Skip to content

Instantly share code, notes, and snippets.

@GeorgeMcIntire
Created October 9, 2017 03:02
Show Gist options
  • Select an option

  • Save GeorgeMcIntire/d003ece0b6ca171be8e095e0bc90af7e to your computer and use it in GitHub Desktop.

Select an option

Save GeorgeMcIntire/d003ece0b6ca171be8e095e0bc90af7e to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Script took 38.52 seconds to complete\n"
]
}
],
"source": [
"#Imports\n",
"import time\n",
"#Assign time.time() object to \"start\" so we can profile the code.\n",
"start = time.time()\n",
"import pandas as pd\n",
"import numpy as np\n",
"from newspaper import Article\n",
"#Load in pickle file with links and slice the first 50 links\n",
"links = pd.read_pickle(\"nytimes_links.pkl\")[:50]\n",
"\n",
"#Intialize list articles_info list\n",
"articles_info = []\n",
"for i in links:\n",
" #Intialize dictionary\n",
" article_dict = {}\n",
" #Insert link \"i\" into the dictionary\n",
" article_dict[\"link\"] = i\n",
" #Pass link into Article() function\n",
" art = Article(i)\n",
" #Download contents of art object\n",
" art.download()\n",
" \n",
" #Try/except is included because not all articles can be parsed\n",
" try:\n",
" #If article can be successfully parsed then insert its text, title, publish_date, keywords\n",
" #and summary into corresponding keys\n",
" art.parse()\n",
" article_dict[\"text\"] = art.text\n",
" article_dict[\"title\"] = art.title\n",
" article_dict[\"date\"] = art.publish_date\n",
" art.nlp()\n",
" article_dict[\"keywords\"] = art.keywords\n",
" article_dict[\"summary\"] = art.summary\n",
" except ArticleException:\n",
" #If article cannot be parse then insert null values for the following keys:\n",
" #\"text\", \"title\", \"date\", \"keywords\", and \"summary\"\n",
" article_dict[\"text\"] = np.nan\n",
" article_dict[\"title\"] = np.nan\n",
" article_dict[\"date\"] = np.nan\n",
" article_dict[\"keywords\"] = np.nan\n",
" article_dict[\"summary\"] = np.nan\n",
" \n",
" #Insert dictionary of article info into the articles_info list\n",
" articles_info.append(article_dict)\n",
"#Pass the list of dictionaries into a pandas data frame\n",
"corpus = pd.DataFrame(articles_info)\n",
"#Print how long the process took\n",
"print(\"Script took {:.2f} seconds to complete\".format(time.time() - start))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\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",
" <th>keywords</th>\n",
" <th>link</th>\n",
" <th>summary</th>\n",
" <th>text</th>\n",
" <th>title</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2017-09-08</td>\n",
" <td>[intelligence, researchers, sexism, female, la...</td>\n",
" <td>https://www.nytimes.com/2017/09/08/upshot/sexi...</td>\n",
" <td>Across all the categories analyzed and all the...</td>\n",
" <td>First, here’s what they reported finding last ...</td>\n",
" <td>Sexism and Shopping: Female Players Get Most o...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2017-09-08</td>\n",
" <td>[latest, versus, intelligence, tegmark, patter...</td>\n",
" <td>https://www.nytimes.com/2017/09/08/books/revie...</td>\n",
" <td>PhotoGODZILLA VERSUS MOTHRA: James Patterson’s...</td>\n",
" <td>Photo\\n\\nGODZILLA VERSUS MOTHRA: James Patters...</td>\n",
" <td>James Patterson’s Latest Villain Looks a Lot L...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2017-09-01</td>\n",
" <td>[intelligence, human, harm, systems, regulate,...</td>\n",
" <td>https://www.nytimes.com/2017/09/01/opinion/art...</td>\n",
" <td>PhotoThe technology entrepreneur Elon Musk rec...</td>\n",
" <td>Photo\\n\\nThe technology entrepreneur Elon Musk...</td>\n",
" <td>How to Regulate Artificial Intelligence</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2017-09-14</td>\n",
" <td>[intelligence, teaching, human, experiments, e...</td>\n",
" <td>https://www.nytimes.com/2017/09/14/opinion/art...</td>\n",
" <td>PhotoTo the Editor:Re “How to Regulate Artific...</td>\n",
" <td>Photo\\n\\nTo the Editor:\\n\\nRe “How to Regulate...</td>\n",
" <td>Ethics and Artificial Intelligence</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2017-08-30</td>\n",
" <td>[assistants, mr, working, way, cortana, bezos,...</td>\n",
" <td>https://www.nytimes.com/2017/08/30/technology/...</td>\n",
" <td>But Mr. Bezos and Mr. Nadella are concerned th...</td>\n",
" <td>But Mr. Bezos and Mr. Nadella are concerned th...</td>\n",
" <td>‘Cortana, Open Alexa,’ Amazon Says. And Micros...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date keywords \\\n",
"0 2017-09-08 [intelligence, researchers, sexism, female, la... \n",
"1 2017-09-08 [latest, versus, intelligence, tegmark, patter... \n",
"2 2017-09-01 [intelligence, human, harm, systems, regulate,... \n",
"3 2017-09-14 [intelligence, teaching, human, experiments, e... \n",
"4 2017-08-30 [assistants, mr, working, way, cortana, bezos,... \n",
"\n",
" link \\\n",
"0 https://www.nytimes.com/2017/09/08/upshot/sexi... \n",
"1 https://www.nytimes.com/2017/09/08/books/revie... \n",
"2 https://www.nytimes.com/2017/09/01/opinion/art... \n",
"3 https://www.nytimes.com/2017/09/14/opinion/art... \n",
"4 https://www.nytimes.com/2017/08/30/technology/... \n",
"\n",
" summary \\\n",
"0 Across all the categories analyzed and all the... \n",
"1 PhotoGODZILLA VERSUS MOTHRA: James Patterson’s... \n",
"2 PhotoThe technology entrepreneur Elon Musk rec... \n",
"3 PhotoTo the Editor:Re “How to Regulate Artific... \n",
"4 But Mr. Bezos and Mr. Nadella are concerned th... \n",
"\n",
" text \\\n",
"0 First, here’s what they reported finding last ... \n",
"1 Photo\\n\\nGODZILLA VERSUS MOTHRA: James Patters... \n",
"2 Photo\\n\\nThe technology entrepreneur Elon Musk... \n",
"3 Photo\\n\\nTo the Editor:\\n\\nRe “How to Regulate... \n",
"4 But Mr. Bezos and Mr. Nadella are concerned th... \n",
"\n",
" title \n",
"0 Sexism and Shopping: Female Players Get Most o... \n",
"1 James Patterson’s Latest Villain Looks a Lot L... \n",
"2 How to Regulate Artificial Intelligence \n",
"3 Ethics and Artificial Intelligence \n",
"4 ‘Cortana, Open Alexa,’ Amazon Says. And Micros... "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Take a look at the data frame\n",
"corpus.head()"
]
},
{
"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": "3.6.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
@amaurya72
Copy link

unable to locate nytimes_links.pkl . Please let us know from where to download it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment