func (this *Spider) AddUrlsEx(urls []string, respType string, headerFile string, proxyHost string) *Spider {
for _, url := range urls {
req := request.NewRequest(url, respType, "", "GET", "", nil, nil, nil, nil)
this.AddRequest(req.AddHeaderFile(headerFile).AddProxyHost(proxyHost))
}
return this
}
func (this *Spider) AddUrls(urls []string, respType string) *Spider {
for _, url := range urls {
req := request.NewRequest(url, respType, "", "GET", "", nil, nil, nil, nil)
this.AddRequest(req)
}
return this
}
func TestQueueScheduler(t *testing.T) {
var r *request.Request
r = request.NewRequest("http://baidu.com", "html", "", "GET", "", nil, nil, nil, nil)
fmt.Printf("%v\n", r)
var s *scheduler.QueueScheduler
s = scheduler.NewQueueScheduler(false)
s.Push(r)
var count int = s.Count()
if count != 1 {
t.Error("count error")
}
fmt.Println(count)
var r1 *request.Request
r1 = s.Poll()
if r1 == nil {
t.Error("poll error")
}
fmt.Printf("%v\n", r1)
// remove duplicate
s = scheduler.NewQueueScheduler(true)
r2 := request.NewRequest("http://qq.com", "html", "", "GET", "", nil, nil, nil, nil)
s.Push(r)
s.Push(r2)
s.Push(r)
count = s.Count()
if count != 2 {
t.Error("count error")
}
fmt.Println(count)
r1 = s.Poll()
if r1 == nil {
t.Error("poll error")
}
fmt.Printf("%v\n", r1)
r1 = s.Poll()
if r1 == nil {
t.Error("poll error")
}
fmt.Printf("%v\n", r1)
}
// Deal with several urls and return the PageItems slice.
func (this *Spider) GetAll(urls []string, respType string) []*page_items.PageItems {
for _, u := range urls {
req := request.NewRequest(u, respType, "", "GET", "", nil, nil, nil, nil)
this.AddRequest(req)
}
pip := pipeline.NewCollectPipelinePageItems()
this.AddPipeline(pip)
this.Run()
return pip.GetCollected()
}
//自定义函数
func (this *Page) AddMyTargetRequest(url, respType, urltag, resqType, postdata, proxy, heardefile, cookie string) *Page {
req := request.NewRequest(url, respType, urltag, resqType, postdata, nil, nil, nil, nil)
if cookie == "" {
print(cookie)
}
if heardefile != "" {
req.AddHeaderFile(heardefile)
}
if proxy != "" {
ip := util.GetIp()
req.AddProxyHost(ip)
}
this.targetRequests = append(this.targetRequests, req)
return this
}
func (this *Spider) AddMyUrl(url, respType, urltag, resqType, postdata, proxy, heardefile, cookie string) *Spider {
req := request.NewRequest(url, respType, urltag, resqType, postdata, nil, nil, nil, nil)
if cookie != "" {
print(cookie)
}
if heardefile != "" {
req.AddHeaderFile(heardefile)
}
if proxy != "" {
ip := util.GetIp()
req.AddProxyHost(ip)
}
this.AddRequest(req)
return this
}
func TestDownloadHtml(t *testing.T) {
//return
//request := request.NewRequest("http://live.sina.com.cn/zt/api/l/get/finance/globalnews1/index.htm?format=json&callback=t13975294&id=23521&pagesize=45&dire=f&dpc=1")
var req *request.Request
req = request.NewRequest("http://live.sina.com.cn/zt/l/v/finance/globalnews1/", "html", "", "GET", "", nil, nil, nil, nil)
var dl downloader.Downloader
dl = downloader.NewHttpDownloader()
var p *page.Page
p = dl.Download(req)
var doc *goquery.Document
doc = p.GetHtmlParser()
//fmt.Println(doc)
//body := p.GetBodyStr()
//fmt.Println(body)
var s *goquery.Selection
s = doc.Find("body")
if s.Length() < 1 {
t.Error("html parse failed!")
}
/*
doc, err := goquery.NewDocument("http://live.sina.com.cn/zt/l/v/finance/globalnews1/")
if err != nil {
fmt.Printf("%v",err)
}
s := doc.Find("meta");
fmt.Println(s.Length())
resp, err := http.Get("http://live.sina.com.cn/zt/l/v/finance/globalnews1/")
if err != nil {
fmt.Printf("%v",err)
}
defer resp.Body.Close()
doc, err = goquery.NewDocumentFromReader(resp.Body)
s = doc.Find("meta");
fmt.Println(s.Length())
*/
}
func TestCharSetChange(t *testing.T) {
var req *request.Request
//req = request.NewRequest("http://stock.finance.sina.com.cn/usstock/api/jsonp.php/t/US_CategoryService.getList?page=1&num=60", "jsonp")
req = request.NewRequest("http://soft.chinabyte.com/416/13164916.shtml", "html", "", "GET", "", nil, nil, nil, nil)
var dl downloader.Downloader
dl = downloader.NewHttpDownloader()
var p *page.Page
p = dl.Download(req)
//hp := p.GetHtmlParser()
//fmt.Printf("%v", jsonMap)
//fmt.Println(doc)
p.GetBodyStr()
body := p.GetBodyStr()
fmt.Println(body)
}
func TestDownloadJson(t *testing.T) {
//return
var req *request.Request
req = request.NewRequest("http://live.sina.com.cn/zt/api/l/get/finance/globalnews1/index.htm?format=json&id=23521&pagesize=4&dire=f&dpc=1", "json", "", "GET", "", nil, nil, nil, nil)
var dl downloader.Downloader
dl = downloader.NewHttpDownloader()
var p *page.Page
p = dl.Download(req)
var jsonMap interface{}
jsonMap = p.GetJson()
fmt.Printf("%v", jsonMap)
//fmt.Println(doc)
//body := p.GetBodyStr()
//fmt.Println(body)
}
// AddTargetRequest adds one new Request waitting for crawl.
func (this *Page) AddTargetRequest(url string, respType string) *Page {
this.targetRequests = append(this.targetRequests, request.NewRequest(url, respType, "", "GET", "", nil, nil, nil, nil))
return this
}
func (this *Spider) AddUrl(url string, respType string) *Spider {
req := request.NewRequest(url, respType, "", "GET", "", nil, nil, nil, nil)
this.AddRequest(req)
return this
}
// Deal with one url and return the PageItems.
func (this *Spider) Get(url string, respType string) *page_items.PageItems {
req := request.NewRequest(url, respType, "", "GET", "", nil, nil, nil, nil)
return this.GetByRequest(req)
}