commit 34a523fa7c9b27737e52106e98cd0ed650e4eafc Author: skidoodle Date: Tue Dec 31 01:50:12 2024 +0100 first commit diff --git a/.env.example b/.env.example new file mode 100644 index 0000000..bb2865e --- /dev/null +++ b/.env.example @@ -0,0 +1,4 @@ +NICK= +# pass= from Set-Cookie header in lower security mode +# set-cookie: pass=<...>; ... +PASS= diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..11ee758 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +.env.local diff --git a/go.mod b/go.mod new file mode 100644 index 0000000..278c658 --- /dev/null +++ b/go.mod @@ -0,0 +1,12 @@ +module scrapencore + +go 1.23 + +toolchain go1.23.2 + +require ( + github.com/PuerkitoBio/goquery v1.10.0 // indirect + github.com/andybalholm/cascadia v1.3.2 // indirect + github.com/joho/godotenv v1.5.1 // indirect + golang.org/x/net v0.30.0 // indirect +) diff --git a/go.sum b/go.sum new file mode 100644 index 0000000..367fe40 --- /dev/null +++ b/go.sum @@ -0,0 +1,42 @@ +github.com/PuerkitoBio/goquery v1.10.0 h1:6fiXdLuUvYs2OJSvNRqlNPoBm6YABE226xrbavY5Wv4= +github.com/PuerkitoBio/goquery v1.10.0/go.mod h1:TjZZl68Q3eGHNBA8CWaxAN7rOU1EbDz3CWuolcO5Yu4= +github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss= +github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU= +github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0= +github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4= +github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= +golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= +golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= +golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= +golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= +golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns= +golang.org/x/net v0.30.0 h1:AcW1SDZMkb8IpzCdQUaIq2sP4sZ4zw+55h6ynffypl4= +golang.org/x/net v0.30.0/go.mod h1:2wGyMJ5iFasEhkwi13ChkO/t1ECNC4X4eBKkVFyYFlU= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= +golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY= +golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= +golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= +golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= +golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= diff --git a/main.go b/main.go new file mode 100644 index 0000000..257e1db --- /dev/null +++ b/main.go @@ -0,0 +1,132 @@ +package main + +import ( + "encoding/csv" + "fmt" + "log" + "net/http" + "os" + "strings" + "sync" + "time" + + "github.com/PuerkitoBio/goquery" + "github.com/joho/godotenv" +) + +const ( + baseURL = "https://ncore.pro/profile.php?id=" + startProfile = 1 + endProfile = 1812000 + concurrency = 50 + outputFile = "output.log" +) + +var ( + nick string + pass string + client *http.Client + wg sync.WaitGroup + mu sync.Mutex +) + +func init() { + _ = godotenv.Load(".env.local") + godotenv.Load() + nick = os.Getenv("NICK") + pass = os.Getenv("PASS") + client = &http.Client{} +} + +func fetchProfile(id int) { + defer wg.Done() + url := fmt.Sprintf("%s%d", baseURL, id) + + req, err := http.NewRequest("GET", url, nil) + if err != nil { + log.Printf("Error creating request for %d: %v\n", id, err) + return + } + req.Header.Set("Cookie", fmt.Sprintf("nick=%s; pass=%s", nick, pass)) + + resp, err := client.Do(req) + if err != nil { + log.Printf("Error fetching profile %d: %v\n", id, err) + return + } + defer resp.Body.Close() + + if resp.StatusCode != http.StatusOK { + return + } + + doc, err := goquery.NewDocumentFromReader(resp.Body) + if err != nil { + log.Printf("Error parsing profile document for %d: %v\n", id, err) + return + } + + doc.Find(".userbox_tartalom_mini").Each(func(i int, s *goquery.Selection) { + s.Find(".profil_jobb_elso2").Each(func(ii int, labelSel *goquery.Selection) { + label := labelSel.Text() + valueSel := labelSel.Next() + if valueSel.Length() > 0 { + value := valueSel.Text() + switch label { + case "Helyezés:": + rank := strings.TrimSuffix(value, ".") + mu.Lock() + logToFile(url, rank) + mu.Unlock() + fmt.Printf("\rProcessed %d/%d profiles...", id, endProfile) + } + } + }) + }) +} + +func logToFile(url string, rank string) { + file, err := os.OpenFile(outputFile, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0644) + if err != nil { + log.Fatalf("Error opening output file: %v\n", err) + } + defer file.Close() + + writer := csv.NewWriter(file) + defer writer.Flush() + + if err := writer.Write([]string{url, rank}); err != nil { + log.Fatalf("Error writing to output file: %v\n", err) + } +} + +func main() { + if _, err := os.Stat(outputFile); err == nil { + var response string + fmt.Printf("Output file %s already exists. Overwrite? (yes/no): ", outputFile) + fmt.Scanln(&response) + if response != "yes" { + log.Println("Exiting. Please rename or remove the existing output file.") + return + } + err := os.Remove(outputFile) + if err != nil { + log.Fatalf("Failed to remove existing output file: %v\n", err) + } + } + + fmt.Println("Scraping in progress...") + startTime := time.Now() + + for i := startProfile; i <= endProfile; i++ { + wg.Add(1) + go fetchProfile(i) + + if i%concurrency == 0 { + wg.Wait() + } + } + wg.Wait() + elapsedTime := time.Since(startTime) + fmt.Printf("\nScraping completed in %s\n", elapsedTime) +}