Merge pull request 'v1.0.0' (#1) from develop into main

Reviewed-on: #1

README.md

@@ -0,0 +1,23 @@
+# blocklist
+
+Пакет Go для получения IP адресов от различных сервисов.
+
+## Установка
+```sh
+go get git.kor-elf.net/kor-elf-shield/blocklist
+```
+
+## Примеры использования
+- [Пример получения списка IP адресов от Spamhaus](/examples/spamhaus.go)
+- [Пример получения списка IP адресов от DShield](/examples/dshield.go)
+- [Пример получения списка IP адресов от HONEYPOT](/examples/honeypot.go)
+- [Пример получения списка IP адресов от Tor](/examples/tor.go)
+- [Пример получения списка IP адресов от CIARMY](/examples/ciarmy.go)
+- [Пример получения списка IP адресов от Daniel Gerzo (BruteforceBlocker)](/examples/bruteforceblocker.go)
+- [Пример получения списка IP адресов от Blocklist.de](/examples/blocklist.go)
+- [Пример получения списка IP адресов от GreenSnow](/examples/greensnow.go)
+- [Пример получения списка IP адресов от StopForumSpam](/examples/stopforumspam.go)
+
+## Лицензия
+
+[MIT](https://git.kor-elf.net/kor-elf-shield/blocklist/src/branch/main/LICENSE)

blocklist.go

@@ -1,10 +1,14 @@
 package blocklist
 
 import (
+	"archive/zip"
+	"bytes"
 	"context"
 	"fmt"
+	"io"
 	"net/http"
 	"net/url"
+	"strings"
 	"time"
 
 	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
@@ -16,6 +20,12 @@ const (
 
 	// requestTimeout defines the maximum duration for request operations before timing out.
 	requestTimeout = 20 * time.Second
+
+	// maxDownloadSize defines the maximum allowed size of the downloaded file in bytes.
+	maxDownloadSize int64 = 20 << 20 // 20 MiB
+
+	// maxArchiveFileSize defines the maximum allowed size of the extracted file from ZIP in bytes.
+	maxArchiveFileSize uint64 = 50 << 20 // 50 MiB
 )
 
 // Config defines the configuration for the blocklist.
@@ -34,6 +44,17 @@ type Config struct {
 	RequestTimeout time.Duration
 }
 
+type ConfigZip struct {
+	// Config is the configuration for the blocklist.
+	Config Config
+
+	// MaxDownloadSize defines the maximum allowed size of the downloaded file in bytes.
+	MaxDownloadSize int64
+
+	// MaxArchiveFileSize defines the maximum allowed size of the extracted file from ZIP in bytes.
+	MaxArchiveFileSize uint64
+}
+
 // NewConfig creates a new Config with default values.
 // limit is the maximum number of items to process or validate. 0 means no limit.
 func NewConfig(limit uint) Config {
@@ -57,6 +78,14 @@ func NewConfigWithValidator(limit uint, validator parser.IPValidator) Config {
 	}
 }
 
+func NewConfigZip(c Config) ConfigZip {
+	return ConfigZip{
+		Config:             c,
+		MaxDownloadSize:    maxDownloadSize,
+		MaxArchiveFileSize: maxArchiveFileSize,
+	}
+}
+
 // Get fetches data from the given URL, parses the response using the provided parser, and applies the given configuration.
 // It returns the parsed IPs and any errors that occurred during the process.
 func Get(fileUrl string, parser parser.Parser, c Config) (parser.IPs, error) {
@@ -94,3 +123,126 @@ func Get(fileUrl string, parser parser.Parser, c Config) (parser.IPs, error) {
 
 	return parser.Parse(res.Body, c.Validator, c.Limit)
 }
+
+// GetZip fetches data from the given URL, parses the response using the provided parser, and applies the given configuration.
+// It returns the parsed IPs and any errors that occurred during the process.
+func GetZip(fileUrl string, parser parser.Parser, c ConfigZip) (parser.IPs, error) {
+	parsedURL, err := url.Parse(fileUrl)
+	if err != nil {
+		return nil, fmt.Errorf("invalid url: %w", err)
+	}
+	if parsedURL.Scheme != "http" && parsedURL.Scheme != "https" {
+		return nil, fmt.Errorf("invalid url scheme: %s", parsedURL.Scheme)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), c.Config.ContextTimeout)
+	defer cancel()
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, fileUrl, nil)
+	if err != nil {
+		return nil, fmt.Errorf("create request: %w", err)
+	}
+
+	client := &http.Client{
+		Timeout: c.Config.RequestTimeout,
+	}
+
+	res, err := client.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("request failed: %w", err)
+	}
+	defer func() {
+		_ = res.Body.Close()
+	}()
+
+	if res.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("unexpected status code: %d", res.StatusCode)
+	}
+
+	if c.MaxDownloadSize > 0 && res.ContentLength > c.MaxDownloadSize {
+		return nil, fmt.Errorf("downloaded file is too large: content-length %d exceeds limit %d", res.ContentLength, c.MaxDownloadSize)
+	}
+
+	reader := res.Body
+	if c.MaxDownloadSize > 0 {
+		reader = io.NopCloser(io.LimitReader(res.Body, c.MaxDownloadSize+1))
+	}
+
+	body, err := io.ReadAll(reader)
+	if err != nil {
+		return nil, fmt.Errorf("read response body: %w", err)
+	}
+
+	if c.MaxDownloadSize > 0 && int64(len(body)) > c.MaxDownloadSize {
+		return nil, fmt.Errorf("downloaded file exceeds limit %d bytes", c.MaxDownloadSize)
+	}
+
+	if !isZip(body) {
+		return nil, fmt.Errorf("invalid zip archive")
+	}
+
+	return parseZip(body, parser, c)
+}
+
+func isZip(body []byte) bool {
+	return len(body) >= 4 &&
+		body[0] == 'P' &&
+		body[1] == 'K' &&
+		body[2] == 0x03 &&
+		body[3] == 0x04
+}
+
+func parseZip(body []byte, p parser.Parser, c ConfigZip) (parser.IPs, error) {
+	reader, err := zip.NewReader(bytes.NewReader(body), int64(len(body)))
+	if err != nil {
+		return nil, fmt.Errorf("open zip archive: %w", err)
+	}
+
+	file := findArchiveFile(reader.File)
+	if file == nil {
+		return nil, fmt.Errorf("zip archive does not contain a supported file")
+	}
+
+	if c.MaxArchiveFileSize > 0 && file.UncompressedSize64 > c.MaxArchiveFileSize {
+		return nil, fmt.Errorf("file %q in zip is too large: %d exceeds limit %d", file.Name, file.UncompressedSize64, c.MaxArchiveFileSize)
+	}
+
+	rc, err := file.Open()
+	if err != nil {
+		return nil, fmt.Errorf("open file %q from zip: %w", file.Name, err)
+	}
+	defer func() {
+		_ = rc.Close()
+	}()
+
+	var zipReader io.Reader = rc
+	if c.MaxArchiveFileSize > 0 {
+		zipReader = io.LimitReader(rc, int64(c.MaxArchiveFileSize)+1)
+	}
+
+	return p.Parse(zipReader, c.Config.Validator, c.Config.Limit)
+}
+
+func findArchiveFile(files []*zip.File) *zip.File {
+	var fallback *zip.File
+
+	for _, file := range files {
+		if file.FileInfo().IsDir() {
+			continue
+		}
+
+		if fallback == nil {
+			fallback = file
+		}
+
+		name := strings.ToLower(file.Name)
+		if strings.HasSuffix(name, ".txt") ||
+			strings.HasSuffix(name, ".json") ||
+			strings.HasSuffix(name, ".xml") ||
+			strings.HasSuffix(name, ".rss") {
+			return file
+		}
+	}
+
+	return fallback
+}

examples/blocklist.go

@@ -0,0 +1,50 @@
+package main
+
+import (
+	"fmt"
+
+	"git.kor-elf.net/kor-elf-shield/blocklist"
+	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
+)
+
+/**
+ * An example of how to get a list of IP addresses from a service https://www.blocklist.de/en/export.html
+ */
+
+func main() {
+	// Getting a list of IP addresses that were entered in the last hour
+	// time=seconds
+	url := "https://api.blocklist.de/getlast.php?time=3600"
+	extract := parser.NewDefaultTextExtract(0, "\t")
+	pars, err := parser.NewText(extract)
+	if err != nil {
+		panic(err)
+	}
+	// limit 0 - no limit
+	limit := uint(0)
+	config := blocklist.NewConfig(limit)
+	ips, err := blocklist.Get(url, pars, config)
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(ips)
+
+	/*
+		// This second list retrieves all the IP addresses added in the last 48 hours and is usually a
+		// very large list (over 10000 entries), so be sure that you have the resources available to use it
+		url := "http://lists.blocklist.de/lists/all.txt"
+		extract := parser.NewDefaultTextExtract(0, "\t")
+		pars, err := parser.NewText(extract)
+		if err != nil {
+			panic(err)
+		}
+		// limit 0 - no limit
+		limit := uint(0)
+		config := blocklist.NewConfig(limit)
+		ips, err := blocklist.Get(url, pars, config)
+		if err != nil {
+			panic(err)
+		}
+		fmt.Println(ips)
+	*/
+}

examples/bruteforceblocker.go

@@ -0,0 +1,29 @@
+package main
+
+import (
+	"fmt"
+
+	"git.kor-elf.net/kor-elf-shield/blocklist"
+	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
+)
+
+/**
+ * An example of how to get a list of IP addresses from a service https://danger.rulez.sk/index.php/bruteforceblocker/
+ */
+
+func main() {
+	url := "https://danger.rulez.sk/projects/bruteforceblocker/blist.php"
+	extract := parser.NewDefaultTextExtract(0, "\t")
+	pars, err := parser.NewText(extract)
+	if err != nil {
+		panic(err)
+	}
+	// limit 0 - no limit
+	limit := uint(0)
+	config := blocklist.NewConfig(limit)
+	ips, err := blocklist.Get(url, pars, config)
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(ips)
+}

examples/ciarmy.go

@@ -0,0 +1,29 @@
+package main
+
+import (
+	"fmt"
+
+	"git.kor-elf.net/kor-elf-shield/blocklist"
+	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
+)
+
+/**
+ * An example of how to get a list of IP addresses from a service https://www.ciarmy.com/#list
+ */
+
+func main() {
+	url := "https://www.ciarmy.com/list/ci-badguys.txt"
+	extract := parser.NewDefaultTextExtract(0, " ")
+	pars, err := parser.NewText(extract)
+	if err != nil {
+		panic(err)
+	}
+	// limit 0 - no limit
+	limit := uint(0)
+	config := blocklist.NewConfig(limit)
+	ips, err := blocklist.Get(url, pars, config)
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(ips)
+}

examples/dshield.go

@@ -8,7 +8,7 @@ import (
 )
 
 /**
- * An example of how to get a list of bad IP addresses from the service https://dshield.org/
+ * An example of how to get a list of IP addresses from a service https://dshield.org/
  */
 
 func main() {

examples/greensnow.go

@@ -0,0 +1,29 @@
+package main
+
+import (
+	"fmt"
+
+	"git.kor-elf.net/kor-elf-shield/blocklist"
+	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
+)
+
+/**
+ * An example of how to get a list of IP addresses from a service https://greensnow.co/
+ */
+
+func main() {
+	url := "https://blocklist.greensnow.co/greensnow.txt"
+	extract := parser.NewDefaultTextExtract(0, " ")
+	pars, err := parser.NewText(extract)
+	if err != nil {
+		panic(err)
+	}
+	// limit 0 - no limit
+	limit := uint(0)
+	config := blocklist.NewConfig(limit)
+	ips, err := blocklist.Get(url, pars, config)
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(ips)
+}

examples/honeypot.go

@@ -10,7 +10,7 @@ import (
 )
 
 /**
- * An example of how to get a list of bad IP addresses from the service https://www.projecthoneypot.org/list_of_ips.php
+ * An example of how to get a list of IP addresses from a service https://www.projecthoneypot.org/list_of_ips.php
  */
 
 type rssItem struct {

examples/spamhaus.go

@@ -9,7 +9,7 @@ import (
 )
 
 /**
- * An example of how to get a list of bad IP addresses from the service https://www.spamhaus.org/blocklists/do-not-route-or-peer/
+ * An example of how to get a list of IP addresses from a service https://www.spamhaus.org/blocklists/do-not-route-or-peer/
  */
 
 type lineJson struct {

examples/stopforumspam.go

@@ -0,0 +1,31 @@
+package main
+
+import (
+	"fmt"
+
+	"git.kor-elf.net/kor-elf-shield/blocklist"
+	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
+)
+
+/**
+ * An example of how to get a list of IP addresses from a service https://www.stopforumspam.com/downloads
+ */
+
+func main() {
+	url := "https://www.stopforumspam.com/downloads/listed_ip_1.zip"
+	//url := "https://www.stopforumspam.com/downloads/listed_ip_1_ipv6.zip"
+	extract := parser.NewDefaultTextExtract(0, " ")
+	pars, err := parser.NewText(extract)
+	if err != nil {
+		panic(err)
+	}
+	// limit 0 - no limit
+	limit := uint(0)
+	config := blocklist.NewConfig(limit)
+	configZip := blocklist.NewConfigZip(config)
+	ips, err := blocklist.GetZip(url, pars, configZip)
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(ips)
+}

examples/tor.go

@@ -0,0 +1,29 @@
+package main
+
+import (
+	"fmt"
+
+	"git.kor-elf.net/kor-elf-shield/blocklist"
+	"git.kor-elf.net/kor-elf-shield/blocklist/parser"
+)
+
+/**
+ * An example of how to get a list of IP addresses from a service https://check.torproject.org/torbulkexitlist
+ */
+
+func main() {
+	url := "https://check.torproject.org/torbulkexitlist"
+	extract := parser.NewDefaultTextExtract(0, " ")
+	pars, err := parser.NewText(extract)
+	if err != nil {
+		panic(err)
+	}
+	// limit 0 - no limit
+	limit := uint(0)
+	config := blocklist.NewConfig(limit)
+	ips, err := blocklist.Get(url, pars, config)
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(ips)
+}