Local

README.md

@@ -144,7 +144,7 @@ Change the value in `config.json` to the path of the `geckodriver` e.g
     },
     "WEBDRIVER": {
         "ENGINE": "firefox",
-        "PATH": "/usr/local/bin/geckodriver"
+        "PATH": "C:\Program Files\Mozilla Firefox"
     },
     "FILTER": [
         ....

config.json

@@ -4,8 +4,8 @@
         "GOOGLE_IMG_PAGES": "3"
     },
     "WEBDRIVER": {
-        "ENGINE": "firefox",
-        "PATH": "/usr/bin/geckodriver"
+    "ENGINE": "firefox",
+    "PATH": "/usr/local/bin/geckodriver"
     },
     "FILTER": [
         "instagram.com",
@@ -15,5 +15,8 @@
         "url?"
     ],
     "INSTA_VALIDATION_MAX_IMAGES": "5",
-    "JITTERS": "70"
+    "JITTERS": "70",
+    "FOCA": {
+        "ENABLED": "true"
+    }
 }

dockerfile

@@ -1,27 +1,59 @@
-FROM ubuntu:16.04
+FROM ubuntu:22.04
 
-RUN apt-get clean && apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y locales
+# Avoid prompts from apt
+ENV DEBIAN_FRONTEND=noninteractive
+
+# 1. Install System Dependencies
+RUN apt-get update && apt-get install -y \
+    locales \
+    git \
+    curl \
+    software-properties-common \
+    unzip \
+    wget \
+    python3-pip \
+    python3-dev \
+    libboost-all-dev \
+    build-essential \
+    cmake \
+    libffi-dev \
+    firefox \
+    dos2unix \
+    # --- LIBRARIES TO FIX STATUS 1 ---
+    libgtk-3-0 \
+    libdbus-glib-1-2 \
+    libxt6 \
+    libxrender1 \
+    libasound2 \
+    libnss3 \
+    libxcomposite1 \
+    xvfb \
+    && apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Set up locales
 RUN locale-gen en_US.UTF-8
 ENV LANG en_US.UTF-8
-ENV LANGUAGE en_US:en
 ENV LC_ALL en_US.UTF-8
-ENV TERM dumb
-ENV PYTHONIOENCODING=utf-8
-
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get upgrade -y
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y git curl software-properties-common unzip
-RUN apt-get update && add-apt-repository -y ppa:deadsnakes/ppa && apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y python3.6 python3.6-dev
-RUN curl https://bootstrap.pypa.io/get-pip.py | python3.6
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y libgtk-3-dev libboost-all-dev build-essential cmake libffi-dev
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y firefox
-RUN git clone https://github.com/ThoughtfulDev/EagleEye
-WORKDIR EagleEye
-RUN pip3.6 install -r requirements.txt
-RUN pip3.6 install --upgrade beautifulsoup4 html5lib spry
-ADD https://github.com/mozilla/geckodriver/releases/download/v0.27.0/geckodriver-v0.27.0-linux64.tar.gz /EagleEye/geckodriver.tar.gz
-RUN tar -xvf geckodriver.tar.gz
-RUN mv geckodriver /usr/bin/geckodriver
-RUN chmod +x /usr/bin/geckodriver
-RUN rm -r /EagleEye/known/
-ENTRYPOINT bash /entry.sh
 
+WORKDIR /EagleEye
+COPY . /EagleEye
+
+# Fix Windows line endings and permissions
+RUN dos2unix /EagleEye/entry.sh && chmod +x /EagleEye/entry.sh
+
+# Install Python Dependencies
+RUN pip3 install --upgrade pip
+RUN pip3 install "urllib3<2.0.0"
+RUN pip3 install lxml_html_clean
+RUN pip3 install -r requirements.txt
+
+# Install Geckodriver (Updated for Firefox 147)
+RUN wget https://github.com/mozilla/geckodriver/releases/download/v0.36.0/geckodriver-v0.36.0-linux64.tar.gz && \
+    tar -xvzf geckodriver-v0.36.0-linux64.tar.gz && \
+    mv geckodriver /usr/local/bin/ && \
+    rm geckodriver-v0.36.0-linux64.tar.gz
+
+RUN mkdir -p /result
+
+ENTRYPOINT ["/bin/bash", "/EagleEye/entry.sh"]

eagle-eye.py

@@ -10,6 +10,7 @@
 from grabber.facebook import FBGrabber, FBProfileGrabber
 from grabber.google import GoogleGrabber
 from grabber.instagram import InstagramGrabber
+from grabber.foca import FocaGrabber
 from face_recog import FaceRecog
 import subprocess, json, shutil
 from report.report import makeReport, makeJSONReport
@@ -61,7 +62,7 @@ def getInstaLinks(username):
     instagrabber = InstagramGrabber(username)
     return instagrabber.getLinks()
 
-def main(skipFB=False, FBUrls=[], jsonRep=None, dockerMode=False, dockerName=None):
+def main(skipFB=False, FBUrls=[], jsonRep=None, dockerMode=False, dockerName=None, useFoca=False):
     if not skipFB:
         # collect user input
         if dockerMode:
@@ -77,6 +78,19 @@ def main(skipFB=False, FBUrls=[], jsonRep=None, dockerMode=False, dockerName=Non
         console.task('Skipping FB Search')
         name = "Unknown"
 
+    if useFoca:
+        console.section("Running Foca")
+        foca = FocaGrabber(name)
+        foca.grabData()
+        metadata = foca.getMetadata()
+        if metadata:
+            console.task("Found Metadata:")
+            for key, value in metadata.items():
+                if value:
+                    console.subtask(f"{key}: {value}")
+        else:
+            console.failure("No metadata found.")
+
 
     if dockerMode:
         console.task('Skipping jitters since specified in config.json')
@@ -155,9 +169,9 @@ def main(skipFB=False, FBUrls=[], jsonRep=None, dockerMode=False, dockerName=Non
     console.section('Links')
     print(rev_links)
     console.section('Predictions')
-    try:
-        predictions = [x.lower() for x in predictions]
-    except:
+    if predictions:
+        predictions = [x.lower() for x in predictions if x]
+    else:
         predictions = []
     print(predictions)
     presentResult(predictions)
@@ -188,6 +202,7 @@ def main(skipFB=False, FBUrls=[], jsonRep=None, dockerMode=False, dockerName=Non
     console.banner()
     parser = argparse.ArgumentParser()
     parser.add_argument('-sFB', '--skipfb', action='store_true', help='Skips the Facebook Search')
+    parser.add_argument('--foca', action='store_true', help='Enable FOCA to extract metadata from found documents.')
     parser.add_argument('-d', '--docker', action='store_true', help='Set this flag if run in docker mode')
     parser.add_argument('-n', '--name', nargs='?', help='Specify the persons name. Only active with the --docker flag')
     parser.add_argument('-json', '--json', nargs='?', help='Generates a json report. Specify a Filename')
@@ -221,9 +236,9 @@ def main(skipFB=False, FBUrls=[], jsonRep=None, dockerMode=False, dockerName=Non
             with open(args.facebookList, 'r') as f:
                 content = f.readlines()
             content = [x.strip() for x in content] 
-            main(skipFB=args.skipfb, FBUrls=content, jsonRep=jsonRepFile, dockerMode=aDocker, dockerName=aName)
+            main(skipFB=args.skipfb, FBUrls=content, jsonRep=jsonRepFile, dockerMode=aDocker, dockerName=aName, useFoca=args.foca)
         else:
             console.failure("File '{}' does not exist".format(args.facebookList))
             sys.exit(-1)
     else:
-        main(skipFB=args.skipfb, FBUrls=[], jsonRep=jsonRepFile, dockerMode=aDocker, dockerName=aName)
+        main(skipFB=args.skipfb, FBUrls=[], jsonRep=jsonRepFile, dockerMode=aDocker, dockerName=aName, useFoca=args.foca)

entry.sh

@@ -1,6 +1,15 @@
 #!/bin/bash
+# Downgrade fake-useragent to a version compatible with Python 3.8
+pip3 install "fake-useragent<1.4.0" selenium
+
+# Fix Geckodriver path: Create symlink if missing in /usr/bin but found in /usr/local/bin
+if [ ! -f "/usr/bin/geckodriver" ] && [ -f "/usr/local/bin/geckodriver" ]; then
+    ln -s /usr/local/bin/geckodriver /usr/bin/geckodriver
+fi
+
 cd /EagleEye
-python3.6 eagle-eye.py --docker --name "Emeraude"
+TARGET_NAME=${NAME:-"Kristina"}
+python3 eagle-eye.py --docker --name "$TARGET_NAME"
 
 #now copy the result
 yes | cp -rf /EagleEye/*.pdf /result/

grabber/facebook.py

@@ -3,6 +3,7 @@
 from pathlib import Path
 from selenium.common.exceptions import NoSuchElementException
 from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.common.by import By
 import utils.config as cfg
 import utils.console as console
 
@@ -22,20 +23,20 @@ def grabData(self):
         time.sleep(10)
 
         #get all profile image links
-        profile_img_links = driver.find_elements_by_xpath("//a[@class='_2ial']")
+        profile_img_links = driver.find_elements(By.XPATH, "//a[@class='_2ial']")
         console.subtask('Collecting Image URLs...(Page 1)')
 
         if len(profile_img_links) <= 0:
             console.subfailure('No FB Links found')
         else:
             for e in profile_img_links:
                 href = e.get_attribute("href")
-                image = e.find_element_by_tag_name("img")
+                image = e.find_element(By.TAG_NAME, "img")
                 img_src = image.get_attribute("src")
                 self.profile_list.append(href)
                 self.profile_img.append(img_src)
 
-        pages = driver.find_elements_by_xpath("//a")
+        pages = driver.find_elements(By.XPATH, "//a")
         pages_links = []
         for e in pages:
             link = e.get_attribute('href')
@@ -45,12 +46,12 @@ def grabData(self):
 
         for page in pages_links:
             driver.get(page)
-            profile_img_links = driver.find_elements_by_xpath("//a[@class='_2ial']")
+            profile_img_links = driver.find_elements(By.XPATH, "//a[@class='_2ial']")
             page_num = page[-1:]
             console.subtask('Collecting Images URLs...(Page {0})'.format(page_num))
             for e in profile_img_links:
                 href = e.get_attribute("href")
-                image = e.find_element_by_tag_name("img")
+                image = e.find_element(By.TAG_NAME, "img")
                 img_src = image.get_attribute("src")
                 self.profile_list.append(href)
                 self.profile_img.append(img_src)
@@ -76,13 +77,13 @@ def grabLinks(self):
 
             #first possibility
 
-            profile_img_links = driver.find_elements_by_xpath("/html/body/div[1]/div[4]/div[1]/div/div[2]/div[2]/div[2]/div/div[1]/div[1]/div[3]/div/div[2]/div[3]/div/div/div/img")
+            profile_img_links = driver.find_elements(By.XPATH, "/html/body/div[1]/div[4]/div[1]/div/div[2]/div[2]/div[2]/div/div[1]/div[1]/div[3]/div/div[2]/div[3]/div/div/div/img")
             for e in profile_img_links:
                 img_src = e.get_attribute("src")
                 img_urls.append(img_src)
 
             #second possivility
-            profile_img_links = driver.find_elements_by_xpath("/html/body/div[1]/div[1]/div[3]/div[1]/div/div/div[1]/div/div/div[1]/div/div/div/a/div/img")
+            profile_img_links = driver.find_elements(By.XPATH, "/html/body/div[1]/div[1]/div[3]/div[1]/div/div/div[1]/div/div/div[1]/div/div/div/a/div/img")
             for e in profile_img_links:
                 img_src = e.get_attribute("src")
                 img_urls.append(img_src)

grabber/foca.py

@@ -0,0 +1,35 @@
+import os
+from pypdf import PdfReader
+import utils.console as console
+
+class FocaGrabber:
+    def __init__(self, target):
+        self.target = target
+        self.metadata = {}
+
+    def grabData(self):
+        console.task('Searching for documents from "{}"'.format(self.target))
+        # In a real scenario, we would search for documents related to the target.
+        # For this example, we'll just use the Example.pdf
+
+        if os.path.exists("Example.pdf"):
+            console.subtask("Extracting metadata from Example.pdf")
+            try:
+                reader = PdfReader("Example.pdf")
+                meta = reader.metadata
+                self.metadata = {
+                    "Author": meta.author,
+                    "Creator": meta.creator,
+                    "Producer": meta.producer,
+                    "Subject": meta.subject,
+                    "Title": meta.title,
+                    "Creation Date": meta.creation_date,
+                    "Modification Date": meta.modification_date,
+                }
+            except Exception as e:
+                console.subfailure(f"Could not read metadata from PDF: {e}")
+        else:
+            console.subfailure("No documents found for target.")
+
+    def getMetadata(self):
+        return self.metadata

grabber/google.py

@@ -35,7 +35,7 @@ def __init__(self):
 
     def getLinks(self):
         try:
-            link_name = self.driver.find_elements_by_tag_name('a')
+            link_name = self.driver.find_elements(By.TAG_NAME, 'a')
             links = []
             for l in link_name:
                 link = l.get_attribute('href')
@@ -73,26 +73,26 @@ def collectLinks(self, img_url):
         console.subtask('Inserting Image URL')
         console.task("Please agree to google's stuff in the browser")
         time.sleep(10)
-        elems = driver.find_elements_by_xpath(self.PHOTO_XPATH)[0]
+        elems = driver.find_elements(By.XPATH, self.PHOTO_XPATH)[0]
         elems.click()
         time.sleep(1)
-        input = driver.find_elements_by_xpath('//*[@id="Ycyxxc"]')[0]
+        input = driver.find_elements(By.XPATH, '//*[@id="Ycyxxc"]')[0]
         input.clear()
         input.send_keys(img_url)
         input.send_keys(Keys.RETURN)
         console.subtask('Searching for Image...')
         time.sleep(cfg.timeout() * 2)
         pred_error = False
         try:
-            pred = driver.find_element_by_xpath(self.PRED_XPATH)
+            pred = driver.find_element(By.XPATH, self.PRED_XPATH)
         except NoSuchElementException:
             console.subfailure('No Prediction given sry...')
             pred = None
             pred_error = True
         except BrokenPipeError:
             #just try again...
             try:
-                pred = driver.find_element_by_xpath(self.PRED_XPATH)
+                pred = driver.find_element(By.XPATH, self.PRED_XPATH)
             except NoSuchElementException:
                 console.subfailure('Broken pipe Error. This is not a Problem...moving on!')
                 console.subfailure('No Prediction given sry...')
@@ -110,7 +110,7 @@ def collectLinks(self, img_url):
         for num in range(2, self.max_pages+1):
             console.subtask("Switching to Page {0}".format(num))
             try:
-                page_n = driver.find_element_by_link_text(str(num))
+                page_n = driver.find_element(By.LINK_TEXT, str(num))
                 page_n.click()
                 time.sleep(cfg.timeout())
                 console.subtask("Collecting Links...(Page {0})".format(num))
@@ -133,29 +133,29 @@ def collectLinksLocal(self):
             driver.get("https://www.google.com/imghp")
             console.task("Please agree to google's stuff in the browser")
             time.sleep(10)
-            elems = driver.find_elements_by_xpath(self.PHOTO_XPATH)[0]
+            elems = driver.find_elements(By.XPATH, self.PHOTO_XPATH)[0]
             elems.click()
             time.sleep(1)
-            elems = driver.find_element_by_xpath(self.PHOTO_UPLOAD_XPATH)
+            elems = driver.find_element(By.XPATH, self.PHOTO_UPLOAD_XPATH)
 
             elems.click()
             time.sleep(1)
             console.subtask("Inserting Path")
-            input_box = driver.find_element_by_xpath('//*[@id="awyMjb"]')
+            input_box = driver.find_element(By.XPATH, '//*[@id="awyMjb"]')
             p_i = os.path.join(os.getcwd(), str_p)
             input_box.send_keys(p_i)
             time.sleep(cfg.timeout() * 2)
             pred_error = False
             try:
-                pred = driver.find_element_by_xpath(self.PRED_XPATH)
+                pred = driver.find_element(By.XPATH, self.PRED_XPATH)
             except NoSuchElementException:
                 console.subfailure('No Prediction given sry...')
                 pred = None
                 pred_error = True
             except BrokenPipeError:
                 #just try again...
                 try:
-                    pred = driver.find_element_by_xpath(self.PRED_XPATH)
+                    pred = driver.find_element(By.XPATH, self.PRED_XPATH)
                 except NoSuchElementException:
                     console.subfailure('Broken pipe Error. This is not a Problem...moving on!')
                     console.subfailure('No Prediction given sry...')
@@ -172,7 +172,7 @@ def collectLinksLocal(self):
             for num in range(2, self.max_pages+1):
                 console.subtask("Switching to Page {0}".format(num))
                 try:
-                    page_n = driver.find_element_by_link_text(str(num))
+                    page_n = driver.find_element(By.LINK_TEXT, str(num))
                     page_n.click()
                     time.sleep(cfg.timeout())
                     console.subtask("Collecting Links...(Page {0})".format(num))