML.Find("div.quote").Each(func(i int, s *goquery.Selection) {
// Export Data
r.Exports <- map[string]interface{}{
"text": s.Find("span.text").Text(),
@ -48,7 +48,7 @@ func TestGeziyor_HTML(t *testing.T) {
})
// Next Page
if href, ok := r.Doc.Find("li.next > a").Attr("href"); ok {
if href, ok := r.DocHTML.Find("li.next > a").Attr("href"); ok {
go r.Geziyor.Get(r.JoinURL(href))
}
},
@ -62,7 +62,7 @@ func TestGeziyor_Concurrent_Requests(t *testing.T) {
StartURLs: []string{"http://quotes.toscrape.com/"},
ParseFunc: func(r *geziyor.Response) {
//r.Exports <- map[string]interface{}{"href": r.Request.URL.String()}
r.Doc.Find("a").Each(func(i int, s *goquery.Selection) {
r.DocHTML.Find("a").Each(func(i int, s *goquery.Selection) {
if href, ok := s.Attr("href"); ok {
go r.Geziyor.Get(r.JoinURL(href))
}

2
go.mod
View File

@ -4,6 +4,8 @@ go 1.12
require (
github.com/PuerkitoBio/goquery v1.5.0
github.com/antchfx/htmlquery v1.0.0 // indirect
github.com/antchfx/xpath v1.0.0 // indirect
github.com/fpfeng/httpcache v0.0.0-20181220155740-6b8f16a92be3
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a
golang.org/x/text v0.3.2 // indirect

4
go.sum
View File

@ -2,6 +2,10 @@ github.com/PuerkitoBio/goquery v1.5.0 h1:uGvmFXOA73IKluu/F84Xd1tt/z07GYm8X49XKHP
github.com/PuerkitoBio/goquery v1.5.0/go.mod h1:qD2PgZ9lccMbQlc7eEOjaeRlFQON7xY8kdmcsrnKqMg=
github.com/andybalholm/cascadia v1.0.0 h1:hOCXnnZ5A+3eVDX8pvgl4kofXv2ELss0bKcqRySc45o=
github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
github.com/antchfx/htmlquery v1.0.0 h1:O5IXz8fZF3B3MW+B33MZWbTHBlYmcfw0BAxgErHuaMA=
github.com/antchfx/htmlquery v1.0.0/go.mod h1:MS9yksVSQXls00iXkiMqXr0J+umL/AmxXKuP28SUJM8=
github.com/antchfx/xpath v1.0.0 h1:Q5gFgh2O40VTSwMOVbFE7nFNRBu3tS21Tn0KAWeEjtk=
github.com/antchfx/xpath v1.0.0/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
github.com/fpfeng/httpcache v0.0.0-20181220155740-6b8f16a92be3 h1:yoJ3JExhshZwcfvvQLLRqKICf4/p4gZ/mDzdQV1hRWQ=
github.com/fpfeng/httpcache v0.0.0-20181220155740-6b8f16a92be3/go.mod h1:QThlC5qj7EJa+O2HqbxzVGWLspJQHQLVsKmBtbg9ak8=
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=

View File

@ -4,6 +4,7 @@ import (
"github.com/PuerkitoBio/goquery"
"net/http"
"net/url"
"strings"
)
// Response type wraps http.Response
@ -11,7 +12,7 @@ import (
type Response struct {
*http.Response
Body []byte
Doc *goquery.Document
DocHTML *goquery.Document
Geziyor *Geziyor
Exports chan interface{}
@ -27,3 +28,13 @@ func (r *Response) JoinURL(relativeURL string) string {
joinedURL := r.Response.Request.URL.ResolveReference(parsedRelativeURL)
return joinedURL.String()
}
func (r *Response) isHTML() bool {
contentType := r.Header.Get("Content-Type")
for _, htmlContentType := range []string{"text/html", "application/xhtml+xml", "application/vnd.wap.xhtml+xml"} {
if strings.Contains(contentType, htmlContentType) {
return true
}
}
return false
}