Merge pull request #3 from pedromlsreis/dates

Get dates from a given chatfile.html
pedromlsreis · Jan 31, 2019 · 3a414c1 · 3a414c1
2 parents ba4cb9f + 2779a44
commit 3a414c1
Showing 1 changed file with 144 additions and 0 deletions.
diff --git a/scraping-messenger.ipynb b/scraping-messenger.ipynb
@@ -0,0 +1,144 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import csv\n",
+    "from bs4 import BeautifulSoup\n",
+    "import re\n",
+    "from datetime import datetime\n",
+    "import pandas as pd\n",
+    "\n",
+    "\n",
+    "# import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_dates(filename):\n",
+    "    #Facebook Messenger date format: Jun 8, 2013, 10:50 PM\n",
+    "    date_pattern = re.compile(r'[A-Z]{1}[a-z]{2}\\s\\d+[,]\\s\\d{4}[,]\\s\\d{1,2}[:]\\d{2}\\s[AM|PM]')\n",
+    "    with open(filename, mode='r', encoding='UTF-8', errors='ignore') as fp:\n",
+    "        soup = BeautifulSoup(fp, \"lxml\", from_encoding='utf-8')\n",
+    "        soup.find('head').decompose() #delete the <head>, useless for this project\n",
+    "        soup.find('div', id=\"bluebarRoot\").decompose() #delete the blue header\n",
+    "        dates = soup.find_all(text=date_pattern)\n",
+    "        csvfile = csv.writer(open(\"chatdata.csv\", \"w\", encoding='UTF-8'))\n",
+    "        csvfile.writerow([\"date\"])\n",
+    "        for date in dates:\n",
+    "            data = datetime.strptime(date,'%b %d, %Y, %I:%M %p')\n",
+    "            csvfile.writerow([data])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "get_dates(r\"\\Path\\to\\File\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2018-12-22 14:23:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2018-12-21 02:35:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2018-12-21 02:35:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2018-12-21 02:35:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2018-12-21 02:35:00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  date\n",
+       "0  2018-12-22 14:23:00\n",
+       "1  2018-12-21 02:35:00\n",
+       "2  2018-12-21 02:35:00\n",
+       "3  2018-12-21 02:35:00\n",
+       "4  2018-12-21 02:35:00"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('chatdata.csv')\n",
+    "df.head()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}