notebooks/imdb-case.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "twelve-interval",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"from bs4 import BeautifulSoup\n",
"\n",
"import aswan"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "published-explanation",
"metadata": {},
"outputs": [],
"source": [
"project = aswan.Project(\"imdb-example\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "optimum-preservation",
"metadata": {},
"outputs": [],
"source": [
"@project.register_handler\n",
"class CelebHandler(aswan.RequestSoupHandler):\n",
" url_root = \"https://www.imdb.com\"\n",
"\n",
" def parse(self, soup: BeautifulSoup):\n",
" return {\n",
" \"name\": soup.find(\"h1\").find(\"span\").text.strip(),\n",
" \"dob\": soup.find(\"div\", id=\"name-born-info\").find(\"time\")[\"datetime\"],\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "front-shower",
"metadata": {},
"outputs": [],
"source": [
"@project.register_handler\n",
"class MovieHandler(aswan.RequestSoupHandler):\n",
" url_root = \"https://www.imdb.com\"\n",
"\n",
" def parse(self, soup: BeautifulSoup):\n",
"\n",
" for cast in soup.find(\"table\", class_=\"cast_list\").find_all(\n",
" \"td\", class_=\"primary_photo\"\n",
" )[:3]:\n",
" self.register_links_to_handler([cast.find(\"a\")[\"href\"]], CelebHandler)\n",
"\n",
" ref_section = soup.find(\"section\", class_=\"titlereference-section-overview\")\n",
" summary = None\n",
" if ref_section is not None:\n",
" summary = getattr(ref_section.find(\"div\"), \"text\", \"\").strip()\n",
" return {\n",
" \"title\": soup.find(\"title\")\n",
" .text.replace(\" - Reference View - IMDb\", \"\")\n",
" .strip(),\n",
" \"summary\": summary,\n",
" \"year\": int(\n",
" soup.find(\"span\", class_=\"titlereference-title-year\").find(\"a\").text\n",
" ),\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "divided-promise",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2022-10-06 16:47.56 [info ] running function setup batch=prep\n",
"2022-10-06 16:47.56 [info ] function setup returned None batch=prep\n",
"2022-10-06 16:47.56 [info ] running function _initiate_status batch=prep\n",
"2022-10-06 16:47.56 [info ] function _initiate_status returned None batch=prep\n",
"2022-10-06 16:47.56 [info ] running function _create_scheduler batch=prep\n",
"2022-10-06 16:47.56 [info ] function _create_scheduler returned None batch=prep\n",
"2022-10-06 16:48.12 [info ] running function join batch=cleanup\n",
"2022-10-06 16:48.12 [info ] function join returned None batch=cleanup\n"
]
}
],
"source": [
"project.run(\n",
" urls_to_register={\n",
" MovieHandler: [\n",
" \"https://www.imdb.com/title/tt1045772/reference\",\n",
" \"https://www.imdb.com/title/tt2543164/reference\",\n",
" ],\n",
" CelebHandler: [\"https://www.imdb.com/name/nm0000190\"],\n",
" },\n",
" force_sync=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "dea76c82",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>title</th>\n",
" <th>summary</th>\n",
" <th>year</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>I Love You Phillip Morris (2009)</td>\n",
" <td>A cop turns con man once he comes out of the c...</td>\n",
" <td>2009</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Arrival (2016)</td>\n",
" <td>A linguist works with the military to communic...</td>\n",
" <td>2016</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" title \\\n",
"0 I Love You Phillip Morris (2009) \n",
"1 Arrival (2016) \n",
"\n",
" summary year \n",
"0 A cop turns con man once he comes out of the c... 2009 \n",
"1 A linguist works with the military to communic... 2016 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame([pcev.content for pcev in project.depot.get_handler_events(MovieHandler)])"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "57d58380",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>name</th>\n",
" <th>dob</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ewan McGregor</td>\n",
" <td>1971-3-31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Jeremy Renner</td>\n",
" <td>1971-1-7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Leslie Mann</td>\n",
" <td>1972-3-26</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Forest Whitaker</td>\n",
" <td>1961-7-15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Amy Adams</td>\n",
" <td>1974-8-20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Jim Carrey</td>\n",
" <td>1962-1-17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Matthew McConaughey</td>\n",
" <td>1969-11-4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" name dob\n",
"0 Ewan McGregor 1971-3-31\n",
"1 Jeremy Renner 1971-1-7\n",
"2 Leslie Mann 1972-3-26\n",
"3 Forest Whitaker 1961-7-15\n",
"4 Amy Adams 1974-8-20\n",
"5 Jim Carrey 1962-1-17\n",
"6 Matthew McConaughey 1969-11-4"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.DataFrame([pcev.content for pcev in project.depot.get_handler_events(CelebHandler)])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4ae4da03",
"metadata": {},
"outputs": [],
"source": [
"project.cleanup_current_run()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "beautiful-lawsuit",
"metadata": {},
"outputs": [],
"source": [
"project.depot.purge()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.10.6 ('data-project')",
"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"
},
"vscode": {
"interpreter": {
"hash": "c34365d60e34b30dc48102674d627ffeb37891f3ae5b0d543a727d8b1b3f5762"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}