Added JSON Report(ThoughtfulDev#33), Fixed Age Detection

Author: ThoughtfulDev

Example_JSON.json

@@ -0,0 +1,15 @@
+{
+    "google_predictions": ["emeraude toubia instagram"], 
+    "instagram_names": ["emeraude"], 
+    "age": "27", 
+    "social_urls": [
+        "https://twitter.com/emeraudetoubia/status/957383692833390593?lang=de", 
+        "https://twitter.com/gio53613", 
+        "https://twitter.com/onlyoulon", 
+        "https://www.instagram.com/emeraude/?hl=de", 
+        "https://www.instagram.com/p/BO3IpgFlVTF/?hl=de", 
+        "https://www.pinterest.com.mx/pin/344595808982228575/", 
+        "https://www.pinterest.com/gogreengo06/gorgeous-emeraude-toubia/", 
+        "https://www.pinterest.com/syc_mary/e-m-e-r-a-u-d-e-toubia/"], 
+    "name": "Unknown"
+}

eagle-eye.py

@@ -15,7 +15,7 @@
 from grabber.instagram import InstagramGrabber
 from face_recog import FaceRecog
 import subprocess, json, shutil
-from report.report import makeReport
+from report.report import makeReport, makeJSONReport
 
 
 def presentResult(predictions):
@@ -43,14 +43,17 @@ def parseInstaUsername(links):
         a = l[8:]
         a = a.split('/')
         if len(a) >= 2:
-            usernames.append(a[1])
+            if len(a[1]) >= 4:
+                usernames.append(a[1])
         else:
             console.subfailure('Error parsing {0}'.format(l))
     return usernames
 
 
 def validateInstaUser(username, num_jitters):
     images = getInstaLinks(username)
+    if len(images) >= cfg.instaLimit():
+        images = images[:cfg.instaLimit()]
     r = FaceRecog(username, images, num_jitters=num_jitters)
     r.loadKnown(username)
     profile_links, _ = r.getValidLinksAndImg(username)
@@ -60,7 +63,7 @@ def getInstaLinks(username):
     instagrabber = InstagramGrabber(username)
     return instagrabber.getLinks()
 
-def main(skipFB=False, skipIR=False, skipY=False, FBUrls=[]):
+def main(skipFB=False, skipIR=False, skipY=False, FBUrls=[], jsonRep=None):
     if not skipFB:
         # collect user input
         console.prompt('Enter the persons name to find on FB: ')
@@ -147,6 +150,7 @@ def main(skipFB=False, skipIR=False, skipY=False, FBUrls=[]):
     raider_img_list = profile_imgs
     for v in validatedInstaNames:
         l = getInstaLinks(v)
+
         for li in l:
             raider_img_list.append(li)
 
@@ -185,16 +189,22 @@ def main(skipFB=False, skipIR=False, skipY=False, FBUrls=[]):
     if len(validatedInstaNames) > 0:
         for v in validatedInstaNames:
             l = getInstaLinks(v)
+            if len(l) >= cfg.instaLimit():
+                l = l[:cfg.instaLimit()]
             for li in l:
                 ageEstimator.collectAges(li)
         age = ageEstimator.finish()
     else:
         console.failure('No Instagram Images to upload...')
-        ageEstimator.finish()
+        #ageEstimator.finish()
         age = "Unknown"
 
-    console.section("Creating PDF Report")
-    makeReport(name, rev_links, predictions, validatedInstaNames, age)
+    if jsonRep:
+        console.section("Dumping JSON Report")
+        makeJSONReport(name, rev_links, predictions, validatedInstaNames, age, jsonRep)
+    else:
+        console.section("Creating PDF Report")
+        makeReport(name, rev_links, predictions, validatedInstaNames, age)
 
 
     p = os.path.join(tempfile.gettempdir(), 'imageraider')
@@ -212,24 +222,33 @@ def main(skipFB=False, skipIR=False, skipY=False, FBUrls=[]):
     parser.add_argument('-sFB', '--skipfb', action='store_true', help='Skips the Facebook Search')
     parser.add_argument('-sIR', '--skipir', action='store_true', help='Skips the ImageRaider Reverse Search')
     #parser.add_argument('-sY', '--skipyandex', action='store_true', help='Skips the Yandex Reverse Search')
+    parser.add_argument('-json', '--json', nargs='?', help='Generates a json report. Specify a Filename')
     parser.add_argument('-fbList', 
                         '--facebookList', 
                         nargs='?', 
                         help="A file which contains Links to Facebook Profiles. '--skipfb' options must be enabled to use this" )
     args = parser.parse_args()
 
+    if args.json:
+        jsonRepFile = args.json
+        if os.path.isfile(jsonRepFile):
+            console.failure("File '{}' already exists".format(jsonRepFile))
+            sys.exit(-1)
+    else:
+        jsonRepFile = None
+
     if args.facebookList and args.skipfb:
         if os.path.isfile(args.facebookList):
             with open(args.facebookList, 'r') as f:
                 content = f.readlines()
             content = [x.strip() for x in content] 
             #TODO: fix yandex
             #main(skipFB=args.skipfb, skipIR=args.skipir, skipY=args.skipyandex, FBUrls=content)
-            main(skipFB=args.skipfb, skipIR=args.skipir, skipY=None, FBUrls=content)
+            main(skipFB=args.skipfb, skipIR=args.skipir, skipY=None, FBUrls=content, jsonRep=jsonRepFile)
         else:
             console.failure("File '{}' does not exist".format(args.facebookList))
             sys.exit(-1)
     else:
         #TODO: fix yandex
         #main(skipFB=args.skipfb, skipIR=args.skipir, skipY=args.skipyandex, FBUrls=[])
-        main(skipFB=args.skipfb, skipIR=args.skipir, skipY=None, FBUrls=[])
+        main(skipFB=args.skipfb, skipIR=args.skipir, skipY=None, FBUrls=[], jsonRep=jsonRepFile)

face_recog.py

@@ -85,6 +85,9 @@ def getValidLinksAndImg(self, label):
         valid_img = []
         valid_indexes = self.constructIndexes(label)
         for index in valid_indexes:
-            valid_url.append(self.profile_list[index])
-            valid_img.append(self.profile_img[index])
+            try:
+                valid_url.append(self.profile_list[index])
+                valid_img.append(self.profile_img[index])
+            except:
+                pass
         return valid_url, valid_img

grabber/pictriev.py

@@ -19,9 +19,9 @@ def filterLink(link):
 
 class PictrievGrabber:
     def __init__(self):
-        console.section('Picture Age and Gender Detection')
+        console.section('Age Detection')
         console.task('Opening Webdriver')
-        self.driver = cfg.getWebDriver()
+        self.driver = None
         self.ages = []
         self.males = []
         self.females = []
@@ -38,6 +38,8 @@ def mean(self, arr):
 
 
     def collectAges(self, img_url):
+        if not self.driver:
+            self.driver = cfg.getWebDriver()
         console.task('New Image: {0}'.format(img_url.strip()[:90]))  
         driver = self.driver
         driver.get("http://www.pictriev.com/?lang=en")
@@ -50,11 +52,15 @@ def collectAges(self, img_url):
         console.subtask('Searching for Image...')
         time.sleep(cfg.timeout() * 3)
         try:
-            age = driver.find_elements_by_css_selector('#age-gauge > svg:nth-child(1) > text:nth-child(6) > tspan:nth-child(1)')[0].text
-            if int(age) > 0:
-                self.ages.append(int(age))
+            age = driver.find_elements_by_css_selector('#age-gauge > svg:nth-child(1) > text:nth-child(6) > tspan:nth-child(1)')
         except:
-            pass
+            age = driver.find_elements_by_css_selector('#age-gauge > svg:nth-child(1) > text:nth-child(6) > tspan:nth-child(1)')
+        if len(age) == 1:
+            age = age[0].text
+        else:
+            age = 0
+        self.ages.append(int(age))
+
 
     def finish(self):
         self.driver.close()

report/report.py

@@ -1,5 +1,6 @@
 from weasyprint import HTML
 import os
+import json
 
 def makeReport(name, links, preds, instnames, age):
     #sort
@@ -37,3 +38,20 @@ def makeReport(name, links, preds, instnames, age):
     doc.write_pdf('{0}_Report.pdf'.format(name))
     os.remove('tmp.html')
 
+def makeJSONReport(name, links, preds, instnames, age, fn):
+    data = {}
+    links = sorted(links)
+    preds = sorted(preds)
+    instnames = sorted(instnames)
+
+    name = name.strip()
+    name = name.replace('%20', '-')
+
+    data['name'] = name
+    data['age'] = str(age)
+    data['social_urls'] = links
+    data['google_predictions'] = preds
+    data['instagram_names'] = instnames
+    with open(fn, 'w') as o:
+        json.dump(data, o)
+