finalize debug logging

This commit is contained in:
Amrit Panesar committed 2020-10-29 15:37:03 -07:00
1 parent b87ac1bb0e
commit ec30c6e4b2
8 files changed
+57 -27

No files matched your search

+8
View File
@@ -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>
+8
View File
@@ -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
View File
@@ -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>
BIN
View File
Binary file not shown.
+2 -2
View File
@@ -1,7 +1,7 @@
package main
import (
cboxscraper ".."
cboxscraper "github.com/Neo-Desktop/go-cbox-scraper"
"log"
)
@@ -12,7 +12,7 @@ func main() {
WebHostID: 6,
BoxID: 850801,
BoxTag: "hD3VIj",
Debug: true,
Debug: false,
}
scraper := cboxscraper.NewScraper(info, -1, -1)
+1 -4
View File
@@ -3,7 +3,6 @@ package go_cbox_scraper
import (
"errors"
"fmt"
"log"
"net/http"
"net/url"
"regexp"
@@ -136,9 +135,7 @@ func (p *CBoxPage) FetchNext() error {
}
func (p *CBoxPage) request(request *http.Request) (*goquery.Document, error) {
if p.Debug {
log.Println(request.URL.String())
}
p.debugPrintln(request.URL.String())
httpClient := &http.Client{
Timeout: 30 * time.Second,
+10 -21
View File
@@ -2,7 +2,6 @@ package go_cbox_scraper
import (
"encoding/gob"
"log"
"os"
"time"
)
@@ -26,16 +25,12 @@ func NewScraper(cboxServerInfo CBoxServerInfo, smallestID int, largestID int) *C
}
func (s *CBoxScraper) sleep() {
if s.Debug {
log.Println("Sleeping 10 seconds...")
}
s.debugPrintln("Sleeping 10 seconds...")
time.Sleep(10 * time.Second)
}
func (s *CBoxScraper) Scrape(updatesOnly bool) error {
if s.Debug {
log.Println("Scraper Started...")
}
s.debugPrintln("Scraper Started...")
page := NewCBoxPage(s.CBoxServerInfo)
@@ -44,16 +39,12 @@ func (s *CBoxScraper) Scrape(updatesOnly bool) error {
return err
}
if s.Debug {
log.Printf("Main fetched, scraped %d messages\n", len(page.Messages))
log.Printf("\tpage smallestID: %d - scraper smallestID: %d\n", page.SmallestID(), s.SmallestMessageID)
log.Printf("\tpage largestID: %d - scraper LargestID: %d\n", page.LargestID(), s.LargestMessageID)
}
s.debugPrintf("Main fetched, scraped %d messages\n", len(page.Messages))
s.debugPrintf("\tpage smallestID: %d - scraper smallestID: %d\n", page.SmallestID(), s.SmallestMessageID)
s.debugPrintf("\tpage largestID: %d - scraper LargestID: %d\n", page.LargestID(), s.LargestMessageID)
if updatesOnly && s.LargestMessageID < page.SmallestID() {
if s.Debug {
log.Println("Scraper: Case 3 - lots of new messages")
}
s.debugPrintln("Scraper: Case 3 - lots of new messages")
s.sleep()
for s.LargestMessageID < page.smallestID {
err := page.FetchPrevious()
@@ -64,11 +55,11 @@ func (s *CBoxScraper) Scrape(updatesOnly bool) error {
}
s.merge(page.Messages)
} 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
s.merge(page.Messages)
} else if !updatesOnly {
log.Println("Scraper: Case 4 - fetch all")
s.debugPrintln("Scraper: Case 4 - fetch all")
s.sleep()
for {
err := page.FetchPrevious()
@@ -79,12 +70,10 @@ func (s *CBoxScraper) Scrape(updatesOnly bool) error {
}
s.merge(page.Messages)
} else {
log.Println("Scraper: Case 0 - no update")
s.debugPrintln("Scraper: Case 0 - no update")
}
if s.Debug {
log.Printf("Archives fetched, scraped %d messages - page smallestID: %d\n", len(page.Messages), page.SmallestID())
}
s.debugPrintf("Archives fetched, scraped %d messages - page smallestID: %d\n", len(page.Messages), page.SmallestID())
return nil
}
+22
View File
@@ -1,8 +1,30 @@
package go_cbox_scraper
import (
"log"
)
type CBoxServerInfo struct {
WebHostID int
BoxID int
BoxTag string
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...)
}
}