Merge pull request #68 from KingAkeem/goBot

Added Go version of getweblinks getLinks function

modules/go_modules/getLinks.go

@@ -0,0 +1,81 @@
+package main
+
+import "C"
+
+import (
+	"fmt"
+	"golang.org/x/net/html"
+	"log"
+	"net/http"
+	"net/url"
+	"regexp"
+	"sync"
+	"time"
+)
+
+func validOnionUrl(url string) bool {
+	pattern := `^https?:\/\/(www\.)?([a-z,A-Z,0-9]*)\.onion/(.*)`
+	re := regexp.MustCompile(pattern)
+	return re.Match([]byte(url))
+}
+
+func asyncHead(client *http.Client, link string) {
+	defer wg.Done()
+	resp, err := client.Get(link)
+	if err == nil && resp.StatusCode < 400 {
+		fmt.Printf("%v is reachable.\n", link)
+	} else {
+		fmt.Printf("%v is not reachable.\n", link)
+	}
+}
+
+var wg sync.WaitGroup
+
+//export GetLinks
+func GetLinks(searchUrl string, addr string, port string, timeout int) {
+	var torProxy string = "socks5://" + addr + ":" + port
+	torProxyUrl, err := url.Parse(torProxy)
+	if err != nil {
+		log.Fatal("Error parsing URL: ", err)
+	}
+	torTransport := &http.Transport{Proxy: http.ProxyURL(torProxyUrl)}
+	client := &http.Client{Transport: torTransport, Timeout: time.Second * time.Duration(timeout)}
+	resp, err := client.Get(searchUrl)
+	if err != nil {
+		log.Fatal("Error with GET request", err)
+	}
+	defer resp.Body.Close()
+	bytes := resp.Body
+	tokenizer := html.NewTokenizer(bytes)
+	found_urls := make([]string, 0)
+	for not_end := true; not_end; {
+		currentTokenType := tokenizer.Next()
+		switch {
+		case currentTokenType == html.ErrorToken:
+			not_end = false
+		case currentTokenType == html.StartTagToken:
+			token := tokenizer.Token()
+			if token.Data == "a" {
+				attributes := token.Attr
+				for i := 0; i < len(attributes); i++ {
+					if attributes[i].Key == "href" && validOnionUrl(attributes[i].Val) {
+						found_urls = append(found_urls, attributes[i].Val)
+					}
+				}
+			}
+		}
+	}
+	fmt.Printf("Number of URLs found: %v\n", len(found_urls))
+	for _, link := range found_urls {
+		_, err := url.ParseRequestURI(link)
+		if err != nil {
+			continue
+		}
+		wg.Add(1)
+		go asyncHead(client, link)
+	}
+	wg.Wait()
+}
+
+func main() {
+}

modules/go_modules/getLinks.py

@@ -0,0 +1,18 @@
+from ctypes import cdll, c_char_p, c_longlong, c_int, Structure
+import sys
+
+goBot = cdll.LoadLibrary("./goBot.so")
+
+
+class GoString(Structure):
+    _fields_ = [("p", c_char_p), ("n", c_longlong)]
+
+
+goBot.GetLinks.argtypes = [GoString, GoString, GoString, c_int]
+url = sys.argv[1].encode('utf-8')
+addr = b"127.0.0.1"
+port = b"9050"
+goBot.GetLinks(GoString(url, len(url)),
+               GoString(addr, len(addr)),
+               GoString(port, len(port)),
+               15)

modules/go_modules/goBot.h

@@ -0,0 +1,60 @@
+/* Created by "go tool cgo" - DO NOT EDIT. */
+
+/* package command-line-arguments */
+
+/* Start of preamble from import "C" comments.  */
+
+
+
+
+/* End of preamble from import "C" comments.  */
+
+
+/* Start of boilerplate cgo prologue.  */
+#line 1 "cgo-gcc-export-header-prolog"
+
+#ifndef GO_CGO_PROLOGUE_H
+#define GO_CGO_PROLOGUE_H
+
+typedef signed char GoInt8;
+typedef unsigned char GoUint8;
+typedef short GoInt16;
+typedef unsigned short GoUint16;
+typedef int GoInt32;
+typedef unsigned int GoUint32;
+typedef long long GoInt64;
+typedef unsigned long long GoUint64;
+typedef GoInt64 GoInt;
+typedef GoUint64 GoUint;
+typedef __SIZE_TYPE__ GoUintptr;
+typedef float GoFloat32;
+typedef double GoFloat64;
+typedef float _Complex GoComplex64;
+typedef double _Complex GoComplex128;
+
+/*
+  static assertion to make sure the file is being used on architecture
+  at least with matching size of GoInt.
+*/
+typedef char _check_for_64_bit_pointer_matching_GoInt[sizeof(void*)==64/8 ? 1:-1];
+
+typedef struct { const char *p; GoInt n; } GoString;
+typedef void *GoMap;
+typedef void *GoChan;
+typedef struct { void *t; void *v; } GoInterface;
+typedef struct { void *data; GoInt len; GoInt cap; } GoSlice;
+
+#endif
+
+/* End of boilerplate cgo prologue.  */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+extern void GetLinks(GoString p0, GoString p1, GoString p2, GoInt p3);
+
+#ifdef __cplusplus
+}
+#endif