def __init__(
self,
hs: "HomeServer",
media_repo: "MediaRepository",
media_storage: MediaStorage,
):
super().__init__()
self.auth = hs.get_auth()
self.clock = hs.get_clock()
self.filepaths = media_repo.filepaths
self.max_spider_size = hs.config.media.max_spider_size
self.server_name = hs.hostname
self.store = hs.get_datastore()
self.client = SimpleHttpClient(
hs,
treq_args={"browser_like_redirects": True},
ip_whitelist=hs.config.media.url_preview_ip_range_whitelist,
ip_blacklist=hs.config.media.url_preview_ip_range_blacklist,
use_proxy=True,
)
self.media_repo = media_repo
self.primary_base_path = media_repo.primary_base_path
self.media_storage = media_storage
self._oembed = OEmbedProvider(hs)
# We run the background jobs if we're the instance specified (or no
# instance is specified, where we assume there is only one instance
# serving media).
instance_running_jobs = hs.config.media.media_instance_running_background_jobs
self._worker_run_media_background_jobs = (
instance_running_jobs is None
or instance_running_jobs == hs.get_instance_name()
)
self.url_preview_url_blacklist = hs.config.media.url_preview_url_blacklist
self.url_preview_accept_language = hs.config.media.url_preview_accept_language
# memory cache mapping urls to an ObservableDeferred returning
# JSON-encoded OG metadata
self._cache: ExpiringCache[str, ObservableDeferred] = ExpiringCache(
cache_name="url_previews",
clock=self.clock,
# don't spider URLs more often than once an hour
expiry_ms=ONE_HOUR,
)
if self._worker_run_media_background_jobs:
self._cleaner_loop = self.clock.looping_call(
self._start_expire_url_cache_data, 10 * 1000
)
def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
self.oembed = OEmbedProvider(hs)
def prepare(self, reactor: MemoryReactor, clock: Clock, homeserver: HomeServer):
self.oembed = OEmbedProvider(homeserver)