{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "import csv\n",
    "from getpass import getpass\n",
    "from time import sleep\n",
    "from selenium.webdriver.common.keys import Keys\n",
    "from selenium.common.exceptions import NoSuchElementException\n",
    "from msedge.selenium_tools import Edge, EdgeOptions "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_tweet_data(card):\n",
    "    \"\"\"Extract data from tweet card\"\"\"\n",
    "    username = card.find_element_by_xpath('.//span').text\n",
    "    try:\n",
    "        handle = card.find_element_by_xpath('.//span[contains(text(), \"@\")]').text\n",
    "    except NoSuchElementException:\n",
    "        return\n",
    "    \n",
    "    try:\n",
    "        postdate = card.find_element_by_xpath('.//time').get_attribute('datetime')\n",
    "    except NoSuchElementException:\n",
    "        return\n",
    "    \n",
    "    comment = card.find_element_by_xpath('.//div[2]/div[2]/div[1]').text\n",
    "    responding = card.find_element_by_xpath('.//div[2]/div[2]/div[2]').text\n",
    "    text = comment + responding\n",
    "    reply_cnt = card.find_element_by_xpath('.//div[@data-testid=\"reply\"]').text\n",
    "    retweet_cnt = card.find_element_by_xpath('.//div[@data-testid=\"retweet\"]').text\n",
    "    like_cnt = card.find_element_by_xpath('.//div[@data-testid=\"like\"]').text\n",
    "\n",
    "    \n",
    "    tweet = (username, handle, postdate, text, reply_cnt, retweet_cnt, like_cnt)\n",
    "    return tweet  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "search_term = input('search term: ')\n",
    "\n",
    "# create instance of web driver\n",
    "options = EdgeOptions()\n",
    "options.use_chromium = True\n",
    "driver = Edge(options=options)\n",
    "\n",
    "# navigate to login screen\n",
    "driver.get('https://twitter.com/search')\n",
    "driver.maximize_window()\n",
    "sleep(5)\n",
    "\n",
    "# find search input and search for term\n",
    "search_input = driver.find_element_by_xpath('//input[@aria-label=\"Search query\"]')\n",
    "search_input.send_keys(search_term)\n",
    "search_input.send_keys(Keys.RETURN)\n",
    "sleep(1)\n",
    "\n",
    "# navigate to historical 'latest' tab\n",
    "driver.find_element_by_link_text('Latest').click()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get all tweets on the page\n",
    "data = []\n",
    "tweet_ids = set()\n",
    "last_position = driver.execute_script(\"return window.pageYOffset;\")\n",
    "scrolling = True\n",
    "\n",
    "while scrolling:\n",
    "    page_cards = driver.find_elements_by_xpath('//article[@data-testid=\"tweet\"]')\n",
    "    for card in page_cards[-15:]:\n",
    "        tweet = get_tweet_data(card)\n",
    "        if tweet:\n",
    "            tweet_id = ''.join(tweet)\n",
    "            if tweet_id not in tweet_ids:\n",
    "                tweet_ids.add(tweet_id)\n",
    "                data.append(tweet)\n",
    "            \n",
    "    scroll_attempt = 0\n",
    "    while True:\n",
    "        # check scroll position\n",
    "        driver.execute_script('window.scrollTo(0, document.body.scrollHeight);')\n",
    "        sleep(2)\n",
    "        curr_position = driver.execute_script(\"return window.pageYOffset;\")\n",
    "        if last_position == curr_position:\n",
    "            scroll_attempt += 1\n",
    "            \n",
    "            # end of scroll region\n",
    "            if scroll_attempt >= 3:\n",
    "                scrolling = False\n",
    "                break\n",
    "            else:\n",
    "                sleep(2) # attempt another scroll\n",
    "        else:\n",
    "            last_position = curr_position\n",
    "            break\n",
    "\n",
    "# close the web driver\n",
    "driver.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Saving the tweet data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('turkcell_tweets.csv', 'w', newline='', encoding='utf-8') as f:\n",
    "    header = ['UserName', 'Handle', 'Timestamp', 'Text', 'Comments', 'Likes', 'Retweets']\n",
    "    writer = csv.writer(f)\n",
    "    writer.writerow(header)\n",
    "    writer.writerows(data)"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "306b4709344c791e982a258cf5494139869959872aa39c2c4102a54cca0d2138"
  },
  "kernelspec": {
   "display_name": "Python 3.7.0 64-bit",
   "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": "3.7.0"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}