1
0
personal-data/personal_data/fetchers/steam_community.py
2024-10-03 23:24:12 +02:00

75 lines
2.2 KiB
Python

import dataclasses
import datetime
import logging
import re
from collections.abc import Iterator
from typing import Any
import bs4
from .. import html_util, parse_util, secrets
from ..data import DeduplicateMode, Scraper
logger = logging.getLogger(__name__)
URL_SITE_ROOT = 'https://steamcommunity.com/'
URL_GAME_ACHIVEMENTS = URL_SITE_ROOT + 'id/{username}/stats/appid/{appid}'
FORMAT_DATE_HEADER = '%d/%m/%YYYY'
@dataclasses.dataclass(frozen=True)
class SteamAchievementScraper(Scraper):
dataset_name = 'games_played_TODO'
deduplicate_mode = DeduplicateMode.BY_ALL_COLUMNS
def scrape(self) -> Iterator[dict[str, Any]]:
yield from self.scrape_app(105600)
def scrape_app(self, appid: int) -> Iterator[dict[str, Any]]:
url = URL_GAME_ACHIVEMENTS.format(
username=secrets.STEAM_USERNAME,
appid=appid,
)
response = self.session.get(url)
response.raise_for_status()
NOW = parse_util.parse_response_datetime(response)
# Parse data
soup = bs4.BeautifulSoup(response.content, 'lxml')
game_name: str = re.match(
r'Steam Community :: (.+) :: Jmaa', soup.head.title.get_text(),
).group(1)
soup = html_util.normalize_soup_slightly(
soup,
classes=False,
)
for entry in soup.select('.achieveRow'):
trophy_name: str = entry.select_one('h3').get_text()
trophy_desc: str = entry.select_one('h5').get_text()
trophy_icon: str = entry.select_one('img').src
time_acquired_html: str = entry.select_one('.achieveUnlockTime')
if time_acquired_html is None:
continue
time_acquired_text: str = (
time_acquired_html.get_text().strip().removeprefix('Unlocked ')
)
time_acquired: datetime.datetime = parse_util.parse_time(time_acquired_text)
yield {
'game.name': game_name,
'me.last_played_time': time_acquired,
# Trophy Data
'trophy.name': trophy_name,
'trophy.desc': trophy_desc,
'trophy.icon': trophy_icon,
}
del entry, time_acquired