project305/courts_scraper/scraper.py

from loguru import logger

import aiohttp
import asyncio

from bs4 import BeautifulSoup


class Scraper:
    def __init__(
        self, domains: list[str], rps: int, proxy: list[str] = None
    ):
        self.domains = domains
        self.proxy = proxy
        self.rps = rps

        self.parse_tasks = set()

    async def fetch(self, url: str):
        async with aiohttp.ClientSession() as session:
            async with session.get(url) as resp:
                return await resp.text()

    async def parse(self, url: str) -> str:
        resp = await self.fetch(url)
        logger.debug(f"Received response from {url}!")
        return resp

    async def scrape(self):
        for domain in self.domains:
            url = f"https://{domain}"
            parse_task = asyncio.create_task(self.parse(url))
            self.parse_tasks.add(parse_task)

        done, _pending = await asyncio.wait(self.parse_tasks)