From 43b1bb837f2a9f6726ce469e516c06a8449a8603 Mon Sep 17 00:00:00 2001
From: AccentuSoft <socials@accentusoft.com>
Date: Mon, 4 Jul 2022 15:29:42 +0300
Subject: [PATCH] Improve extraction of website text

---
 Core/Resolutions/Core/GetWebsiteBody.py | 45 ----------------
 Core/Resolutions/Core/GetWebsiteText.py | 72 +++++++++++++++++++++++++
 2 files changed, 72 insertions(+), 45 deletions(-)
 delete mode 100644 Core/Resolutions/Core/GetWebsiteBody.py
 create mode 100644 Core/Resolutions/Core/GetWebsiteText.py

diff --git a/Core/Resolutions/Core/GetWebsiteBody.py b/Core/Resolutions/Core/GetWebsiteBody.py
deleted file mode 100644
index 0024bcb..0000000
--- a/Core/Resolutions/Core/GetWebsiteBody.py
+++ /dev/null
@@ -1,45 +0,0 @@
-#!/usr/bin/env python3
-
-
-class GetWebsiteBody:
-    # A string that is treated as the name of this resolution.
-    name = "Get Website Body"
-
-    category = "Website Information"
-
-    # A string that describes this resolution.
-    description = "Returns the contents of the body tag of the selected websites."
-
-    originTypes = {'Website'}
-
-    resultTypes = {'Phrase'}
-
-    parameters = {}
-
-    def resolution(self, entityJsonList, parameters):
-        import requests
-
-        headers = {
-            'User-Agent': 'user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
-        }
-
-        returnResults = []
-
-        for entity in entityJsonList:
-            uid = entity['uid']
-
-            primaryField = entity['URL']
-
-            if primaryField.startswith('http://') or primaryField.startswith('https://'):
-                url = primaryField
-            else:
-                url = 'http://' + primaryField
-
-            r = requests.get(url, headers=headers)
-            doc = r.text
-
-            returnResults.append([{'Phrase': 'Website Body: ' + primaryField,
-                                   'Notes': doc,
-                                   'Entity Type': 'Phrase'},
-                                  {uid: {'Resolution': 'Website Body', 'Notes': ''}}])
-        return returnResults
diff --git a/Core/Resolutions/Core/GetWebsiteText.py b/Core/Resolutions/Core/GetWebsiteText.py
new file mode 100644
index 0000000..ce503a6
--- /dev/null
+++ b/Core/Resolutions/Core/GetWebsiteText.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+
+class GetWebsiteText:
+    # A string that is treated as the name of this resolution.
+    name = "Get Website Text"
+
+    category = "Website Information"
+
+    # A string that describes this resolution.
+    description = "Returns the text content of the selected websites."
+
+    originTypes = {'Website'}
+
+    resultTypes = {'Phrase'}
+
+    parameters = {}
+
+    def resolution(self, entityJsonList, parameters):
+        from bs4 import BeautifulSoup
+        from bs4.element import Comment
+        from playwright.sync_api import sync_playwright, TimeoutError, Error
+        from urllib.parse import urlparse
+
+        returnResults = []
+
+        def tag_visible(element):
+            if element.parent.name in ['style', 'script', 'head', 'title', 'meta', '[document]']:
+                return False
+            if isinstance(element, Comment):
+                return False
+            return True
+
+        def text_from_html(body):
+            soup = BeautifulSoup(body, 'html.parser')
+            texts = soup.findAll(text=True)
+            visible_texts = filter(tag_visible, texts)
+            return u" ".join(t.strip() for t in visible_texts if t.strip() != '')
+
+        with sync_playwright() as p:
+            browser = p.chromium.launch()
+            context = browser.new_context(
+                viewport={'width': 1920, 'height': 1080},
+                user_agent='Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) '
+                           'Chrome/101.0.4951.64 Safari/537.36'
+            )
+            page = context.new_page()
+
+            for site in entityJsonList:
+                uid = site['uid']
+                url = site['URL']
+                parsedURL = urlparse(url)
+                if not all([parsedURL.scheme, parsedURL.netloc]):
+                    continue
+
+                # Try to load the page a few times, in case of timeouts.
+                # I don't think making parts of this async actually helps in this case.
+                for _ in range(3):
+                    try:
+                        page.goto(url, wait_until="networkidle", timeout=10000)
+                        textContent = text_from_html(page.content())
+                        returnResults.append([{'Phrase': 'Website Body of: ' + url,
+                                               'Notes': textContent,
+                                               'Entity Type': 'Phrase'},
+                                              {uid: {'Resolution': 'Website Body', 'Notes': ''}}])
+                        break
+                    except TimeoutError:
+                        pass
+                    except Error:
+                        break
+
+        return returnResults