{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "#import library\n", "import urllib\n", "import requests\n", "import bs4\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# request a link\n", "def request_url(link):\n", " response = requests.get(link)\n", " html = response.text\n", " return html" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# Function to parse html\n", "def parse_html(to_parse):\n", " soup = bs4.BeautifulSoup(to_parse, 'html.parser')\n", " return soup" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "#take sub menu news form liputan6.com\n", "def all_section(main_url):\n", " section_list = []\n", " for i in main_url:\n", " soup = parse_html(request_url(i))\n", " for a in soup.find_all('a', href=True): \n", " if a.text:\n", " section_list.append(a['href'])\n", " return section_list" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "#get only link about corona or covid\n", "def find_corona(main_url):\n", " url_list = []\n", " not_news=[]\n", " for i in main_url:\n", " if i.find('corona')!=-1 or i.find('covid')!=-1 or i.find('pandemi')!=-1:\n", " url_list.append(i)\n", " url_list = list(dict.fromkeys(url_list))\n", " for i in url_list:\n", " if (i.find('tag') != -1 or i.find('https://') == -1 or i.find('topic')!=-1):\n", " not_news.append(i) \n", " for j in not_news:\n", " url_list.remove(j)\n", " return url_list" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "def title(main_url):\n", " titles = []\n", " for i in main_url:\n", " soup = parse_html(request_url(i))\n", " try :\n", " h1 = soup.select('h1', {'class' : 'f50 black2 f400 crismon'})[0].text.strip()\n", " titles.append(h1)\n", " except:\n", " titles.append('None')\n", " return titles " ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "def writer(main_url):\n", " author = []\n", " for i in main_url:\n", " soup=parse_html(request_url(i))\n", " try: \n", " get_author = soup.find(\"div\", id=\"penulis\")\n", " get_editor = soup.find(\"div\", id=\"editor\")\n", " if(get_author):\n", " get_author = ' '.join(get_author.text.split())\n", " author.append(''.join(get_author.partition('Penulis: ')[2:]))\n", " elif(get_editor):\n", " get_editor = ' '.join(get_editor.text.split())\n", " author.append(''.join(get_editor.partition('Editor: ')[2:]))\n", " else:\n", " author.append('None')\n", " except:\n", " author.append('None')\n", " return author" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "def date(main_url):\n", " datetime = []\n", " for i in main_url:\n", " soup=parse_html(request_url(i))\n", " try:\n", " get_datetime = soup.find(\"time\", class_=\"grey\")\n", " if(get_datetime):\n", " datetime.append(get_datetime.text)\n", " else:\n", " datetime.append('None')\n", " except:\n", " datetime.append('None')\n", " return datetime" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "def collect_text(main_url, titles = [], author = [], datetime = []):\n", " paragraf = []\n", " data = []\n", " join =[]\n", " isiteks = []\n", " \n", " for i,j in enumerate(main_url):\n", " a = parse_html(request_url(j))\n", " try:\n", " content = a.find('div', class_='side-article txt-article')\n", " pragraf = content.find_all('p')\n", " for k in pragraf:\n", " s = ' '.join(k.text.split())\n", " paragraf.append(s)\n", " data.append(paragraf)\n", " paragraf = []\n", " except:\n", " data.append(paragraf)\n", " for i in data:\n", " join.append(' '.join(i))\n", " \n", " for i, j in enumerate(main_url):\n", " isiteks.append({'news': 'Tribunnews.com', 'link' : j, 'title': titles[i], 'author' : author[i], 'date_time': datetime[i], 'paragraf' : join[i]})\n", " return isiteks" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "#take all article pages from urls\n", "def all_pages(main_url):\n", " all_pages_articles = []\n", " for page in main_url:\n", " soup = parse_html(request_url(page))\n", " div_class = soup.find_all(\"div\", class_= \"pt10 pb5 plr10 ovh bggrey\")\n", " \n", " if (div_class == []):\n", " all_pages_articles.append(page)\n", " else :\n", " for i in div_class:\n", " url_class = i.find_all(\"a\")\n", " for j in url_class:\n", " all_pages_articles.append(j.get('href'))\n", " return all_pages_articles" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "def save_file(file, file_name = ''):\n", " new_file = pd.DataFrame(file, columns=['news','link','title', 'author', 'date_time', 'paragraf'])\n", " new_file.to_csv(file_name + '.csv', index=True, encoding='utf-8', sep = ',')\n", " \n", " return new_file" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "def get_news(main_url, file_name = ''):\n", " section = all_section(main_url)\n", " corona = find_corona(section)\n", " all_page = all_pages(corona)\n", " titles = title(all_page)\n", " author = writer(all_page)\n", " dates = date(all_page)\n", " text = collect_text(all_page, titles, author, dates)\n", " file = save_file(text, file_name)\n", " \n", " return file " ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "url=[\"https://www.tribunnews.com/\"]" ] }, { "cell_type": "code", "execution_count": 23, "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>news</th>\n", " <th>link</th>\n", " <th>title</th>\n", " <th>author</th>\n", " <th>date_time</th>\n", " <th>paragraf</th>\n", " </tr>\n", " </thead>\n", " <tbody>\n", " <tr>\n", " <th>0</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.covid19.go.id/</td>\n", " <td>Tips Atasi Rasa Jenuh dan cemas dari Presiden ...</td>\n", " <td>None</td>\n", " <td>None</td>\n", " <td>Laporan Wartawan Tribunnews.com, Larasati Dyah...</td>\n", " </tr>\n", " <tr>\n", " <th>1</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona</td>\n", " <td>Data Covid-19 di Indonesia</td>\n", " <td>None</td>\n", " <td>1 hari lalu</td>\n", " <td>Laporan Wartawan Tribunnews.com, Larasati Dyah...</td>\n", " </tr>\n", " <tr>\n", " <th>2</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/w...</td>\n", " <td>WNI Kabur Dari Pusat Karantina Covid-19 di Mal...</td>\n", " <td>Larasati Dyah Utami</td>\n", " <td>Kamis, 7 Mei 2020 21:50 WIB</td>\n", " <td>Laporan Wartawan Tribunnews.com, Larasati Dyah...</td>\n", " </tr>\n", " <tr>\n", " <th>3</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/lifestyle/2020/05/0...</td>\n", " <td>Anak Rentan Stres di Masa Pandemi Covid-19, In...</td>\n", " <td>Widyadewi Metta Adya Irani</td>\n", " <td>Kamis, 7 Mei 2020 21:45 WIB</td>\n", " <td>TRIBUNNEWS.COM - Berikut cara mencegah dan men...</td>\n", " </tr>\n", " <tr>\n", " <th>4</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/lifestyle/2020/05/0...</td>\n", " <td>Anak Rentan Stres di Masa Pandemi Covid-19, In...</td>\n", " <td>Widyadewi Metta Adya Irani</td>\n", " <td>Kamis, 7 Mei 2020 21:45 WIB</td>\n", " <td>Sehingga, adanya kebijakan Pembatasan Sosial B...</td>\n", " </tr>\n", " <tr>\n", " <th>5</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/lifestyle/2020/05/0...</td>\n", " <td>Anak Rentan Stres di Masa Pandemi Covid-19, In...</td>\n", " <td>Widyadewi Metta Adya Irani</td>\n", " <td>Kamis, 7 Mei 2020 21:45 WIB</td>\n", " <td>Berikut cara mencegah stres pada anak: 1. Memb...</td>\n", " </tr>\n", " <tr>\n", " <th>6</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/lifestyle/2020/05/0...</td>\n", " <td>Anak Rentan Stres di Masa Pandemi Covid-19, In...</td>\n", " <td>Widyadewi Metta Adya Irani</td>\n", " <td>Kamis, 7 Mei 2020 21:45 WIB</td>\n", " <td>Pasalnya, menurut Hudan, stres yang dialami or...</td>\n", " </tr>\n", " <tr>\n", " <th>7</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/k...</td>\n", " <td>Karena Pandemi Corona, Gadis Kirgiztan Terjeba...</td>\n", " <td>Talitha Desena Darenti</td>\n", " <td>Kamis, 7 Mei 2020 20:44 WIB</td>\n", " <td>TRIBUNNEWS.COM - Di balik pandemi virus Corona...</td>\n", " </tr>\n", " <tr>\n", " <th>8</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/g...</td>\n", " <td>Gubernur Ganjar Bentuk Tim Khusus Cari Orang Y...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:31 WIB</td>\n", " <td>TRIBUNNEWS.COM, SEMARANG - Alumni ijtima dunia...</td>\n", " </tr>\n", " <tr>\n", " <th>9</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/g...</td>\n", " <td>Gubernur Ganjar Bentuk Tim Khusus Cari Orang Y...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:31 WIB</td>\n", " <td>Ada kekhawatiran yang akan terjadi jika para a...</td>\n", " </tr>\n", " <tr>\n", " <th>10</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/g...</td>\n", " <td>Gubernur Ganjar Bentuk Tim Khusus Cari Orang Y...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:31 WIB</td>\n", " <td>Karena itu, masyarakat harus jujur. Diperkirak...</td>\n", " </tr>\n", " <tr>\n", " <th>11</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/a...</td>\n", " <td>Anies Baswedan: Pemprov DKI Telah Menyiapkan A...</td>\n", " <td>Adi Suhendi</td>\n", " <td>Kamis, 7 Mei 2020 22:30 WIB</td>\n", " <td>TRIBUNNEWS.COM, JAKARTA - Pemerintah Provinsi ...</td>\n", " </tr>\n", " <tr>\n", " <th>12</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/a...</td>\n", " <td>Anies Baswedan: Pemprov DKI Telah Menyiapkan A...</td>\n", " <td>Adi Suhendi</td>\n", " <td>Kamis, 7 Mei 2020 22:30 WIB</td>\n", " <td>Sampai April, anggaran BTT yang telah dialokas...</td>\n", " </tr>\n", " <tr>\n", " <th>13</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/a...</td>\n", " <td>Anies Baswedan: Pemprov DKI Telah Menyiapkan A...</td>\n", " <td>Adi Suhendi</td>\n", " <td>Kamis, 7 Mei 2020 22:30 WIB</td>\n", " <td>Namun, lantaran DKI meminta 1,1 juta warganya ...</td>\n", " </tr>\n", " <tr>\n", " <th>14</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/regional/2020/05/07...</td>\n", " <td>Tansuli Jatuh dan Meninggal, Warga Tak Berani ...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:18 WIB</td>\n", " <td>TRIBUNNEWS.COM, BANDAR LAMPUNG -- Seorang pria...</td>\n", " </tr>\n", " <tr>\n", " <th>15</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/regional/2020/05/07...</td>\n", " <td>Tansuli Jatuh dan Meninggal, Warga Tak Berani ...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:18 WIB</td>\n", " <td>Warga Tanjungkarang, Enggal, Bandar Lampung, T...</td>\n", " </tr>\n", " <tr>\n", " <th>16</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/b...</td>\n", " <td>Banyak Jenis Bansos yang Disalurkan Pemerintah...</td>\n", " <td>Mafani Fidesya Hutauruk</td>\n", " <td>Kamis, 7 Mei 2020 22:16 WIB</td>\n", " <td>Laporan wartawan Tribunnews.com, Mafani Fidesy...</td>\n", " </tr>\n", " <tr>\n", " <th>17</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/b...</td>\n", " <td>Banyak Jenis Bansos yang Disalurkan Pemerintah...</td>\n", " <td>Mafani Fidesya Hutauruk</td>\n", " <td>Kamis, 7 Mei 2020 22:16 WIB</td>\n", " <td>“Dalam kondisi normal pun kehidupannya sudah p...</td>\n", " </tr>\n", " <tr>\n", " <th>18</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/k...</td>\n", " <td>Kisah Cewek Kirgizstan 'Cinlok' dengan Pria La...</td>\n", " <td>Hasanudin Aco</td>\n", " <td>Kamis, 7 Mei 2020 12:14 WIB</td>\n", " <td>TRIBUNNEWS.COM, LAMPUNG - Lockdown di China sa...</td>\n", " </tr>\n", " <tr>\n", " <th>19</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/k...</td>\n", " <td>Kisah Cewek Kirgizstan 'Cinlok' dengan Pria La...</td>\n", " <td>Hasanudin Aco</td>\n", " <td>Kamis, 7 Mei 2020 12:14 WIB</td>\n", " <td>Namun, kebijakan lockdown oleh pemerintah Chin...</td>\n", " </tr>\n", " <tr>\n", " <th>20</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/k...</td>\n", " <td>Kisah Cewek Kirgizstan 'Cinlok' dengan Pria La...</td>\n", " <td>Hasanudin Aco</td>\n", " <td>Kamis, 7 Mei 2020 12:14 WIB</td>\n", " <td>Meski baru sebentar di Bandar Lampung, Aiperi ...</td>\n", " </tr>\n", " <tr>\n", " <th>21</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/images/regional/vie...</td>\n", " <td>None</td>\n", " <td>None</td>\n", " <td>6 jam lalu</td>\n", " <td>TRIBUNNEWS.COM, TULUNGAGUNG - Puskesmas Simo d...</td>\n", " </tr>\n", " <tr>\n", " <th>22</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/regional/2020/05/07...</td>\n", " <td>Ada Kasus Covid-19, Puskesmas Simo Tulungagung...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:04 WIB</td>\n", " <td>TRIBUNNEWS.COM, TULUNGAGUNG - Puskesmas Simo d...</td>\n", " </tr>\n", " <tr>\n", " <th>23</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/regional/2020/05/07...</td>\n", " <td>Ada Kasus Covid-19, Puskesmas Simo Tulungagung...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 22:04 WIB</td>\n", " <td>Pada penutupan kali ini karena ditemukan satu ...</td>\n", " </tr>\n", " <tr>\n", " <th>24</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/seleb/2020/05/07/mi...</td>\n", " <td>Mikha Tambayong: Covid-19 Hancurkan Agenda Aku...</td>\n", " <td>Willem Jonata</td>\n", " <td>Kamis, 7 Mei 2020 21:57 WIB</td>\n", " <td>TRIBUNNEWS.COM - Karena pandemi virus corona (...</td>\n", " </tr>\n", " <tr>\n", " <th>25</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/06/3...</td>\n", " <td>3 Penumpang Positif Covid-19, Kemenhub Pastika...</td>\n", " <td>Hari Darmawan</td>\n", " <td>Rabu, 6 Mei 2020 08:36 WIB</td>\n", " <td>Laporan Wartawan Tribunnews, Hari Darmawan TRI...</td>\n", " </tr>\n", " <tr>\n", " <th>26</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/images/editorial/vi...</td>\n", " <td>None</td>\n", " <td>None</td>\n", " <td>6 jam lalu</td>\n", " <td>TRIBUNNEWS.COM - Founder sekaligus Chief Execu...</td>\n", " </tr>\n", " <tr>\n", " <th>27</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/images/editorial/vi...</td>\n", " <td>None</td>\n", " <td>None</td>\n", " <td>6 jam lalu</td>\n", " <td>TRIBUNNEWS.COM - Founder sekaligus Chief Execu...</td>\n", " </tr>\n", " <tr>\n", " <th>28</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/bisnis/2020/05/07/c...</td>\n", " <td>Cara Hendy Setiono Motivasi Karyawan Baba Rafi...</td>\n", " <td>Endra Kurniawan</td>\n", " <td>Kamis, 7 Mei 2020 21:44 WIB</td>\n", " <td>TRIBUNNEWS.COM - Founder sekaligus Chief Execu...</td>\n", " </tr>\n", " <tr>\n", " <th>29</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/bisnis/2020/05/07/c...</td>\n", " <td>Cara Hendy Setiono Motivasi Karyawan Baba Rafi...</td>\n", " <td>Endra Kurniawan</td>\n", " <td>Kamis, 7 Mei 2020 21:44 WIB</td>\n", " <td>Baginya krisis yang ditimbulkan akibat Covid-1...</td>\n", " </tr>\n", " <tr>\n", " <th>30</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/bisnis/2020/05/07/c...</td>\n", " <td>Cara Hendy Setiono Motivasi Karyawan Baba Rafi...</td>\n", " <td>Endra Kurniawan</td>\n", " <td>Kamis, 7 Mei 2020 21:44 WIB</td>\n", " <td>Usahanya yang ada di luar negeri juga mengalam...</td>\n", " </tr>\n", " <tr>\n", " <th>31</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/r...</td>\n", " <td>Riset Terbaru Sebut Wabah Corona di Indonesia ...</td>\n", " <td>Hasanudin Aco</td>\n", " <td>Kamis, 7 Mei 2020 16:06 WIB</td>\n", " <td>TRIBUNNEWS.COM, SINGAPURA - Sebuah riset yang ...</td>\n", " </tr>\n", " <tr>\n", " <th>32</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/internasional/2020/...</td>\n", " <td>Kasus Positif Covid-19 Baru di New York Mayori...</td>\n", " <td>Imanuel Nicolas Manafe</td>\n", " <td>Kamis, 7 Mei 2020 16:06 WIB</td>\n", " <td>TRIBUNNEWS.COM, NEW YORK - Warga yang terpapar...</td>\n", " </tr>\n", " <tr>\n", " <th>33</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/internasional/2020/...</td>\n", " <td>Kasus Positif Covid-19 Baru di New York Mayori...</td>\n", " <td>Imanuel Nicolas Manafe</td>\n", " <td>Kamis, 7 Mei 2020 16:06 WIB</td>\n", " <td>Gubernur New York dari Partai Demokrat itu men...</td>\n", " </tr>\n", " <tr>\n", " <th>34</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/internasional/2020/...</td>\n", " <td>Kasus Positif Covid-19 Baru di New York Mayori...</td>\n", " <td>Imanuel Nicolas Manafe</td>\n", " <td>Kamis, 7 Mei 2020 16:06 WIB</td>\n", " <td>Dia memaparkan sekitar 600 orang yang terinfek...</td>\n", " </tr>\n", " <tr>\n", " <th>35</th>\n", " <td>Tribunnews.com</td>\n", " <td>https://www.tribunnews.com/corona/2020/05/07/j...</td>\n", " <td>Jokowi Minta Gugus Tugas Pusat Ikut Tangani Co...</td>\n", " <td>Hendra Gunawan</td>\n", " <td>Kamis, 7 Mei 2020 16:08 WIB</td>\n", " <td>TRIBUNNEWS.COM, SURABAYA - Presiden Joko Widod...</td>\n", " </tr>\n", " </tbody>\n", "</table>\n", "</div>" ], "text/plain": [ " news link \\\n", "0 Tribunnews.com https://www.covid19.go.id/ \n", "1 Tribunnews.com https://www.tribunnews.com/corona \n", "2 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/w... \n", "3 Tribunnews.com https://www.tribunnews.com/lifestyle/2020/05/0... \n", "4 Tribunnews.com https://www.tribunnews.com/lifestyle/2020/05/0... \n", "5 Tribunnews.com https://www.tribunnews.com/lifestyle/2020/05/0... \n", "6 Tribunnews.com https://www.tribunnews.com/lifestyle/2020/05/0... \n", "7 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/k... \n", "8 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/g... \n", "9 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/g... \n", "10 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/g... \n", "11 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/a... \n", "12 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/a... \n", "13 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/a... \n", "14 Tribunnews.com https://www.tribunnews.com/regional/2020/05/07... \n", "15 Tribunnews.com https://www.tribunnews.com/regional/2020/05/07... \n", "16 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/b... \n", "17 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/b... \n", "18 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/k... \n", "19 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/k... \n", "20 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/k... \n", "21 Tribunnews.com https://www.tribunnews.com/images/regional/vie... \n", "22 Tribunnews.com https://www.tribunnews.com/regional/2020/05/07... \n", "23 Tribunnews.com https://www.tribunnews.com/regional/2020/05/07... \n", "24 Tribunnews.com https://www.tribunnews.com/seleb/2020/05/07/mi... \n", "25 Tribunnews.com https://www.tribunnews.com/corona/2020/05/06/3... \n", "26 Tribunnews.com https://www.tribunnews.com/images/editorial/vi... \n", "27 Tribunnews.com https://www.tribunnews.com/images/editorial/vi... \n", "28 Tribunnews.com https://www.tribunnews.com/bisnis/2020/05/07/c... \n", "29 Tribunnews.com https://www.tribunnews.com/bisnis/2020/05/07/c... \n", "30 Tribunnews.com https://www.tribunnews.com/bisnis/2020/05/07/c... \n", "31 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/r... \n", "32 Tribunnews.com https://www.tribunnews.com/internasional/2020/... \n", "33 Tribunnews.com https://www.tribunnews.com/internasional/2020/... \n", "34 Tribunnews.com https://www.tribunnews.com/internasional/2020/... \n", "35 Tribunnews.com https://www.tribunnews.com/corona/2020/05/07/j... \n", "\n", " title \\\n", "0 Tips Atasi Rasa Jenuh dan cemas dari Presiden ... \n", "1 Data Covid-19 di Indonesia \n", "2 WNI Kabur Dari Pusat Karantina Covid-19 di Mal... \n", "3 Anak Rentan Stres di Masa Pandemi Covid-19, In... \n", "4 Anak Rentan Stres di Masa Pandemi Covid-19, In... \n", "5 Anak Rentan Stres di Masa Pandemi Covid-19, In... \n", "6 Anak Rentan Stres di Masa Pandemi Covid-19, In... \n", "7 Karena Pandemi Corona, Gadis Kirgiztan Terjeba... \n", "8 Gubernur Ganjar Bentuk Tim Khusus Cari Orang Y... \n", "9 Gubernur Ganjar Bentuk Tim Khusus Cari Orang Y... \n", "10 Gubernur Ganjar Bentuk Tim Khusus Cari Orang Y... \n", "11 Anies Baswedan: Pemprov DKI Telah Menyiapkan A... \n", "12 Anies Baswedan: Pemprov DKI Telah Menyiapkan A... \n", "13 Anies Baswedan: Pemprov DKI Telah Menyiapkan A... \n", "14 Tansuli Jatuh dan Meninggal, Warga Tak Berani ... \n", "15 Tansuli Jatuh dan Meninggal, Warga Tak Berani ... \n", "16 Banyak Jenis Bansos yang Disalurkan Pemerintah... \n", "17 Banyak Jenis Bansos yang Disalurkan Pemerintah... \n", "18 Kisah Cewek Kirgizstan 'Cinlok' dengan Pria La... \n", "19 Kisah Cewek Kirgizstan 'Cinlok' dengan Pria La... \n", "20 Kisah Cewek Kirgizstan 'Cinlok' dengan Pria La... \n", "21 None \n", "22 Ada Kasus Covid-19, Puskesmas Simo Tulungagung... \n", "23 Ada Kasus Covid-19, Puskesmas Simo Tulungagung... \n", "24 Mikha Tambayong: Covid-19 Hancurkan Agenda Aku... \n", "25 3 Penumpang Positif Covid-19, Kemenhub Pastika... \n", "26 None \n", "27 None \n", "28 Cara Hendy Setiono Motivasi Karyawan Baba Rafi... \n", "29 Cara Hendy Setiono Motivasi Karyawan Baba Rafi... \n", "30 Cara Hendy Setiono Motivasi Karyawan Baba Rafi... \n", "31 Riset Terbaru Sebut Wabah Corona di Indonesia ... \n", "32 Kasus Positif Covid-19 Baru di New York Mayori... \n", "33 Kasus Positif Covid-19 Baru di New York Mayori... \n", "34 Kasus Positif Covid-19 Baru di New York Mayori... \n", "35 Jokowi Minta Gugus Tugas Pusat Ikut Tangani Co... \n", "\n", " author date_time \\\n", "0 None None \n", "1 None 1 hari lalu \n", "2 Larasati Dyah Utami Kamis, 7 Mei 2020 21:50 WIB \n", "3 Widyadewi Metta Adya Irani Kamis, 7 Mei 2020 21:45 WIB \n", "4 Widyadewi Metta Adya Irani Kamis, 7 Mei 2020 21:45 WIB \n", "5 Widyadewi Metta Adya Irani Kamis, 7 Mei 2020 21:45 WIB \n", "6 Widyadewi Metta Adya Irani Kamis, 7 Mei 2020 21:45 WIB \n", "7 Talitha Desena Darenti Kamis, 7 Mei 2020 20:44 WIB \n", "8 Hendra Gunawan Kamis, 7 Mei 2020 22:31 WIB \n", "9 Hendra Gunawan Kamis, 7 Mei 2020 22:31 WIB \n", "10 Hendra Gunawan Kamis, 7 Mei 2020 22:31 WIB \n", "11 Adi Suhendi Kamis, 7 Mei 2020 22:30 WIB \n", "12 Adi Suhendi Kamis, 7 Mei 2020 22:30 WIB \n", "13 Adi Suhendi Kamis, 7 Mei 2020 22:30 WIB \n", "14 Hendra Gunawan Kamis, 7 Mei 2020 22:18 WIB \n", "15 Hendra Gunawan Kamis, 7 Mei 2020 22:18 WIB \n", "16 Mafani Fidesya Hutauruk Kamis, 7 Mei 2020 22:16 WIB \n", "17 Mafani Fidesya Hutauruk Kamis, 7 Mei 2020 22:16 WIB \n", "18 Hasanudin Aco Kamis, 7 Mei 2020 12:14 WIB \n", "19 Hasanudin Aco Kamis, 7 Mei 2020 12:14 WIB \n", "20 Hasanudin Aco Kamis, 7 Mei 2020 12:14 WIB \n", "21 None 6 jam lalu \n", "22 Hendra Gunawan Kamis, 7 Mei 2020 22:04 WIB \n", "23 Hendra Gunawan Kamis, 7 Mei 2020 22:04 WIB \n", "24 Willem Jonata Kamis, 7 Mei 2020 21:57 WIB \n", "25 Hari Darmawan Rabu, 6 Mei 2020 08:36 WIB \n", "26 None 6 jam lalu \n", "27 None 6 jam lalu \n", "28 Endra Kurniawan Kamis, 7 Mei 2020 21:44 WIB \n", "29 Endra Kurniawan Kamis, 7 Mei 2020 21:44 WIB \n", "30 Endra Kurniawan Kamis, 7 Mei 2020 21:44 WIB \n", "31 Hasanudin Aco Kamis, 7 Mei 2020 16:06 WIB \n", "32 Imanuel Nicolas Manafe Kamis, 7 Mei 2020 16:06 WIB \n", "33 Imanuel Nicolas Manafe Kamis, 7 Mei 2020 16:06 WIB \n", "34 Imanuel Nicolas Manafe Kamis, 7 Mei 2020 16:06 WIB \n", "35 Hendra Gunawan Kamis, 7 Mei 2020 16:08 WIB \n", "\n", " paragraf \n", "0 Laporan Wartawan Tribunnews.com, Larasati Dyah... \n", "1 Laporan Wartawan Tribunnews.com, Larasati Dyah... \n", "2 Laporan Wartawan Tribunnews.com, Larasati Dyah... \n", "3 TRIBUNNEWS.COM - Berikut cara mencegah dan men... \n", "4 Sehingga, adanya kebijakan Pembatasan Sosial B... \n", "5 Berikut cara mencegah stres pada anak: 1. Memb... \n", "6 Pasalnya, menurut Hudan, stres yang dialami or... \n", "7 TRIBUNNEWS.COM - Di balik pandemi virus Corona... \n", "8 TRIBUNNEWS.COM, SEMARANG - Alumni ijtima dunia... \n", "9 Ada kekhawatiran yang akan terjadi jika para a... \n", "10 Karena itu, masyarakat harus jujur. Diperkirak... \n", "11 TRIBUNNEWS.COM, JAKARTA - Pemerintah Provinsi ... \n", "12 Sampai April, anggaran BTT yang telah dialokas... \n", "13 Namun, lantaran DKI meminta 1,1 juta warganya ... \n", "14 TRIBUNNEWS.COM, BANDAR LAMPUNG -- Seorang pria... \n", "15 Warga Tanjungkarang, Enggal, Bandar Lampung, T... \n", "16 Laporan wartawan Tribunnews.com, Mafani Fidesy... \n", "17 “Dalam kondisi normal pun kehidupannya sudah p... \n", "18 TRIBUNNEWS.COM, LAMPUNG - Lockdown di China sa... \n", "19 Namun, kebijakan lockdown oleh pemerintah Chin... \n", "20 Meski baru sebentar di Bandar Lampung, Aiperi ... \n", "21 TRIBUNNEWS.COM, TULUNGAGUNG - Puskesmas Simo d... \n", "22 TRIBUNNEWS.COM, TULUNGAGUNG - Puskesmas Simo d... \n", "23 Pada penutupan kali ini karena ditemukan satu ... \n", "24 TRIBUNNEWS.COM - Karena pandemi virus corona (... \n", "25 Laporan Wartawan Tribunnews, Hari Darmawan TRI... \n", "26 TRIBUNNEWS.COM - Founder sekaligus Chief Execu... \n", "27 TRIBUNNEWS.COM - Founder sekaligus Chief Execu... \n", "28 TRIBUNNEWS.COM - Founder sekaligus Chief Execu... \n", "29 Baginya krisis yang ditimbulkan akibat Covid-1... \n", "30 Usahanya yang ada di luar negeri juga mengalam... \n", "31 TRIBUNNEWS.COM, SINGAPURA - Sebuah riset yang ... \n", "32 TRIBUNNEWS.COM, NEW YORK - Warga yang terpapar... \n", "33 Gubernur New York dari Partai Demokrat itu men... \n", "34 Dia memaparkan sekitar 600 orang yang terinfek... \n", "35 TRIBUNNEWS.COM, SURABAYA - Presiden Joko Widod... " ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tribunnews_news = get_news(url, file_name = 'tribunnews_satu')\n", "tribunnews_news" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }