Filter to IG,FB,YT and TT. Down to 1166 links

Author: neon-ninja

googlesearch.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 22,
    "id": "e36a7e0b",
    "metadata": {},
    "outputs": [],
@@ -21,7 +21,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 38,
+   "id": "c285f9c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((1287, 5), (1164, 5))"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv(\"supplements.csv\")\n",
+    "df.shape,df[df.source.isin([\"Instagram\", \"TikTok\", \"YouTube\", \"Facebook\"])].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
    "id": "b542f394",
    "metadata": {},
    "outputs": [],
@@ -33,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 17,
    "id": "889b794c",
    "metadata": {},
    "outputs": [],
@@ -43,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 18,
    "id": "20312a24",
    "metadata": {},
    "outputs": [],
@@ -56,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 19,
    "id": "40cf9486",
    "metadata": {},
    "outputs": [],

run_googlesearch.py

@@ -180,6 +180,7 @@ def main():
         # Save results
         print("\nSaving results...")
         df.sort_values(by="link", inplace=True)
+        df = df[df.source.isin(["Instagram", "TikTok", "YouTube", "Facebook"])]
         df.to_csv("supplements.csv", index=False)
         df.link.drop_duplicates().to_csv("supplements_links.txt", index=False, header=False)
         print("Saved to: supplements.csv and supplements_links.txt")