910 lines
58 KiB
Plaintext
910 lines
58 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"# Crawl Data Twitter > 1500 Tweets\n",
|
||
"The crawling process was done using Tweet-Harvest. Written by Helmi Satria on October 18th."
|
||
],
|
||
"metadata": {
|
||
"id": "xEWpayxURuUn"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {
|
||
"collapsed": true,
|
||
"id": "4UIL1x21P9rQ",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/"
|
||
},
|
||
"outputId": "ced4d1b2-e272-49fe-9fa2-1f75e9a59357"
|
||
},
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (2.0.3)\n",
|
||
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)\n",
|
||
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.4)\n",
|
||
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2024.1)\n",
|
||
"Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.10/dist-packages (from pandas) (1.25.2)\n",
|
||
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
|
||
"Hit:1 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 InRelease\n",
|
||
"Get:2 https://cloud.r-project.org/bin/linux/ubuntu jammy-cran40/ InRelease [3,626 B]\n",
|
||
"Get:3 http://security.ubuntu.com/ubuntu jammy-security InRelease [129 kB]\n",
|
||
"Hit:4 http://archive.ubuntu.com/ubuntu jammy InRelease\n",
|
||
"Get:5 http://archive.ubuntu.com/ubuntu jammy-updates InRelease [128 kB]\n",
|
||
"Hit:6 https://ppa.launchpadcontent.net/c2d4u.team/c2d4u4.0+/ubuntu jammy InRelease\n",
|
||
"Hit:7 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu jammy InRelease\n",
|
||
"Get:8 https://ppa.launchpadcontent.net/graphics-drivers/ppa/ubuntu jammy InRelease [24.3 kB]\n",
|
||
"Hit:9 https://ppa.launchpadcontent.net/ubuntugis/ppa/ubuntu jammy InRelease\n",
|
||
"Get:10 http://archive.ubuntu.com/ubuntu jammy-backports InRelease [127 kB]\n",
|
||
"Get:11 http://security.ubuntu.com/ubuntu jammy-security/universe amd64 Packages [1,084 kB]\n",
|
||
"Get:12 https://ppa.launchpadcontent.net/graphics-drivers/ppa/ubuntu jammy/main amd64 Packages [47.6 kB]\n",
|
||
"Get:13 http://archive.ubuntu.com/ubuntu jammy-updates/universe amd64 Packages [1,377 kB]\n",
|
||
"Get:14 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 Packages [2,129 kB]\n",
|
||
"Get:15 http://security.ubuntu.com/ubuntu jammy-security/main amd64 Packages [1,858 kB]\n",
|
||
"Fetched 6,907 kB in 5s (1,378 kB/s)\n",
|
||
"Reading package lists... Done\n",
|
||
"Reading package lists... Done\n",
|
||
"Building dependency tree... Done\n",
|
||
"Reading state information... Done\n",
|
||
"ca-certificates is already the newest version (20230311ubuntu0.22.04.1).\n",
|
||
"curl is already the newest version (7.81.0-1ubuntu1.16).\n",
|
||
"gnupg is already the newest version (2.2.27-3ubuntu2.1).\n",
|
||
"gnupg set to manually installed.\n",
|
||
"0 upgraded, 0 newly installed, 0 to remove and 51 not upgraded.\n",
|
||
"deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_20.x nodistro main\n",
|
||
"Hit:1 https://cloud.r-project.org/bin/linux/ubuntu jammy-cran40/ InRelease\n",
|
||
"Hit:2 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 InRelease\n",
|
||
"Get:3 https://deb.nodesource.com/node_20.x nodistro InRelease [12.1 kB]\n",
|
||
"Hit:4 http://archive.ubuntu.com/ubuntu jammy InRelease\n",
|
||
"Hit:5 http://security.ubuntu.com/ubuntu jammy-security InRelease\n",
|
||
"Hit:6 http://archive.ubuntu.com/ubuntu jammy-updates InRelease\n",
|
||
"Get:7 https://deb.nodesource.com/node_20.x nodistro/main amd64 Packages [7,495 B]\n",
|
||
"Hit:8 http://archive.ubuntu.com/ubuntu jammy-backports InRelease\n",
|
||
"Hit:9 https://ppa.launchpadcontent.net/c2d4u.team/c2d4u4.0+/ubuntu jammy InRelease\n",
|
||
"Hit:10 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu jammy InRelease\n",
|
||
"Hit:11 https://ppa.launchpadcontent.net/graphics-drivers/ppa/ubuntu jammy InRelease\n",
|
||
"Hit:12 https://ppa.launchpadcontent.net/ubuntugis/ppa/ubuntu jammy InRelease\n",
|
||
"Fetched 19.6 kB in 1s (16.1 kB/s)\n",
|
||
"Reading package lists... Done\n",
|
||
"Reading package lists... Done\n",
|
||
"Building dependency tree... Done\n",
|
||
"Reading state information... Done\n",
|
||
"The following NEW packages will be installed:\n",
|
||
" nodejs\n",
|
||
"0 upgraded, 1 newly installed, 0 to remove and 51 not upgraded.\n",
|
||
"Need to get 31.6 MB of archives.\n",
|
||
"After this operation, 196 MB of additional disk space will be used.\n",
|
||
"Get:1 https://deb.nodesource.com/node_20.x nodistro/main amd64 nodejs amd64 20.14.0-1nodesource1 [31.6 MB]\n",
|
||
"Fetched 31.6 MB in 1s (59.9 MB/s)\n",
|
||
"debconf: unable to initialize frontend: Dialog\n",
|
||
"debconf: (No usable dialog-like program is installed, so the dialog based frontend cannot be used. at /usr/share/perl5/Debconf/FrontEnd/Dialog.pm line 78, <> line 1.)\n",
|
||
"debconf: falling back to frontend: Readline\n",
|
||
"debconf: unable to initialize frontend: Readline\n",
|
||
"debconf: (This frontend requires a controlling tty.)\n",
|
||
"debconf: falling back to frontend: Teletype\n",
|
||
"dpkg-preconfigure: unable to re-open stdin: \n",
|
||
"Selecting previously unselected package nodejs.\n",
|
||
"(Reading database ... 121918 files and directories currently installed.)\n",
|
||
"Preparing to unpack .../nodejs_20.14.0-1nodesource1_amd64.deb ...\n",
|
||
"Unpacking nodejs (20.14.0-1nodesource1) ...\n",
|
||
"Setting up nodejs (20.14.0-1nodesource1) ...\n",
|
||
"Processing triggers for man-db (2.10.2-1) ...\n",
|
||
"v20.14.0\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#@title Install Requirement\n",
|
||
"!pip install pandas\n",
|
||
"import pandas as pd\n",
|
||
"# Install Node.js (because tweet-harvest built using Node.js)\n",
|
||
"!sudo apt-get update\n",
|
||
"!sudo apt-get install -y ca-certificates curl gnupg\n",
|
||
"!sudo mkdir -p /etc/apt/keyrings\n",
|
||
"!curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | sudo gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg\n",
|
||
"\n",
|
||
"!NODE_MAJOR=20 && echo \"deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_$NODE_MAJOR.x nodistro main\" | sudo tee /etc/apt/sources.list.d/nodesource.list\n",
|
||
"\n",
|
||
"!sudo apt-get update\n",
|
||
"!sudo apt-get install nodejs -y\n",
|
||
"\n",
|
||
"!node -v"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"source": [
|
||
"#@title Crawling Data\n",
|
||
"\n",
|
||
"twitter_auth_token = '226ba6333b7918979c2c5a16d991aee92a3a62c7'\n",
|
||
"filename = 'kdrt.csv'\n",
|
||
"keyWord = 'perselingkuhan'\n",
|
||
"dateSearch = 'until:2021-01-21 since:2020-03-22'\n",
|
||
"search_keyword = f\"{keyWord} {dateSearch}\"\n",
|
||
"limit = 1000\n",
|
||
"\n",
|
||
"!npx --yes tweet-harvest@2.6.0 -o \"{filename}\" -s \"{search_keyword}\" -l {limit} --token {twitter_auth_token}"
|
||
],
|
||
"metadata": {
|
||
"id": "LYDR51dJlVlX",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/"
|
||
},
|
||
"outputId": "e333b5d2-42a0-4c61-9a31-eba4c5fabd19"
|
||
},
|
||
"execution_count": 2,
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K\u001b[1mnpm\u001b[22m \u001b[33mwarn\u001b[39m \u001b[94mdeprecated\u001b[39m rimraf@3.0.2: Rimraf versions prior to v4 are no longer supported\n",
|
||
"\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K\u001b[1mnpm\u001b[22m \u001b[33mwarn\u001b[39m \u001b[94mdeprecated\u001b[39m inflight@1.0.6: This module is not supported, and leaks memory. Do not use it. Check out lru-cache if you want a good and tested way to coalesce async requests by a key value, which is much more comprehensive and powerful.\n",
|
||
"\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K\u001b[1mnpm\u001b[22m \u001b[33mwarn\u001b[39m \u001b[94mdeprecated\u001b[39m glob@7.2.3: Glob versions prior to v9 are no longer supported\n",
|
||
"\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K⠧\u001b[1G\u001b[0K⠇\u001b[1G\u001b[0K⠏\u001b[1G\u001b[0K⠋\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K⠹\u001b[1G\u001b[0K⠸\u001b[1G\u001b[0K⠼\u001b[1G\u001b[0K⠴\u001b[1G\u001b[0K⠦\u001b[1G\u001b[0K\u001b[1m\u001b[32mTweet Harvest [v2.6.0]\u001b[39m\u001b[22m\n",
|
||
"\u001b[1m\u001b[32m\u001b[39m\u001b[22m\n",
|
||
"\u001b[34mResearch by \u001b[39m\u001b[1m\u001b[34mHelmi Satria\u001b[39m\u001b[22m\u001b[34m\u001b[39m\n",
|
||
"\u001b[34mUse it for Educational Purposes only!\u001b[39m\n",
|
||
"\u001b[34m\u001b[39m\n",
|
||
"\u001b[33mThis script uses Chromium Browser to crawl data from Twitter with \u001b[1myour Twitter auth token\u001b[22m.\u001b[39m\n",
|
||
"\u001b[33mPlease enter your Twitter auth token when prompted.\u001b[39m\n",
|
||
"\u001b[33m\u001b[39m\n",
|
||
"\u001b[31m\u001b[1mNote:\u001b[22m\u001b[39m Keep your access token secret! Don't share it with anyone else.\n",
|
||
"\u001b[31m\u001b[1mNote:\u001b[22m\u001b[39m This script only runs on your local device.\n",
|
||
"\n",
|
||
"\u001b[34m\u001b[39m\n",
|
||
"\u001b[34mOpening twitter search page...\u001b[39m\n",
|
||
"\u001b[34m\u001b[39m\n",
|
||
"\u001b[90m[v2.6.0]\u001b[39m Invalid twitter auth token. Please check your auth token\n",
|
||
"\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K\u001b[1mnpm\u001b[22m \u001b[96mnotice\u001b[39m\n",
|
||
"\u001b[1mnpm\u001b[22m \u001b[96mnotice\u001b[39m New \u001b[33mminor\u001b[39m version of npm available! \u001b[33m10.7.0\u001b[39m -> \u001b[34m10.8.1\u001b[39m\n",
|
||
"\u001b[1mnpm\u001b[22m \u001b[96mnotice\u001b[39m Changelog: \u001b[34mhttps://github.com/npm/cli/releases/tag/v10.8.1\u001b[39m\n",
|
||
"\u001b[1mnpm\u001b[22m \u001b[96mnotice\u001b[39m To update run: \u001b[4mnpm install -g npm@10.8.1\u001b[24m\n",
|
||
"\u001b[1mnpm\u001b[22m \u001b[96mnotice\u001b[39m\n",
|
||
"\u001b[1G\u001b[0K⠙\u001b[1G\u001b[0K"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"source": [
|
||
"#@title Cek Crawling\n",
|
||
"filename = 'kdrt.csv'\n",
|
||
"filePath = f\"tweets-data/{filename}\"\n",
|
||
"data = pd.read_csv(filePath)\n",
|
||
"print(f\"Jumlah tweet dalam dataframe adalah {len(data)}.\")\n",
|
||
"data.head(5)"
|
||
],
|
||
"metadata": {
|
||
"id": "JjY7CF83qTtF",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/",
|
||
"height": 356
|
||
},
|
||
"outputId": "2542c2b4-2ddc-46c8-bc63-50379dacc48c"
|
||
},
|
||
"execution_count": 3,
|
||
"outputs": [
|
||
{
|
||
"output_type": "error",
|
||
"ename": "FileNotFoundError",
|
||
"evalue": "[Errno 2] No such file or directory: 'tweets-data/kdrt.csv'",
|
||
"traceback": [
|
||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||
"\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
|
||
"\u001b[0;32m<ipython-input-3-97c56697db95>\u001b[0m in \u001b[0;36m<cell line: 4>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mfilename\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'kdrt.csv'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mfilePath\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"tweets-data/{filename}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilePath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Jumlah tweet dalam dataframe adalah {len(data)}.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 910\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkwds_defaults\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 911\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 912\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 913\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 914\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
|
||
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 575\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 576\u001b[0m \u001b[0;31m# Create the parser.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 577\u001b[0;31m \u001b[0mparser\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mTextFileReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 578\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 579\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mchunksize\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0miterator\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m 1405\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1406\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandles\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mIOHandles\u001b[0m \u001b[0;34m|\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1407\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_engine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1408\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1409\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m_make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m 1659\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m\"b\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1660\u001b[0m \u001b[0mmode\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;34m\"b\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1661\u001b[0;31m self.handles = get_handle(\n\u001b[0m\u001b[1;32m 1662\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1663\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/io/common.py\u001b[0m in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m 857\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoding\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;34m\"b\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 858\u001b[0m \u001b[0;31m# Encoding\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 859\u001b[0;31m handle = open(\n\u001b[0m\u001b[1;32m 860\u001b[0m \u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 861\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||
"\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'tweets-data/kdrt.csv'"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {
|
||
"id": "eRfDl54waHC4",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/",
|
||
"height": 1000
|
||
},
|
||
"outputId": "3599ad01-6f93-47ca-f32c-69e85d245969"
|
||
},
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (2.0.3)\n",
|
||
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)\n",
|
||
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.4)\n",
|
||
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2024.1)\n",
|
||
"Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.10/dist-packages (from pandas) (1.25.2)\n",
|
||
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
|
||
"Jumlah tweet dalam dataframe adalah 1108.\n",
|
||
"Jumlah tweet dalam dataframe adalah 56.\n",
|
||
"Jumlah tweet dalam dataframe adalah 2157.\n",
|
||
"Jumlah Total adalah 3010.\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "execute_result",
|
||
"data": {
|
||
"text/plain": [
|
||
" Unnamed: 0.5 Unnamed: 0.3 Unnamed: 0.2 Unnamed: 0.1 Unnamed: 0 \\\n",
|
||
"0 0 0.0 0.0 0.0 0.0 \n",
|
||
"1 1 1.0 1.0 1.0 1.0 \n",
|
||
"2 2 2.0 2.0 2.0 2.0 \n",
|
||
"3 3 3.0 3.0 3.0 3.0 \n",
|
||
"4 4 4.0 4.0 4.0 4.0 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"3005 3005 NaN NaN NaN NaN \n",
|
||
"3006 3006 NaN NaN NaN NaN \n",
|
||
"3007 3007 NaN NaN NaN NaN \n",
|
||
"3008 3008 NaN NaN NaN NaN \n",
|
||
"3009 3009 NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" conversation_id_str created_at favorite_count \\\n",
|
||
"0 1580076775752994816 Wed Oct 12 06:03:54 +0000 2022 40485 \n",
|
||
"1 1612732602531602432 Tue Jan 10 08:46:30 +0000 2023 238 \n",
|
||
"2 1593769984022310913 Sat Nov 19 00:55:49 +0000 2022 37 \n",
|
||
"3 1613113017025331201 Wed Jan 11 09:58:08 +0000 2023 74 \n",
|
||
"4 1608084597035929603 Wed Dec 28 12:56:59 +0000 2022 288 \n",
|
||
"... ... ... ... \n",
|
||
"3005 1610520173974519808 Wed Jan 04 06:51:47 +0000 2023 40 \n",
|
||
"3006 1616113161366822912 Thu Jan 19 16:39:38 +0000 2023 4 \n",
|
||
"3007 1615107283838726144 Mon Jan 16 22:02:38 +0000 2023 23 \n",
|
||
"3008 1613303489140248578 Wed Jan 11 23:52:58 +0000 2023 20 \n",
|
||
"3009 1614130490969030658 Sat Jan 14 05:21:12 +0000 2023 2 \n",
|
||
"\n",
|
||
" full_text id_str \\\n",
|
||
"0 Tabok2an anjing2an pukul2an dalam rumah tangg... 1580076775752994816 \n",
|
||
"1 Pengacara Hotman Paris Hutapea mengaku ditelep... 1612732602531602432 \n",
|
||
"2 STOP Kekerasan dalam Rumah Tangga Maafkan suam... 1593769984022310913 \n",
|
||
"3 Kita sering melihat kekerasan dalam rumah tang... 1613113017025331201 \n",
|
||
"4 Ya kalau suaminya maksa-maksa istrinya hamil n... 1608084597035929603 \n",
|
||
"... ... ... \n",
|
||
"3005 @convomfs Iya trauma gara2 ngeliat anak sebaya... 1610529407118225409 \n",
|
||
"3006 Sepanjang tahun 2022 PA Lumajang mengabulkan 2... 1616113161366822912 \n",
|
||
"3007 Blak-blakan! Hotman Paris Beberkan Pesan Venna... 1615107283838726144 \n",
|
||
"3008 @tanyarlfes Males ngasih tau males Mau red fla... 1613323110341804032 \n",
|
||
"3009 Perceraian orangtua akibat perselingkuhan memb... 1614130490969030658 \n",
|
||
"\n",
|
||
" ... in_reply_to_screen_name lang location \\\n",
|
||
"0 ... NaN in Indonesia \n",
|
||
"1 ... NaN in NaN \n",
|
||
"2 ... NaN in NaN \n",
|
||
"3 ... NaN in ciputat, Tangerang Selatan \n",
|
||
"4 ... NaN in Greater Jakarta, Indonesia \n",
|
||
"... ... ... ... ... \n",
|
||
"3005 ... convomfs in Hogwarts \n",
|
||
"3006 ... NaN in Jakarta \n",
|
||
"3007 ... NaN in Pulo Gadung, Indonesia \n",
|
||
"3008 ... tanyarlfes in Balikpapan,Indonesia \n",
|
||
"3009 ... NaN in Palmerah, Jakarta \n",
|
||
"\n",
|
||
" quote_count reply_count retweet_count \\\n",
|
||
"0 862 727 5638 \n",
|
||
"1 0 15 29 \n",
|
||
"2 4 23 4 \n",
|
||
"3 1 1 20 \n",
|
||
"4 1 4 102 \n",
|
||
"... ... ... ... \n",
|
||
"3005 0 1 0 \n",
|
||
"3006 0 0 1 \n",
|
||
"3007 1 3 2 \n",
|
||
"3008 0 0 0 \n",
|
||
"3009 0 0 0 \n",
|
||
"\n",
|
||
" tweet_url user_id_str \\\n",
|
||
"0 https://twitter.com/Hujandisenja/status/158007... 36906324 \n",
|
||
"1 https://twitter.com/IDNTimes/status/1612732602... 388190238 \n",
|
||
"2 https://twitter.com/tokoghoib/status/159376998... 1285403043425447936 \n",
|
||
"3 https://twitter.com/BincangSyariah/status/1613... 4836542132 \n",
|
||
"4 https://twitter.com/RodriChen/status/160808459... 963890288 \n",
|
||
"... ... ... \n",
|
||
"3005 https://twitter.com/oversizedmoon_/status/1610... 1597022213445943297 \n",
|
||
"3006 https://twitter.com/kompascom/status/161611316... 23343960 \n",
|
||
"3007 https://twitter.com/tvOneNews/status/161510728... 55507370 \n",
|
||
"3008 https://twitter.com/rcyourbae/status/161332311... 238097101 \n",
|
||
"3009 https://twitter.com/hariankompas/status/161413... 255866913 \n",
|
||
"\n",
|
||
" username Unnamed: 0.4 \n",
|
||
"0 Hujandisenja 0.0 \n",
|
||
"1 IDNTimes 1.0 \n",
|
||
"2 tokoghoib 2.0 \n",
|
||
"3 BincangSyariah 3.0 \n",
|
||
"4 RodriChen 4.0 \n",
|
||
"... ... ... \n",
|
||
"3005 oversizedmoon_ 2152.0 \n",
|
||
"3006 kompascom 2153.0 \n",
|
||
"3007 tvOneNews 2154.0 \n",
|
||
"3008 rcyourbae 2155.0 \n",
|
||
"3009 hariankompas 2156.0 \n",
|
||
"\n",
|
||
"[3010 rows x 21 columns]"
|
||
],
|
||
"text/html": [
|
||
"\n",
|
||
" <div id=\"df-97bc159a-4c74-4b99-b67d-40d7943d13d5\" class=\"colab-df-container\">\n",
|
||
" <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>Unnamed: 0.5</th>\n",
|
||
" <th>Unnamed: 0.3</th>\n",
|
||
" <th>Unnamed: 0.2</th>\n",
|
||
" <th>Unnamed: 0.1</th>\n",
|
||
" <th>Unnamed: 0</th>\n",
|
||
" <th>conversation_id_str</th>\n",
|
||
" <th>created_at</th>\n",
|
||
" <th>favorite_count</th>\n",
|
||
" <th>full_text</th>\n",
|
||
" <th>id_str</th>\n",
|
||
" <th>...</th>\n",
|
||
" <th>in_reply_to_screen_name</th>\n",
|
||
" <th>lang</th>\n",
|
||
" <th>location</th>\n",
|
||
" <th>quote_count</th>\n",
|
||
" <th>reply_count</th>\n",
|
||
" <th>retweet_count</th>\n",
|
||
" <th>tweet_url</th>\n",
|
||
" <th>user_id_str</th>\n",
|
||
" <th>username</th>\n",
|
||
" <th>Unnamed: 0.4</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>1580076775752994816</td>\n",
|
||
" <td>Wed Oct 12 06:03:54 +0000 2022</td>\n",
|
||
" <td>40485</td>\n",
|
||
" <td>Tabok2an anjing2an pukul2an dalam rumah tangg...</td>\n",
|
||
" <td>1580076775752994816</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Indonesia</td>\n",
|
||
" <td>862</td>\n",
|
||
" <td>727</td>\n",
|
||
" <td>5638</td>\n",
|
||
" <td>https://twitter.com/Hujandisenja/status/158007...</td>\n",
|
||
" <td>36906324</td>\n",
|
||
" <td>Hujandisenja</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>1612732602531602432</td>\n",
|
||
" <td>Tue Jan 10 08:46:30 +0000 2023</td>\n",
|
||
" <td>238</td>\n",
|
||
" <td>Pengacara Hotman Paris Hutapea mengaku ditelep...</td>\n",
|
||
" <td>1612732602531602432</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>15</td>\n",
|
||
" <td>29</td>\n",
|
||
" <td>https://twitter.com/IDNTimes/status/1612732602...</td>\n",
|
||
" <td>388190238</td>\n",
|
||
" <td>IDNTimes</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>2</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>1593769984022310913</td>\n",
|
||
" <td>Sat Nov 19 00:55:49 +0000 2022</td>\n",
|
||
" <td>37</td>\n",
|
||
" <td>STOP Kekerasan dalam Rumah Tangga Maafkan suam...</td>\n",
|
||
" <td>1593769984022310913</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>4</td>\n",
|
||
" <td>23</td>\n",
|
||
" <td>4</td>\n",
|
||
" <td>https://twitter.com/tokoghoib/status/159376998...</td>\n",
|
||
" <td>1285403043425447936</td>\n",
|
||
" <td>tokoghoib</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>3</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>1613113017025331201</td>\n",
|
||
" <td>Wed Jan 11 09:58:08 +0000 2023</td>\n",
|
||
" <td>74</td>\n",
|
||
" <td>Kita sering melihat kekerasan dalam rumah tang...</td>\n",
|
||
" <td>1613113017025331201</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>ciputat, Tangerang Selatan</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>20</td>\n",
|
||
" <td>https://twitter.com/BincangSyariah/status/1613...</td>\n",
|
||
" <td>4836542132</td>\n",
|
||
" <td>BincangSyariah</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>4</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>1608084597035929603</td>\n",
|
||
" <td>Wed Dec 28 12:56:59 +0000 2022</td>\n",
|
||
" <td>288</td>\n",
|
||
" <td>Ya kalau suaminya maksa-maksa istrinya hamil n...</td>\n",
|
||
" <td>1608084597035929603</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Greater Jakarta, Indonesia</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>4</td>\n",
|
||
" <td>102</td>\n",
|
||
" <td>https://twitter.com/RodriChen/status/160808459...</td>\n",
|
||
" <td>963890288</td>\n",
|
||
" <td>RodriChen</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3005</th>\n",
|
||
" <td>3005</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1610520173974519808</td>\n",
|
||
" <td>Wed Jan 04 06:51:47 +0000 2023</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>@convomfs Iya trauma gara2 ngeliat anak sebaya...</td>\n",
|
||
" <td>1610529407118225409</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>convomfs</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Hogwarts</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>https://twitter.com/oversizedmoon_/status/1610...</td>\n",
|
||
" <td>1597022213445943297</td>\n",
|
||
" <td>oversizedmoon_</td>\n",
|
||
" <td>2152.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3006</th>\n",
|
||
" <td>3006</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1616113161366822912</td>\n",
|
||
" <td>Thu Jan 19 16:39:38 +0000 2023</td>\n",
|
||
" <td>4</td>\n",
|
||
" <td>Sepanjang tahun 2022 PA Lumajang mengabulkan 2...</td>\n",
|
||
" <td>1616113161366822912</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Jakarta</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>https://twitter.com/kompascom/status/161611316...</td>\n",
|
||
" <td>23343960</td>\n",
|
||
" <td>kompascom</td>\n",
|
||
" <td>2153.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3007</th>\n",
|
||
" <td>3007</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1615107283838726144</td>\n",
|
||
" <td>Mon Jan 16 22:02:38 +0000 2023</td>\n",
|
||
" <td>23</td>\n",
|
||
" <td>Blak-blakan! Hotman Paris Beberkan Pesan Venna...</td>\n",
|
||
" <td>1615107283838726144</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Pulo Gadung, Indonesia</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>3</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>https://twitter.com/tvOneNews/status/161510728...</td>\n",
|
||
" <td>55507370</td>\n",
|
||
" <td>tvOneNews</td>\n",
|
||
" <td>2154.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3008</th>\n",
|
||
" <td>3008</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1613303489140248578</td>\n",
|
||
" <td>Wed Jan 11 23:52:58 +0000 2023</td>\n",
|
||
" <td>20</td>\n",
|
||
" <td>@tanyarlfes Males ngasih tau males Mau red fla...</td>\n",
|
||
" <td>1613323110341804032</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>tanyarlfes</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Balikpapan,Indonesia</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>https://twitter.com/rcyourbae/status/161332311...</td>\n",
|
||
" <td>238097101</td>\n",
|
||
" <td>rcyourbae</td>\n",
|
||
" <td>2155.0</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3009</th>\n",
|
||
" <td>3009</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1614130490969030658</td>\n",
|
||
" <td>Sat Jan 14 05:21:12 +0000 2023</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>Perceraian orangtua akibat perselingkuhan memb...</td>\n",
|
||
" <td>1614130490969030658</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>in</td>\n",
|
||
" <td>Palmerah, Jakarta</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>https://twitter.com/hariankompas/status/161413...</td>\n",
|
||
" <td>255866913</td>\n",
|
||
" <td>hariankompas</td>\n",
|
||
" <td>2156.0</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>3010 rows × 21 columns</p>\n",
|
||
"</div>\n",
|
||
" <div class=\"colab-df-buttons\">\n",
|
||
"\n",
|
||
" <div class=\"colab-df-container\">\n",
|
||
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-97bc159a-4c74-4b99-b67d-40d7943d13d5')\"\n",
|
||
" title=\"Convert this dataframe to an interactive table.\"\n",
|
||
" style=\"display:none;\">\n",
|
||
"\n",
|
||
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
|
||
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
|
||
" </svg>\n",
|
||
" </button>\n",
|
||
"\n",
|
||
" <style>\n",
|
||
" .colab-df-container {\n",
|
||
" display:flex;\n",
|
||
" gap: 12px;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-convert {\n",
|
||
" background-color: #E8F0FE;\n",
|
||
" border: none;\n",
|
||
" border-radius: 50%;\n",
|
||
" cursor: pointer;\n",
|
||
" display: none;\n",
|
||
" fill: #1967D2;\n",
|
||
" height: 32px;\n",
|
||
" padding: 0 0 0 0;\n",
|
||
" width: 32px;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-convert:hover {\n",
|
||
" background-color: #E2EBFA;\n",
|
||
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
|
||
" fill: #174EA6;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-buttons div {\n",
|
||
" margin-bottom: 4px;\n",
|
||
" }\n",
|
||
"\n",
|
||
" [theme=dark] .colab-df-convert {\n",
|
||
" background-color: #3B4455;\n",
|
||
" fill: #D2E3FC;\n",
|
||
" }\n",
|
||
"\n",
|
||
" [theme=dark] .colab-df-convert:hover {\n",
|
||
" background-color: #434B5C;\n",
|
||
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
|
||
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
|
||
" fill: #FFFFFF;\n",
|
||
" }\n",
|
||
" </style>\n",
|
||
"\n",
|
||
" <script>\n",
|
||
" const buttonEl =\n",
|
||
" document.querySelector('#df-97bc159a-4c74-4b99-b67d-40d7943d13d5 button.colab-df-convert');\n",
|
||
" buttonEl.style.display =\n",
|
||
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
|
||
"\n",
|
||
" async function convertToInteractive(key) {\n",
|
||
" const element = document.querySelector('#df-97bc159a-4c74-4b99-b67d-40d7943d13d5');\n",
|
||
" const dataTable =\n",
|
||
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
|
||
" [key], {});\n",
|
||
" if (!dataTable) return;\n",
|
||
"\n",
|
||
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
|
||
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
|
||
" + ' to learn more about interactive tables.';\n",
|
||
" element.innerHTML = '';\n",
|
||
" dataTable['output_type'] = 'display_data';\n",
|
||
" await google.colab.output.renderOutput(dataTable, element);\n",
|
||
" const docLink = document.createElement('div');\n",
|
||
" docLink.innerHTML = docLinkHtml;\n",
|
||
" element.appendChild(docLink);\n",
|
||
" }\n",
|
||
" </script>\n",
|
||
" </div>\n",
|
||
"\n",
|
||
"\n",
|
||
"<div id=\"df-5b9217cb-3051-4e6c-9ede-1761f346f44b\">\n",
|
||
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-5b9217cb-3051-4e6c-9ede-1761f346f44b')\"\n",
|
||
" title=\"Suggest charts\"\n",
|
||
" style=\"display:none;\">\n",
|
||
"\n",
|
||
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
|
||
" width=\"24px\">\n",
|
||
" <g>\n",
|
||
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
|
||
" </g>\n",
|
||
"</svg>\n",
|
||
" </button>\n",
|
||
"\n",
|
||
"<style>\n",
|
||
" .colab-df-quickchart {\n",
|
||
" --bg-color: #E8F0FE;\n",
|
||
" --fill-color: #1967D2;\n",
|
||
" --hover-bg-color: #E2EBFA;\n",
|
||
" --hover-fill-color: #174EA6;\n",
|
||
" --disabled-fill-color: #AAA;\n",
|
||
" --disabled-bg-color: #DDD;\n",
|
||
" }\n",
|
||
"\n",
|
||
" [theme=dark] .colab-df-quickchart {\n",
|
||
" --bg-color: #3B4455;\n",
|
||
" --fill-color: #D2E3FC;\n",
|
||
" --hover-bg-color: #434B5C;\n",
|
||
" --hover-fill-color: #FFFFFF;\n",
|
||
" --disabled-bg-color: #3B4455;\n",
|
||
" --disabled-fill-color: #666;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-quickchart {\n",
|
||
" background-color: var(--bg-color);\n",
|
||
" border: none;\n",
|
||
" border-radius: 50%;\n",
|
||
" cursor: pointer;\n",
|
||
" display: none;\n",
|
||
" fill: var(--fill-color);\n",
|
||
" height: 32px;\n",
|
||
" padding: 0;\n",
|
||
" width: 32px;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-quickchart:hover {\n",
|
||
" background-color: var(--hover-bg-color);\n",
|
||
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
|
||
" fill: var(--button-hover-fill-color);\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-quickchart-complete:disabled,\n",
|
||
" .colab-df-quickchart-complete:disabled:hover {\n",
|
||
" background-color: var(--disabled-bg-color);\n",
|
||
" fill: var(--disabled-fill-color);\n",
|
||
" box-shadow: none;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .colab-df-spinner {\n",
|
||
" border: 2px solid var(--fill-color);\n",
|
||
" border-color: transparent;\n",
|
||
" border-bottom-color: var(--fill-color);\n",
|
||
" animation:\n",
|
||
" spin 1s steps(1) infinite;\n",
|
||
" }\n",
|
||
"\n",
|
||
" @keyframes spin {\n",
|
||
" 0% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-bottom-color: var(--fill-color);\n",
|
||
" border-left-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" 20% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-left-color: var(--fill-color);\n",
|
||
" border-top-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" 30% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-left-color: var(--fill-color);\n",
|
||
" border-top-color: var(--fill-color);\n",
|
||
" border-right-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" 40% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-right-color: var(--fill-color);\n",
|
||
" border-top-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" 60% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-right-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" 80% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-right-color: var(--fill-color);\n",
|
||
" border-bottom-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" 90% {\n",
|
||
" border-color: transparent;\n",
|
||
" border-bottom-color: var(--fill-color);\n",
|
||
" }\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"\n",
|
||
" <script>\n",
|
||
" async function quickchart(key) {\n",
|
||
" const quickchartButtonEl =\n",
|
||
" document.querySelector('#' + key + ' button');\n",
|
||
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
|
||
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
|
||
" try {\n",
|
||
" const charts = await google.colab.kernel.invokeFunction(\n",
|
||
" 'suggestCharts', [key], {});\n",
|
||
" } catch (error) {\n",
|
||
" console.error('Error during call to suggestCharts:', error);\n",
|
||
" }\n",
|
||
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
|
||
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
|
||
" }\n",
|
||
" (() => {\n",
|
||
" let quickchartButtonEl =\n",
|
||
" document.querySelector('#df-5b9217cb-3051-4e6c-9ede-1761f346f44b button');\n",
|
||
" quickchartButtonEl.style.display =\n",
|
||
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
|
||
" })();\n",
|
||
" </script>\n",
|
||
"</div>\n",
|
||
" </div>\n",
|
||
" </div>\n"
|
||
],
|
||
"application/vnd.google.colaboratory.intrinsic+json": {
|
||
"type": "dataframe",
|
||
"variable_name": "xxx"
|
||
}
|
||
},
|
||
"metadata": {},
|
||
"execution_count": 5
|
||
}
|
||
],
|
||
"source": [
|
||
"#@title Merge Crawling Data\n",
|
||
"# Cek jumlah data yang didapatkan\n",
|
||
"!pip install pandas\n",
|
||
"import pandas as pd\n",
|
||
"listFile = ['1108.csv','perempuan.csv','2157.csv']\n",
|
||
"for x in range(len(listFile)):\n",
|
||
" #print(x)\n",
|
||
" fileName = listFile[x]\n",
|
||
" filePath = f\"tweets-data/{fileName}\"\n",
|
||
" data = pd.read_csv(filePath)\n",
|
||
" #data = data['full_text']\n",
|
||
" if x > 0:\n",
|
||
" result = pd.merge(result, data, how=\"outer\")\n",
|
||
" else:\n",
|
||
" result = data\n",
|
||
"\n",
|
||
" print(f\"Jumlah tweet dalam dataframe adalah {len(data)}.\")\n",
|
||
"##result.sort_values(by=['favorite_count'], ascending=False)\n",
|
||
"namaSave = '/content/dataset.csv'\n",
|
||
"result.to_csv(namaSave)\n",
|
||
"print(f\"Jumlah Total adalah {len(result)}.\")\n",
|
||
"xxx = pd.read_csv(namaSave)\n",
|
||
"xxx"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"colab": {
|
||
"provenance": []
|
||
},
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"name": "python"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 0
|
||
} |