Files

120 lines
3.0 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'username': '@otwndk',\n",
" 'time': datetime.datetime(2022, 12, 16, 21, 19, 9, tzinfo=tzutc()),\n",
" 'content': 'Sponsoreret: Verdensmestre, europamestre og store danske medaljetagere rammer Odense til et prestigefyldt stævne\\n#odense #fyn #cykling'}"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from database import Data_table\n",
"from scraper import scrape\n",
"\n",
"topic = 'Odense'\n",
"username_list, timestamp_list, content_list = scrape(topic, limit=3, headless=False)\n",
"\n",
"val_dict = {\n",
" 'username': username_list[0],\n",
" 'time': timestamp_list[0],\n",
" 'content': content_list[0]\n",
"}\n",
"\n",
"print(val_dict)\n",
"\n",
"with Data_table() as dt:\n",
" dt.insert(val_dict)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 Odense Universitets Hospital søger #Afdelingsc...\n",
"1 \"Odense Dänemark, Seaside\" Fotografie als Post...\n",
"2 Danimarkanın Odense takımı bu yaz müthiş bir ...\n",
"3 Highlights: SønderjyskE Odense https://t.co/...\n",
"4 “Meta Platforms Inc has halted construction of...\n",
" ... \n",
"1810 Kunne du tænke dig at være med til at begejstr...\n",
"1811 UDEBANEAFSNITTET UDVIDES TIL 1800 PLADSER! \\n\\...\n",
"1812 Der er lagt op til fynsk fodboldfest på søndag...\n",
"1813 Jeg har i stigende omfang den oplevelse, at @A...\n",
"1814 PhD position podning in Odense, Denmark: Impro...\n",
"Name: content, Length: 1815, dtype: object"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from database import get_content\n",
"\n",
"df = get_content()\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv('~/Desktop/content.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.10.6"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "1d532f3642617da00cbdbdc5ef98bd8d4ca226c95ac593ade79d8cbc880a2afe"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}