Documentation ¶
Index ¶
- type GoSpider
- type OnErrorCallback
- type OnQueryCallback
- type OnRequestCallback
- type OnResponseCallback
- type TaskHandler
- type TaskOpt
- func TaskOptCache(path string) TaskOpt
- func TaskOptDomains(domains []string) TaskOpt
- func TaskOptEnableCookie(b bool) TaskOpt
- func TaskOptGapLimit(num int) TaskOpt
- func TaskOptGapLimitRandom(min int, max int) TaskOpt
- func TaskOptProxy(proxy []string) TaskOpt
- func TaskOptSrcCharset(charset string) TaskOpt
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type GoSpider ¶
type GoSpider struct {
// contains filtered or unexported fields
}
func NewGoSpider ¶
func NewGoSpider() *GoSpider
func (*GoSpider) AddTask ¶
func (g *GoSpider) AddTask(handler *TaskHandler)
type OnErrorCallback ¶
type OnQueryCallback ¶
type OnRequestCallback ¶
type TaskHandler ¶
type TaskHandler struct { Name string Entry string GapLimit int GapLimitMin int GapLimitMax int IdleLimit int WorkerLimit int SrcCharset string Http *req.Req Headers *req.Header Params *req.Param Domains []string Proxies []string Queue chan string QueueProcessNum int QueueTotalNum int CachePath string // contains filtered or unexported fields }
task handler
func NewTaskHandler ¶
func NewTaskHandler(name string, entry string, opts ...TaskOpt) *TaskHandler
func (*TaskHandler) Clone ¶
func (t *TaskHandler) Clone() *TaskHandler
func (*TaskHandler) Handle ¶
func (t *TaskHandler) Handle()
func (*TaskHandler) OnQuery ¶
func (t *TaskHandler) OnQuery(selector string, cb OnQueryCallback)
func (*TaskHandler) OnRequest ¶
func (t *TaskHandler) OnRequest(cb OnRequestCallback)
func (*TaskHandler) OnResponse ¶
func (t *TaskHandler) OnResponse(cb OnResponseCallback)
func (*TaskHandler) Visit ¶
func (t *TaskHandler) Visit(url string)
type TaskOpt ¶
type TaskOpt func(*TaskHandler)
func TaskOptCache ¶
func TaskOptDomains ¶
func TaskOptEnableCookie ¶
func TaskOptGapLimit ¶
func TaskOptGapLimitRandom ¶ added in v1.0.2
func TaskOptProxy ¶
func TaskOptSrcCharset ¶
Click to show internal directories.
Click to hide internal directories.