Files
twitter_scraper/code/scraper.ipynb
T

94 lines
1.8 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"12\n"
]
}
],
"source": [
"from selenium.webdriver.common.action_chains import ActionChains\n",
"from dateutil.parser import parse\n",
"from selenium import webdriver\n",
"import os\n",
"import importlib\n",
"import scraper\n",
"\n",
"importlib.reload(scraper)\n",
"topic = 'Odense'\n",
"limit = 10\n",
"username_list, timestamp_list, content_list = scraper.scrape(topic, limit, headless=False)\n",
"\n",
"print(len(username_list))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"289"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"max([len(c) for c in content_list])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# headless mode - has proven difficult...\n",
"# database access\n",
"# logging with warning to discord\n",
"# main loop - go once every hour\n",
"# containerize"
]
}
],
"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
}