{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import newspaper\n",
    "url = \"http://www.missingkids.org/poster/NCMC/2045193/1\"\n",
    "#url = \"https://www.missingkids.org/new-poster/NCMC/2045193/1\"\n",
    "\n",
    "art = newspaper.article(url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "art.__dict__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import ollama\n",
    "\n",
    "#model = \"llama3.2:1b\"\n",
    "client = ollama.Client(\n",
    "    host = 'https://ollamamodel.matitos.org',\n",
    ")\n",
    "l = client.list()\n",
    "list_models = [m.get(\"model\") for m in l.model_dump().get(\"models\")]\n",
    "\n",
    "list_models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for m in list_models:\n",
    "    context_key = [ k for k in client.show(m).model_dump().get(\"modelinfo\").keys() if \"context_length\" in k]\n",
    "    if (len(context_key) != 1):\n",
    "        print(\"Problem!!!\")\n",
    "    print(m, client.show(m).model_dump().get(\"modelinfo\").get(context_key[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"...\"\n",
    "model = \"falcon3:1b\"\n",
    "\n",
    "msg_content = {\n",
    "    \"role\": \"user\", \n",
    "    \"content\": text,\n",
    "}\n",
    "response = client.chat(model=model, messages=[msg_content], stream=False)\n",
    "print(response[\"message\"][\"content\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import cv2\n",
    "import base64\n",
    "import numpy as np\n",
    "\n",
    "endpoint = \"http://192.168.2.64:12343/image\"\n",
    "\n",
    "\n",
    "\n",
    "prompt = \"Majestic mountain landscape with snow-capped peaks, autumn foliage in vibrant reds and oranges, a turquoise river winding through a valley, crisp and serene atmosphere, ultra-realistic style.\"\n",
    "prompt = \"A group of kids happily playing in a joy environment\"\n",
    "#prompt = \"A bitcoin behaving like a king, surrounded by small alternative coins. Detailed, geometric style\"\n",
    "\n",
    "json = {\n",
    "    \"prompt\": prompt,\n",
    "    \"num_inference_steps\": 10,\n",
    "    \"size\": \"512x512\",\n",
    "    \"seed\": 123456,\n",
    "}\n",
    "\n",
    "for inf_step in [1, 4, 10, 20, 25, 30, 35, 40, 45, 50, 60, 70, 80, 90, 100]:\n",
    "    json[\"num_inference_steps\"] = inf_step\n",
    "\n",
    "    %time r = requests.post(endpoint, json=json)\n",
    "    print(\"Status code\", r.status_code)\n",
    "\n",
    "    # Image\n",
    "    png_as_np = np.frombuffer(base64.b64decode(r.text), dtype=np.uint8)\n",
    "    image_bgr = cv2.imdecode(png_as_np, cv2.IMREAD_COLOR)\n",
    "\n",
    "    cv2.imwrite(\"sample_img_{}.png\".format(json[\"num_inference_steps\"]), image_bgr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install trafilatura\n",
    "import trafilatura\n",
    "from pprint import pprint\n",
    "\n",
    "url = \"https://www.foxnews.com/us/utah-mommy-blogger-ruby-franke-power-public-image-allowed-child-abuse-go-unchecked-expert\"\n",
    "# url = \"https://www.missingkids.org/poster/USVA/VA25-0820/1\"\n",
    "url = \"https://www.bloomberg.com/news/articles/2025-03-12/eu-launches-metals-tariff-retaliation-on-26-billion-of-us-goods\"\n",
    "\n",
    "# Fetch\n",
    "doc = trafilatura.fetch_url(url)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Content & metadata\n",
    "metadata = trafilatura.extract_metadata(doc)\n",
    "content = trafilatura.extract(doc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pprint(metadata.as_dict())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install newspaper4k\n",
    "# !pip install langdetect \n",
    "import newspaper\n",
    "import langdetect\n",
    "langdetect.DetectorFactory.seed = 0\n",
    "\n",
    "\n",
    "\n",
    "# url = \"https://www.missingkids.org/poster/USVA/VA25-0820/1\"\n",
    "#url = \"https://www.waff.com/2025/03/11/colbert-heights-high-school-employee-arrested-child-abuse/\"\n",
    "\n",
    "\n",
    "\n",
    "#url = \"https://www.bloomberg.com/news/articles/2025-03-12/eu-launches-metals-tariff-retaliation-on-26-billion-of-us-goods\"\n",
    "\n",
    "\n",
    "url = \"https://apnews.com/article/canada-trump-us-tariffs-steel-2517a6a2baf0596cb1a43d3a7d1e7939\"\n",
    "url = \"https://www.foxnews.com/us/utah-mommy-blogger-ruby-franke-power-public-image-allowed-child-abuse-go-unchecked-expert\"\n",
    "#url = \"https://www.ft.com/content/6d7c6915-4ceb-43fc-9896-590036b12a87\"\n",
    "#url = \"https://www.lanacion.com.ar/politica/milei-en-bahia-blanca-un-viaje-sorpresa-para-frenar-las-criticas-y-mostrar-cercania-nid12032025/\"\n",
    "#url = \"https://www.missingkids.org/poster/NCMC/2043547/1\"\n",
    "\n",
    "try:\n",
    "    article = newspaper.article(url)\n",
    "except newspaper.ArticleException as e:\n",
    "    print(\"ArticleException: {}\".format(str(e)))\n",
    "except Exception as e:\n",
    "    print(\"Err: {}\".format(str(e)))\n",
    "\n",
    "# url_photo = set([i for i in article.images if \"api.missingkids.org/photographs\" in i])\n",
    "# article.is_valid_url(), article.is_parsed, article.is_media_news(), article.is_valid_body()\n",
    "article.meta_data\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install news-please\n",
    "from newsplease import NewsPlease\n",
    "\n",
    "url = \"https://variety.com/2025/film/news/gene-hackman-death-suspicious-gas-leak-search-warrant-1236322610/\"\n",
    "url = \"https://www.bbc.com/news/articles/cewkkkvkzn9o\"\n",
    "url = \"https://www.foxnews.com/us/utah-mommy-blogger-ruby-franke-power-public-image-allowed-child-abuse-go-unchecked-expert\"\n",
    "article = NewsPlease.from_url(url)\n",
    "print(article.title)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(article.maintext)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "matitos",
   "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": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}