-
Notifications
You must be signed in to change notification settings - Fork 135
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
b089a32
commit 126eb85
Showing
5 changed files
with
72 additions
and
23 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,62 @@ | ||
import cv2 | ||
import pytesseract | ||
import iocextract | ||
import requests | ||
import datetime | ||
import os | ||
import numpy as np | ||
|
||
from threatingestor.sources import Source | ||
import threatingestor.artifacts | ||
|
||
class Plugin(Source): | ||
""" | ||
Image text extraction using Google's OCR Tesseract engine and computer vision | ||
""" | ||
|
||
def __init__(self, name, img=""): | ||
self.name = name | ||
self.img = img | ||
|
||
if "http" in img: | ||
with open("/tmp/data.png", "wb") as i: | ||
i.write(requests.get(str(self.img)).content) | ||
|
||
def run(self, saved_state): | ||
saved_state = datetime.datetime.utcnow().isoformat()[:-7] + "Z" | ||
|
||
if os.path.exists("/tmp/data.png"): | ||
data = cv2.imread("/tmp/data.png") | ||
else: | ||
data = cv2.imread(self.img) | ||
|
||
try: | ||
# Helps with preprocessing by converting to a grayscale | ||
grayscale_img = cv2.cvtColor(data, cv2.COLOR_BGR2GRAY) | ||
|
||
# Creates a binary image by using the proper threshold from cv | ||
binary_img = cv2.threshold(grayscale_img, 130, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1] | ||
|
||
# Inverts the binary | ||
invert_img = cv2.bitwise_not(binary_img) | ||
|
||
# Helps with cleanup | ||
noise_reduction = np.ones((2,2), np.uint8) | ||
process_iter = cv2.erode(invert_img, noise_reduction, iterations = 1) | ||
process_iter = cv2.dilate(process_iter, noise_reduction, iterations = 1) | ||
|
||
# Converts image data to a string | ||
img_data = pytesseract.image_to_string(process_iter) | ||
|
||
artifact_list = [] | ||
|
||
title = "Image: {0}".format(self.img) | ||
description = 'URL: {u}\nTask autogenerated by ThreatIngestor from source: {s}' | ||
description = description.format(s=self.name, u=list(iocextract.extract_urls(img_data))) | ||
artifact = threatingestor.artifacts.Task(title, self.name, reference_link=str(list(iocextract.extract_urls(img_data))), reference_text=description) | ||
artifact_list.append(artifact) | ||
|
||
except cv2.error: | ||
raise FileNotFoundError | ||
|
||
return saved_state, artifact_list |