1
0

PSN Profiles: Implemented pagination

This commit is contained in:
Jon Michael Aanes 2024-10-23 21:29:53 +02:00
parent 5255206cf4
commit 3170d8e7a8
Signed by: Jmaa
SSH Key Fingerprint: SHA256:Ab0GfHGCblESJx7JRE4fj4bFy/KRpeLhi41y4pF3sNA
2 changed files with 47 additions and 8 deletions

View File

@ -1,6 +1,7 @@
import dataclasses
import logging
import re
import datetime
from collections.abc import Iterator
import bs4
@ -17,6 +18,7 @@ logger = logging.getLogger(__name__)
URL_API_ROOT = 'https://psnprofiles.com/'
URL_PROFILE = URL_API_ROOT + '{psn_id}'
URL_USER_GAME_TROPHIES = URL_API_ROOT + 'trophies/{game_id}/{psn_id}'
URL_GAMES_OVERVIEW = URL_API_ROOT + '{psn_id}'
def game_psnprofiles_id_from_url(relative_url: str) -> int:
@ -42,6 +44,8 @@ class PsnProfilesScraper(Scraper):
games_rows = list(self._scrape_games_overview())
games_ids = {row['psnprofiles.game_id']: row['game.name'] for row in games_rows}
logger.info('Found %d games from overview', len(games_rows))
SCRAPE_FROM_OVERVIEW = False
if SCRAPE_FROM_OVERVIEW:
yield from games_rows
@ -59,24 +63,50 @@ class PsnProfilesScraper(Scraper):
self.session,
URL_API_ROOT,
per_minute=5,
expire_after=datetime.timedelta(hours=1),
)
requests_util.setup_limiter(
self.session,
URL_API_ROOT+'/trophies/',
expire_after=datetime.timedelta(days=14),
)
def _scrape_games_overview(self) -> Iterator[dict]:
for page_num in range(1, 1000):
logger.info('Getting Overview (page %d)', page_num)
url = URL_GAMES_OVERVIEW.format(psn_id=secrets.PLAYSTATION_PSN_ID)
response = self.session.get(url, params={'page': page_num})
if 'page' not in response.url:
msg = 'Configuration error? psnprofiles.com made an redirection. This is possibly because your profile name wasn\'t exactly as expected. Please check it'
raise RuntimeError(msg)
response.raise_for_status()
soup = bs4.BeautifulSoup(response.text, 'lxml')
soup = personal_data.html_util.normalize_soup_slightly(soup, classes=False)
games_on_page = list(self._iterate_games_from_games_table(soup))
yield from games_on_page
if len(games_on_page) == 0:
return
def _scrape_games_overview_old(self) -> Iterator[dict]:
# Request to get overview
logger.info('Getting Overview')
url = URL_PROFILE.format(psn_id=secrets.PLAYSTATION_PSN_ID)
response = self.session.get(url)
response.raise_for_status()
NOW = parse_util.parse_response_datetime(response)
now = parse_util.parse_response_datetime(response)
# Parse data
soup = bs4.BeautifulSoup(response.content, 'lxml')
soup = personal_data.html_util.normalize_soup_slightly(soup, classes=False)
# Recent trophies.
yield from self._iterate_games_from_recent_tropies(soup, now)
yield from self._iterate_games_from_games_table(soup)
def _iterate_games_from_recent_tropies(self, soup, now) -> Iterator[dict]:
soup_recent_tropies = soup.select('ul#recent-trophies > li')
assert len(soup_recent_tropies) > 0, url
assert len(soup_recent_tropies) > 0
for row in soup_recent_tropies:
cells = row.select_one('.info .box td').find_all('div')
@ -91,7 +121,7 @@ class PsnProfilesScraper(Scraper):
cells[2].get_text().strip().removesuffix(' in').removesuffix(' ago')
)
gotten_at = parse_util.parse_duration(gotten_at)
time_acquired = NOW - gotten_at
time_acquired = now - gotten_at
yield {
'game.name': game_name,
@ -105,10 +135,15 @@ class PsnProfilesScraper(Scraper):
del row, cells, time_acquired
def _iterate_games_from_games_table(self, soup) -> Iterator[dict]:
# Games table
table_rows = soup.find(id='gamesTable').find_all('tr')
assert len(table_rows) > 0, url
if title := table_rows[0].h2:
if title.get_text().strip() == 'No games found':
return
for row in table_rows:
cells = row.find_all('td')

View File

@ -54,12 +54,16 @@ def get_session(
ignore_cache: bool,
) -> requests.Session:
assert isinstance(with_cfscrape, bool)
session_class = requests_cache.CachedSession
if ignore_cache:
logger.warning('HTTP cache disabled')
return requests.Session()
if cfscrape:
session_class = CachedCfScrape
if ignore_cache:
logger.warning('HTTP cache disabled')
return cfscrape.create_scraper()
else:
session_class = requests_cache.CachedSession
if ignore_cache:
logger.warning('HTTP cache disabled')
return requests.Session()
session = session_class(
OUTPUT_PATH / 'web_cache',
cookies=cookiejar,