finalize debug logging
This commit is contained in:
1 parent
b87ac1bb0e
commit
ec30c6e4b2
8 files changed
+57
-27
No files matched your search
Generated
+8
@@ -0,0 +1,8 @@
|
|||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<module type="WEB_MODULE" version="4">
|
||||||
|
<component name="NewModuleRootManager">
|
||||||
|
<content url="file://$MODULE_DIR$" />
|
||||||
|
<orderEntry type="inheritedJdk" />
|
||||||
|
<orderEntry type="sourceFolder" forTests="false" />
|
||||||
|
</component>
|
||||||
|
</module>
|
||||||
Generated
+8
@@ -0,0 +1,8 @@
|
|||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<project version="4">
|
||||||
|
<component name="ProjectModuleManager">
|
||||||
|
<modules>
|
||||||
|
<module fileurl="file://$PROJECT_DIR$/.idea/go-cbox-scraper.iml" filepath="$PROJECT_DIR$/.idea/go-cbox-scraper.iml" />
|
||||||
|
</modules>
|
||||||
|
</component>
|
||||||
|
</project>
|
||||||
Generated
+6
@@ -0,0 +1,6 @@
|
|||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<project version="4">
|
||||||
|
<component name="VcsDirectoryMappings">
|
||||||
|
<mapping directory="$PROJECT_DIR$" vcs="Git" />
|
||||||
|
</component>
|
||||||
|
</project>
|
||||||
Binary file not shown.
+2
-2
@@ -1,7 +1,7 @@
|
|||||||
package main
|
package main
|
||||||
|
|
||||||
import (
|
import (
|
||||||
cboxscraper ".."
|
cboxscraper "github.com/Neo-Desktop/go-cbox-scraper"
|
||||||
"log"
|
"log"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -12,7 +12,7 @@ func main() {
|
|||||||
WebHostID: 6,
|
WebHostID: 6,
|
||||||
BoxID: 850801,
|
BoxID: 850801,
|
||||||
BoxTag: "hD3VIj",
|
BoxTag: "hD3VIj",
|
||||||
Debug: true,
|
Debug: false,
|
||||||
}
|
}
|
||||||
|
|
||||||
scraper := cboxscraper.NewScraper(info, -1, -1)
|
scraper := cboxscraper.NewScraper(info, -1, -1)
|
||||||
|
|||||||
@@ -3,7 +3,6 @@ package go_cbox_scraper
|
|||||||
import (
|
import (
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"log"
|
|
||||||
"net/http"
|
"net/http"
|
||||||
"net/url"
|
"net/url"
|
||||||
"regexp"
|
"regexp"
|
||||||
@@ -136,9 +135,7 @@ func (p *CBoxPage) FetchNext() error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (p *CBoxPage) request(request *http.Request) (*goquery.Document, error) {
|
func (p *CBoxPage) request(request *http.Request) (*goquery.Document, error) {
|
||||||
if p.Debug {
|
p.debugPrintln(request.URL.String())
|
||||||
log.Println(request.URL.String())
|
|
||||||
}
|
|
||||||
|
|
||||||
httpClient := &http.Client{
|
httpClient := &http.Client{
|
||||||
Timeout: 30 * time.Second,
|
Timeout: 30 * time.Second,
|
||||||
|
|||||||
+10
-21
@@ -2,7 +2,6 @@ package go_cbox_scraper
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"encoding/gob"
|
"encoding/gob"
|
||||||
"log"
|
|
||||||
"os"
|
"os"
|
||||||
"time"
|
"time"
|
||||||
)
|
)
|
||||||
@@ -26,16 +25,12 @@ func NewScraper(cboxServerInfo CBoxServerInfo, smallestID int, largestID int) *C
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (s *CBoxScraper) sleep() {
|
func (s *CBoxScraper) sleep() {
|
||||||
if s.Debug {
|
s.debugPrintln("Sleeping 10 seconds...")
|
||||||
log.Println("Sleeping 10 seconds...")
|
|
||||||
}
|
|
||||||
time.Sleep(10 * time.Second)
|
time.Sleep(10 * time.Second)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (s *CBoxScraper) Scrape(updatesOnly bool) error {
|
func (s *CBoxScraper) Scrape(updatesOnly bool) error {
|
||||||
if s.Debug {
|
s.debugPrintln("Scraper Started...")
|
||||||
log.Println("Scraper Started...")
|
|
||||||
}
|
|
||||||
|
|
||||||
page := NewCBoxPage(s.CBoxServerInfo)
|
page := NewCBoxPage(s.CBoxServerInfo)
|
||||||
|
|
||||||
@@ -44,16 +39,12 @@ func (s *CBoxScraper) Scrape(updatesOnly bool) error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
if s.Debug {
|
s.debugPrintf("Main fetched, scraped %d messages\n", len(page.Messages))
|
||||||
log.Printf("Main fetched, scraped %d messages\n", len(page.Messages))
|
s.debugPrintf("\tpage smallestID: %d - scraper smallestID: %d\n", page.SmallestID(), s.SmallestMessageID)
|
||||||
log.Printf("\tpage smallestID: %d - scraper smallestID: %d\n", page.SmallestID(), s.SmallestMessageID)
|
s.debugPrintf("\tpage largestID: %d - scraper LargestID: %d\n", page.LargestID(), s.LargestMessageID)
|
||||||
log.Printf("\tpage largestID: %d - scraper LargestID: %d\n", page.LargestID(), s.LargestMessageID)
|
|
||||||
}
|
|
||||||
|
|
||||||
if updatesOnly && s.LargestMessageID < page.SmallestID() {
|
if updatesOnly && s.LargestMessageID < page.SmallestID() {
|
||||||
if s.Debug {
|
s.debugPrintln("Scraper: Case 3 - lots of new messages")
|
||||||
log.Println("Scraper: Case 3 - lots of new messages")
|
|
||||||
}
|
|
||||||
s.sleep()
|
s.sleep()
|
||||||
for s.LargestMessageID < page.smallestID {
|
for s.LargestMessageID < page.smallestID {
|
||||||
err := page.FetchPrevious()
|
err := page.FetchPrevious()
|
||||||
@@ -64,11 +55,11 @@ func (s *CBoxScraper) Scrape(updatesOnly bool) error {
|
|||||||
}
|
}
|
||||||
s.merge(page.Messages)
|
s.merge(page.Messages)
|
||||||
} else if updatesOnly && s.LargestMessageID < page.LargestID() {
|
} else if updatesOnly && s.LargestMessageID < page.LargestID() {
|
||||||
log.Println("Scraper: Case 2 - Some new Messages")
|
s.debugPrintln("Scraper: Case 2 - Some new Messages")
|
||||||
// merge what we retrieved
|
// merge what we retrieved
|
||||||
s.merge(page.Messages)
|
s.merge(page.Messages)
|
||||||
} else if !updatesOnly {
|
} else if !updatesOnly {
|
||||||
log.Println("Scraper: Case 4 - fetch all")
|
s.debugPrintln("Scraper: Case 4 - fetch all")
|
||||||
s.sleep()
|
s.sleep()
|
||||||
for {
|
for {
|
||||||
err := page.FetchPrevious()
|
err := page.FetchPrevious()
|
||||||
@@ -79,12 +70,10 @@ func (s *CBoxScraper) Scrape(updatesOnly bool) error {
|
|||||||
}
|
}
|
||||||
s.merge(page.Messages)
|
s.merge(page.Messages)
|
||||||
} else {
|
} else {
|
||||||
log.Println("Scraper: Case 0 - no update")
|
s.debugPrintln("Scraper: Case 0 - no update")
|
||||||
}
|
}
|
||||||
|
|
||||||
if s.Debug {
|
s.debugPrintf("Archives fetched, scraped %d messages - page smallestID: %d\n", len(page.Messages), page.SmallestID())
|
||||||
log.Printf("Archives fetched, scraped %d messages - page smallestID: %d\n", len(page.Messages), page.SmallestID())
|
|
||||||
}
|
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,8 +1,30 @@
|
|||||||
package go_cbox_scraper
|
package go_cbox_scraper
|
||||||
|
|
||||||
|
import (
|
||||||
|
"log"
|
||||||
|
)
|
||||||
|
|
||||||
type CBoxServerInfo struct {
|
type CBoxServerInfo struct {
|
||||||
WebHostID int
|
WebHostID int
|
||||||
BoxID int
|
BoxID int
|
||||||
BoxTag string
|
BoxTag string
|
||||||
Debug bool
|
Debug bool
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func (c *CBoxServerInfo) debugPrint(args ... interface{}) {
|
||||||
|
if c.Debug {
|
||||||
|
log.Print(args...)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (c *CBoxServerInfo) debugPrintf(format string, args ... interface{}) {
|
||||||
|
if c.Debug {
|
||||||
|
log.Printf(format, args...)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (c *CBoxServerInfo) debugPrintln(args ... interface{}) {
|
||||||
|
if c.Debug {
|
||||||
|
log.Println(args...)
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in new issue
Block a user