Documentation
¶
Index ¶
- func Crawler(running *int32, group *sync.WaitGroup, jbd *JobDB, dbd *DoneDB, config Config, ...)
- func GetChromeWSEndpoint() string
- func GetSize(db *DB) int
- func Ini()
- func InsertSpider(db *DB, title string, name string, url string)
- func Parser(running *int32, group *sync.WaitGroup, jbd *JobDB, dbd *DoneDB, config Config, ...)
- func Saver(running *int32, group *sync.WaitGroup, save <-chan interface{}, stat *Stat, ...)
- func Start(ctx *Content, config Config, url string, stat *Stat)
- type Config
- type Content
- type DB
- type DBLinkInfo
- type DoneDB
- type FindData
- type JobDB
- type LoopSpider
- type LoopSpiderSlot
- type LoopSpiderStatus
- type PageInfo
- type PageLinkInfo
- type SpiderData
- type Stat
- type URLInfo
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func GetChromeWSEndpoint ¶
func GetChromeWSEndpoint() string
Types ¶
type LoopSpider ¶
type LoopSpider struct {
Thread int
Buffer int
Cur string
// contains filtered or unexported fields
}
func NewLoopSpider ¶
func NewLoopSpider(lss LoopSpiderSlot) *LoopSpider
func (*LoopSpider) GetLoopSpiderStatus ¶
func (ls *LoopSpider) GetLoopSpiderStatus() LoopSpiderStatus
type LoopSpiderSlot ¶
type LoopSpiderStatus ¶
type PageInfo ¶
type PageInfo struct {
UI URLInfo
Title string
Son []PageLinkInfo
}
type PageLinkInfo ¶
type SpiderData ¶
type SpiderData struct {
// contains filtered or unexported fields
}
type Stat ¶
type Stat struct {
CrawBePushJobNum int
CrawChannelNum int
CrawFunc string
CrawNum int
CrawRetrtyNum int
CrawOKNum int64
CrawFailNum int
CrawOKTotalTime int64
CrawOKAvgTime int64
ParseChannelNum int
ParseNum int
ParseValidNum int
ParseSpawnNum int
ParseFinishNum int
ParseTooDeepNum int
ParseJobNum int
SaveChannelNum int
SaveNum int
InsertNum int64
InsertTotalTime int64
InsertAvgTime int64
JobInsertNum int64
JobInsertTotalTime int64
JobInsertAvgTime int64
JobPopNum int64
JobPopTotalTime int64
JobPopAvgTime int64
JobHasNum int64
JobHasTotalTime int64
JobHasAvgTime int64
DoneInsertNum int64
DoneInsertTotalTime int64
DoneInsertAvgTime int64
DoneHasNum int64
DoneHasTotalTime int64
DoneHasAvgTime int64
}
Click to show internal directories.
Click to hide internal directories.