Working fetch search, refactoring DB towards source search

A_Development.ipynb

@@ -2,15 +2,80 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import newspaper\n",
-    "url = \"http://www.missingkids.org/poster/NCMC/2045193/1\"\n",
-    "#url = \"https://www.missingkids.org/new-poster/NCMC/2045193/1\"\n",
+    "# !pip install git+https://github.com/tasos-py/Search-Engines-Scraper.git\n",
+    "import search_engines\n",
     "\n",
-    "art = newspaper.article(url)"
+    "engine = search_engines.Bing()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Searching Bing                                                                 \n",
+      "                                                                               \r"
+     ]
+    }
+   ],
+   "source": [
+    "results = engine.search('news: \"child abuse\"', pages=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "engine = search_engines.search_engines_dict[\"brave\"]()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Searching Brave                                                                \n",
+      "                                                                               \r"
+     ]
+    }
+   ],
+   "source": [
+    "query = 'news: child abuse'\n",
+    "r = engine.search(query, pages=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'_results': []}"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r.__dict__"
    ]
   },
   {
@@ -18,8 +83,57 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "newspaper.exceptions.ArticleBinaryDataException"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "art.__dict__"
+    "import newspaper\n",
+    "newspaper.ArticleBinaryDataException"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "'''\n",
+    "import newspaper\n",
+    "\n",
+    "url = 'https://www.missingkids.org/poster/USVA/VA25-0820/1'\n",
+    "art_1 = newspaper.article(url)\n",
+    "url = 'https://www.missingkids.org/poster/NCMC/2045193/1'\n",
+    "art_2 = newspaper.article(url)\n",
+    "'''"
    ]
   },
   {
@@ -44,15 +158,8 @@
     "l = client.list()\n",
     "list_models = [m.get(\"model\") for m in l.model_dump().get(\"models\")]\n",
     "\n",
-    "list_models"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "print(list_models)\n",
+    "\n",
     "for m in list_models:\n",
     "    context_key = [ k for k in client.show(m).model_dump().get(\"modelinfo\").keys() if \"context_length\" in k]\n",
     "    if (len(context_key) != 1):\n",