Refactor and relocate text summarizer notebooks
Deleted the old kiran-text-summarizer-gpt5mini notebook and added refactored versions for OpenAI GPT-5-mini and Ollama models under week1_assignments. Introduced a reusable scrape_website.py module for web scraping logic. Updated 'day2 EXERCISE.ipynb' to set execution counts and include output for code cells, improving reproducibility and clarity.
This commit is contained in:
KiranAyyagari
@@ -1,231 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1e45263e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Web Data Extraction and Summarization using openAI Latest model gpt-5-mini"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "df155151",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Import Libraries"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "588f8e43",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import requests\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"from bs4 import BeautifulSoup\n",
|
||||
"from IPython.display import Markdown, display\n",
|
||||
"from openai import OpenAI "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b5925769",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### load api key"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6cca85ec",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"load_dotenv(override=True)\n",
|
||||
"api_key = os.getenv('OPENAI_API_KEY')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "56703f80",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### ScrapWebsite using BeautifulSoup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3d60c909",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"headers = {\n",
|
||||
" \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"class ScrapeWebsite:\n",
|
||||
"\n",
|
||||
" def __init__(self, url):\n",
|
||||
" \"\"\" Scraping Website which provides title and content\"\"\"\n",
|
||||
" self.url = url\n",
|
||||
" response = requests.get(self.url, headers=headers)\n",
|
||||
" soup = BeautifulSoup(response.content, 'html.parser')\n",
|
||||
" self.title = soup.title.string if soup.title else \"No title found\"\n",
|
||||
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
|
||||
" irrelevant.decompose()\n",
|
||||
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a8b73c27",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### System Prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4a0c3bda",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"system_prompt = \"You are an analyst that analyses the content of the website \\\n",
|
||||
" provides summary and ignore text related to navigation. Respond in markdown.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9117963b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### User Prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ab164d55",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def user_prompt_for(website):\n",
|
||||
" user_prompt = f\"You are looking at a website titled {website.title}\"\n",
|
||||
" user_prompt += \"\\nThe contents of this website is as follows; Please provide short summary in Markdown. Please include news and \\\n",
|
||||
" announcements\"\n",
|
||||
" user_prompt+=website.text\n",
|
||||
" return user_prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "de7423fb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Format messages in openAI standard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "47c82247",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def messages_for(website):\n",
|
||||
" return [\n",
|
||||
" {\"role\":\"system\", \"content\": system_prompt},\n",
|
||||
" {\"role\":\"user\", \"content\": user_prompt_for(website)}\n",
|
||||
" ]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6e9bb6e1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Summarise the content in website using openAI latest model gpt-5-mini"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "068d6bb2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def summarise(url):\n",
|
||||
" website = ScrapeWebsite(url)\n",
|
||||
" openai = OpenAI()\n",
|
||||
" response = openai.chat.completions.create(model=\"gpt-5-mini\", messages=messages_for(website))\n",
|
||||
" return response.choices[0].message.content"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7e6e9da6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Show summary as Markdown"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cd86c2ca",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def display_summary(url):\n",
|
||||
" summary = summarise(url)\n",
|
||||
" display(Markdown(summary))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ed5e50d2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "74a056b1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"display_summary(\"https://www.firstpost.com/world/united-states/\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "llms",
|
||||
"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": "3.11.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
from bs4 import BeautifulSoup
|
||||
import requests
|
||||
|
||||
|
||||
class ScrapeWebsite:
|
||||
|
||||
def __init__(self, url, headers):
|
||||
""" Scraping Website which provides title and content"""
|
||||
self.url = url
|
||||
response = requests.get(self.url, headers=headers)
|
||||
soup = BeautifulSoup(response.content, 'html.parser')
|
||||
self.title = soup.title.string if soup.title else "No title found"
|
||||
for irrelevant in soup.body(["script", "style", "img", "input"]):
|
||||
irrelevant.decompose()
|
||||
self.text = soup.body.get_text(separator="\n", strip=True)
|
||||
@@ -0,0 +1,186 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# imports\n",
|
||||
"import os\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"from IPython.display import Markdown, display\n",
|
||||
"from openai import OpenAI \n",
|
||||
"from scrape_website import ScrapeWebsite"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "29ddd15d-a3c5-4f4e-a678-873f56162724",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Constants\n",
|
||||
"MODEL = \"llama3.2\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "42c8a8c2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"system_prompt = \"You are an analyst that analyses the content of the website \\\n",
|
||||
" provides summary and ignore text related to navigation. Respond in markdown.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "51e86dd1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def user_prompt_for(website):\n",
|
||||
" user_prompt = f\"You are looking at a website titled {website.title}\"\n",
|
||||
" user_prompt += \"\\nThe contents of this website is as follows; Please provide short summary in Markdown. Please include news and \\\n",
|
||||
" announcements\"\n",
|
||||
" user_prompt+=website.text\n",
|
||||
" return user_prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b69d7238",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def messages_for(website):\n",
|
||||
" return [\n",
|
||||
" {\"role\":\"system\", \"content\": system_prompt},\n",
|
||||
" {\"role\":\"user\", \"content\": user_prompt_for(website)}\n",
|
||||
" ]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a56e99ea",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"headers = {\n",
|
||||
" \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9b4061d0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def summarise(url):\n",
|
||||
" website = ScrapeWebsite(url, headers)\n",
|
||||
" ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
|
||||
" response = ollama_via_openai.chat.completions.create(\n",
|
||||
" model=MODEL,\n",
|
||||
" messages=messages_for(website)\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" return response.choices[0].message.content"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "65f96545",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def display_summary(url):\n",
|
||||
" summary = summarise(url)\n",
|
||||
" display(Markdown(summary))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "23057e00-b6fc-4678-93a9-6b31cb704bff",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Generative AI has numerous business applications across various industries. Here are some examples:\n",
|
||||
"\n",
|
||||
"1. **Marketing and Advertising**: Generative AI can create personalized product recommendations, generate targeted advertisements, and develop new marketing campaigns.\n",
|
||||
"2. **Content Creation**: AI-powered tools can assist in content creation, such as writing articles, generating social media posts, and creating videos, podcasts, and music.\n",
|
||||
"3. **Product Design and Development**: Generative AI can aid in designing products, such as 3D modeling, prototyping, and testing product feasibility.\n",
|
||||
"4. **Customer Service Chatbots**: AI-powered chatbots can provide personalized customer service, answering common queries, and helping resolve issues faster.\n",
|
||||
"5. **Language Translation**: Generative AI can translate languages in real-time, enabling businesses to communicate with global customers more effectively.\n",
|
||||
"6. **Data Analysis and Visualization**: AI can analyze large datasets, identify patterns, and create insights, making it easier for businesses to make informed decisions.\n",
|
||||
"7. **Cybersecurity Threat Detection**: Generative AI-powered systems can detect and respond to cyber threats more efficiently, reducing the risk of data breaches and attacks.\n",
|
||||
"8. **Supply Chain Optimization**: AI can optimize supply chain operations, predict demand, and identify opportunities for improvement, leading to increased efficiency and reduced costs.\n",
|
||||
"9. **Network Security**: Generative AI can analyze network traffic patterns, detect anomalies, and prevent cyber-attacks.\n",
|
||||
"10. **Finance and Banking**: AI-powered systems can detect financial fraud, predict customer creditworthiness, and generate credit reports.\n",
|
||||
"\n",
|
||||
"**Industry-specific applications:**\n",
|
||||
"\n",
|
||||
"1. **Healthcare**: AI can help with medical diagnosis, patient data analysis, and personalized medicine.\n",
|
||||
"2. **Manufacturing**: Generative AI can create optimized production schedules, predict equipment failures, and improve product quality.\n",
|
||||
"3. **Education**: AI-powered tools can develop personalized learning plans, automate grading, and provide educational resources.\n",
|
||||
"4. **Real Estate**: AI can help with property valuations, identify market trends, and analyze potential clients' needs.\n",
|
||||
"\n",
|
||||
"**Business benefits:**\n",
|
||||
"\n",
|
||||
"1. **Increased efficiency**: Automating mundane tasks frees up human resources for more strategic work.\n",
|
||||
"2. **Improved accuracy**: Generative AI reduces the likelihood of human error in decision-making and task execution.\n",
|
||||
"3. **Enhanced customer experience**: Personalized experiences are created through data-driven insights.\n",
|
||||
"4. **Competitive advantage**: Companies using AI can differentiate themselves from competitors by offering innovative services and products.\n",
|
||||
"\n",
|
||||
"As Generative AI continues to evolve, we can expect even more exciting applications across various industries, leading to increased efficiency, accuracy, and improved competitiveness for businesses worldwide.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"display_summary(\"https://www.firstpost.com/world/united-states/\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6de38216-6d1c-48c4-877b-86d403f4e0f8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "llms",
|
||||
"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": "3.11.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -0,0 +1,265 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1e45263e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Web Data Extraction and Summarization using openAI Latest model gpt-5-mini"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "df155151",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Import Libraries"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "588f8e43",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"from IPython.display import Markdown, display\n",
|
||||
"from openai import OpenAI \n",
|
||||
"from scrape_website import ScrapeWebsite"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b5925769",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### load api key"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "6cca85ec",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"load_dotenv(override=True)\n",
|
||||
"api_key = os.getenv('OPENAI_API_KEY')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "56703f80",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### ScrapWebsite using BeautifulSoup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "3d60c909",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"headers = {\n",
|
||||
" \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a8b73c27",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### System Prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "4a0c3bda",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"system_prompt = \"You are an analyst that analyses the content of the website \\\n",
|
||||
" provides summary and ignore text related to navigation. Respond in markdown.\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9117963b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### User Prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "ab164d55",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def user_prompt_for(website):\n",
|
||||
" user_prompt = f\"You are looking at a website titled {website.title}\"\n",
|
||||
" user_prompt += \"\\nThe contents of this website is as follows; Please provide short summary in Markdown. Please include news and \\\n",
|
||||
" announcements\"\n",
|
||||
" user_prompt+=website.text\n",
|
||||
" return user_prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "de7423fb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Format messages in openAI standard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "47c82247",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def messages_for(website):\n",
|
||||
" return [\n",
|
||||
" {\"role\":\"system\", \"content\": system_prompt},\n",
|
||||
" {\"role\":\"user\", \"content\": user_prompt_for(website)}\n",
|
||||
" ]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6e9bb6e1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Summarise the content in website using openAI latest model gpt-5-mini"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "068d6bb2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def summarise(url):\n",
|
||||
" website = ScrapeWebsite(url, headers)\n",
|
||||
" openai = OpenAI()\n",
|
||||
" response = openai.chat.completions.create(model=\"gpt-5-mini\", messages=messages_for(website))\n",
|
||||
" return response.choices[0].message.content"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7e6e9da6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Show summary as Markdown"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "cd86c2ca",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def display_summary(url):\n",
|
||||
" summary = summarise(url)\n",
|
||||
" display(Markdown(summary))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ed5e50d2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "74a056b1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/markdown": [
|
||||
"# Summary — United States Of America | Firstpost (Live/Latest)\n",
|
||||
"\n",
|
||||
"Site focus: Live updates and rundowns of US and world news with emphasis on politics, justice, economy, national security, and breaking incidents. Coverage mixes headlines, investigations, opinion and special features/web stories.\n",
|
||||
"\n",
|
||||
"## Major news (headlines)\n",
|
||||
"- Police shooting near CDC/Emory in Atlanta: a suspected shooter and a police officer were killed after reports of an active shooter near the CDC and Emory University campuses. \n",
|
||||
"- Death of astronaut Jim Lovell (97): Apollo 13 commander and former Navy pilot died in a Chicago suburb. \n",
|
||||
"- Stephen Miran named to Fed Board (short-term): Trump appointed economist Stephen Miran to the Federal Reserve Board through Jan 2026; noted for support of tariffs and rate cuts. \n",
|
||||
"- Trump fires labour statistics chief: President Trump sacked the official overseeing labor data hours after a weak jobs report. \n",
|
||||
"- House panel subpoenas Clintons over Epstein: congressional subpoenas seek documents in relation to Jeffrey Epstein amid pressure on the administration over Epstein files. \n",
|
||||
"- Ghislaine Maxwell moved to lower-security prison in Texas amid scrutiny of Epstein files and government handling. \n",
|
||||
"- FBI/administration tension on Epstein Files: Trump said he would “release everything” after reports the FBI redacted names from the Epstein Files. \n",
|
||||
"- Probe launched into attorney who investigated Trump cases: US officials began a probe targeting Special Counsel Jack Smith. \n",
|
||||
"- NTSB finds technical issues in Army helicopter crash: investigation into crash that killed 67 people identified technical problems. \n",
|
||||
"- Trump unveils modified reciprocal tariffs: new executive order introduced modified tariffs on multiple countries; effective date possibly as late as Oct 5. \n",
|
||||
"- Trump-EU trade deal announced: reported pact imposing a 15% tariff on most EU goods, with large energy and investment components but unresolved issues remain. \n",
|
||||
"- Federal Reserve holds rates steady: Fed kept rates unchanged for a fifth meeting, despite political pressure from Trump. \n",
|
||||
"- White House remodel plan: Trump pushing to build a reported $200 million ballroom at the presidential residence, funded by Trump/donors per WH. \n",
|
||||
"- US citizenship test format under review: Trump administration considers reverting to the 2020 naturalisation test format, citing concerns the current test is too easy. \n",
|
||||
"- American Airlines incident in Denver: passengers evacuated after a Boeing plane caught fire (tire/maintenance issue) before takeoff. \n",
|
||||
"- John Bolton criticizes Tulsi Gabbard: former NSA lambastes Gabbard’s report on Obama as exaggerated and lacking substance. \n",
|
||||
"- Ohio solicitor general Mathura Sridharan trolled: Indian-origin jurist faced racist online backlash after appointment; Ohio AG responded strongly.\n",
|
||||
"\n",
|
||||
"## Announcements, features & recurring elements\n",
|
||||
"- Web stories and quick-read lists: travel/animals/safety themed pieces (e.g., “10 airport codes”, “10 animals that are naturally blue”, World Tiger Day lists). \n",
|
||||
"- Regular sections and shows highlighted in coverage: Firstpost America, Firstpost Africa, First Sports, Vantage, Fast and Factual, Between The Lines, Flashback, Live TV. \n",
|
||||
"- Events and special coverage teased: Raisina Dialogue, Champions Trophy, Delhi Elections 2025, Budget 2025, US Elections 2024, Firstpost Defence Summit. \n",
|
||||
"- Trending topics emphasized: Donald Trump, Narendra Modi, Elon Musk, United States, Joe Biden. \n",
|
||||
"- Quick-links / network: cross-promotion of other Network18 properties (News18, Moneycontrol, CNBC TV18, Forbes India).\n",
|
||||
"\n",
|
||||
"## Tone and emphasis\n",
|
||||
"- Heavy focus on US politics, Trump administration actions and controversies (Epstein Files, tariffs, personnel changes), justice probes, national security incidents, and major breaking events.\n",
|
||||
"- Mix of investigative/legal reporting, immediate breaking news, and light/web-story listicles.\n",
|
||||
"\n",
|
||||
"If you want, I can produce a one-page brief of just the Trump-related items, a timeline of the Epstein/Clinton/Subpoena coverage, or extract all headlines with publication order."
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.Markdown object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"display_summary(\"https://www.firstpost.com/world/united-states/\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "llms",
|
||||
"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": "3.11.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user