def tests(self):
for hdr, expected in self.TEST_CASES.items():
res = get_filename_from_headers({b'Content-Disposition': [hdr]})
self.assertEqual(
res,
expected,
"expected output for %s to be %s but was %s" % (hdr, expected, res),
)
def tests(self) -> None:
for hdr, expected in self.TEST_CASES.items():
res = get_filename_from_headers({b"Content-Disposition": [hdr]})
self.assertEqual(
res,
expected,
f"expected output for {hdr!r} to be {expected} but was {res}",
)
def tests(self):
for hdr, expected in self.TEST_CASES.items():
res = get_filename_from_headers({b"Content-Disposition": [hdr]})
self.assertEqual(
res,
expected,
"expected output for %s to be %s but was %s" %
(hdr, expected, res),
)
def _download_url(self, url, user):
# TODO: we should probably honour robots.txt... except in practice
# we're most likely being explicitly triggered by a human rather than a
# bot, so are we really a robot?
file_id = datetime.date.today().isoformat() + "_" + random_string(16)
file_info = FileInfo(server_name=None, file_id=file_id, url_cache=True)
with self.media_storage.store_into_file(file_info) as (f, fname,
finish):
try:
logger.debug("Trying to get url '%s'" % url)
length, headers, uri, code = yield self.client.get_file(
url, output_stream=f, max_size=self.max_spider_size)
except SynapseError:
# Pass SynapseErrors through directly, so that the servlet
# handler will return a SynapseError to the client instead of
# blank data or a 500.
raise
except DNSLookupError:
# DNS lookup returned no results
# Note: This will also be the case if one of the resolved IP
# addresses is blacklisted
raise SynapseError(
502,
"DNS resolution failure during URL preview generation",
Codes.UNKNOWN,
)
except Exception as e:
# FIXME: pass through 404s and other error messages nicely
logger.warn("Error downloading %s: %r", url, e)
raise SynapseError(
500,
"Failed to download content: %s" %
(traceback.format_exception_only(sys.exc_info()[0], e), ),
Codes.UNKNOWN,
)
yield finish()
try:
if b"Content-Type" in headers:
media_type = headers[b"Content-Type"][0].decode("ascii")
else:
media_type = "application/octet-stream"
time_now_ms = self.clock.time_msec()
download_name = get_filename_from_headers(headers)
yield self.store.store_local_media(
media_id=file_id,
media_type=media_type,
time_now_ms=self.clock.time_msec(),
upload_name=download_name,
media_length=length,
user_id=user,
url_cache=url,
)
except Exception as e:
logger.error("Error handling downloaded %s: %r", url, e)
# TODO: we really ought to delete the downloaded file in this
# case, since we won't have recorded it in the db, and will
# therefore not expire it.
raise
defer.returnValue({
"media_type":
media_type,
"media_length":
length,
"download_name":
download_name,
"created_ts":
time_now_ms,
"filesystem_id":
file_id,
"filename":
fname,
"uri":
uri,
"response_code":
code,
# FIXME: we should calculate a proper expiration based on the
# Cache-Control and Expire headers. But for now, assume 1 hour.
"expires":
60 * 60 * 1000,
"etag":
headers["ETag"][0] if "ETag" in headers else None,
})
async def _download_url(self, url: str, output_stream: BinaryIO) -> DownloadResult:
"""
Fetches a remote URL and parses the headers.
Args:
url: The URL to fetch.
output_stream: The stream to write the content to.
Returns:
A tuple of:
Media length, URL downloaded, the HTTP response code,
the media type, the downloaded file name, the number of
milliseconds the result is valid for, the etag header.
"""
try:
logger.debug("Trying to get preview for url '%s'", url)
length, headers, uri, code = await self.client.get_file(
url,
output_stream=output_stream,
max_size=self.max_spider_size,
headers={"Accept-Language": self.url_preview_accept_language},
)
except SynapseError:
# Pass SynapseErrors through directly, so that the servlet
# handler will return a SynapseError to the client instead of
# blank data or a 500.
raise
except DNSLookupError:
# DNS lookup returned no results
# Note: This will also be the case if one of the resolved IP
# addresses is blacklisted
raise SynapseError(
502,
"DNS resolution failure during URL preview generation",
Codes.UNKNOWN,
)
except Exception as e:
# FIXME: pass through 404s and other error messages nicely
logger.warning("Error downloading %s: %r", url, e)
raise SynapseError(
500,
"Failed to download content: %s"
% (traceback.format_exception_only(sys.exc_info()[0], e),),
Codes.UNKNOWN,
)
if b"Content-Type" in headers:
media_type = headers[b"Content-Type"][0].decode("ascii")
else:
media_type = "application/octet-stream"
download_name = get_filename_from_headers(headers)
# FIXME: we should calculate a proper expiration based on the
# Cache-Control and Expire headers. But for now, assume 1 hour.
expires = ONE_HOUR
etag = headers[b"ETag"][0].decode("ascii") if b"ETag" in headers else None
return DownloadResult(
length, uri, code, media_type, download_name, expires, etag
)
async def _download_url(self, url: str, user):
# TODO: we should probably honour robots.txt... except in practice
# we're most likely being explicitly triggered by a human rather than a
# bot, so are we really a robot?
file_id = datetime.date.today().isoformat() + "_" + random_string(16)
file_info = FileInfo(server_name=None, file_id=file_id, url_cache=True)
# If this URL can be accessed via oEmbed, use that instead.
url_to_download = url # type: Optional[str]
oembed_url = self._get_oembed_url(url)
if oembed_url:
# The result might be a new URL to download, or it might be HTML content.
try:
oembed_result = await self._get_oembed_content(oembed_url, url)
if oembed_result.url:
url_to_download = oembed_result.url
elif oembed_result.html:
url_to_download = None
except OEmbedError:
# If an error occurs, try doing a normal preview.
pass
if url_to_download:
with self.media_storage.store_into_file(file_info) as (f, fname, finish):
try:
logger.debug("Trying to get preview for url '%s'", url_to_download)
length, headers, uri, code = await self.client.get_file(
url_to_download,
output_stream=f,
max_size=self.max_spider_size,
headers={"Accept-Language": self.url_preview_accept_language},
)
except SynapseError:
# Pass SynapseErrors through directly, so that the servlet
# handler will return a SynapseError to the client instead of
# blank data or a 500.
raise
except DNSLookupError:
# DNS lookup returned no results
# Note: This will also be the case if one of the resolved IP
# addresses is blacklisted
raise SynapseError(
502,
"DNS resolution failure during URL preview generation",
Codes.UNKNOWN,
)
except Exception as e:
# FIXME: pass through 404s and other error messages nicely
logger.warning("Error downloading %s: %r", url_to_download, e)
raise SynapseError(
500,
"Failed to download content: %s"
% (traceback.format_exception_only(sys.exc_info()[0], e),),
Codes.UNKNOWN,
)
await finish()
if b"Content-Type" in headers:
media_type = headers[b"Content-Type"][0].decode("ascii")
else:
media_type = "application/octet-stream"
download_name = get_filename_from_headers(headers)
# FIXME: we should calculate a proper expiration based on the
# Cache-Control and Expire headers. But for now, assume 1 hour.
expires = ONE_HOUR
etag = (
headers[b"ETag"][0].decode("ascii") if b"ETag" in headers else None
)
else:
# we can only get here if we did an oembed request and have an oembed_result.html
assert oembed_result.html is not None
assert oembed_url is not None
html_bytes = oembed_result.html.encode("utf-8")
with self.media_storage.store_into_file(file_info) as (f, fname, finish):
f.write(html_bytes)
await finish()
media_type = "text/html"
download_name = oembed_result.title
length = len(html_bytes)
# If a specific cache age was not given, assume 1 hour.
expires = oembed_result.cache_age or ONE_HOUR
uri = oembed_url
code = 200
etag = None
try:
time_now_ms = self.clock.time_msec()
await self.store.store_local_media(
media_id=file_id,
media_type=media_type,
time_now_ms=time_now_ms,
upload_name=download_name,
media_length=length,
user_id=user,
url_cache=url,
)
except Exception as e:
logger.error("Error handling downloaded %s: %r", url, e)
# TODO: we really ought to delete the downloaded file in this
# case, since we won't have recorded it in the db, and will
# therefore not expire it.
raise
return {
"media_type": media_type,
"media_length": length,
"download_name": download_name,
"created_ts": time_now_ms,
"filesystem_id": file_id,
"filename": fname,
"uri": uri,
"response_code": code,
"expires": expires,
"etag": etag,
}
def _download_url(self, url, user):
# TODO: we should probably honour robots.txt... except in practice
# we're most likely being explicitly triggered by a human rather than a
# bot, so are we really a robot?
file_id = datetime.date.today().isoformat() + '_' + random_string(16)
file_info = FileInfo(
server_name=None,
file_id=file_id,
url_cache=True,
)
with self.media_storage.store_into_file(file_info) as (f, fname, finish):
try:
logger.debug("Trying to get url '%s'" % url)
length, headers, uri, code = yield self.client.get_file(
url, output_stream=f, max_size=self.max_spider_size,
)
except SynapseError:
# Pass SynapseErrors through directly, so that the servlet
# handler will return a SynapseError to the client instead of
# blank data or a 500.
raise
except DNSLookupError:
# DNS lookup returned no results
# Note: This will also be the case if one of the resolved IP
# addresses is blacklisted
raise SynapseError(
502, "DNS resolution failure during URL preview generation",
Codes.UNKNOWN
)
except Exception as e:
# FIXME: pass through 404s and other error messages nicely
logger.warn("Error downloading %s: %r", url, e)
raise SynapseError(
500, "Failed to download content: %s" % (
traceback.format_exception_only(sys.exc_info()[0], e),
),
Codes.UNKNOWN,
)
yield finish()
try:
if b"Content-Type" in headers:
media_type = headers[b"Content-Type"][0].decode('ascii')
else:
media_type = "application/octet-stream"
time_now_ms = self.clock.time_msec()
download_name = get_filename_from_headers(headers)
yield self.store.store_local_media(
media_id=file_id,
media_type=media_type,
time_now_ms=self.clock.time_msec(),
upload_name=download_name,
media_length=length,
user_id=user,
url_cache=url,
)
except Exception as e:
logger.error("Error handling downloaded %s: %r", url, e)
# TODO: we really ought to delete the downloaded file in this
# case, since we won't have recorded it in the db, and will
# therefore not expire it.
raise
defer.returnValue({
"media_type": media_type,
"media_length": length,
"download_name": download_name,
"created_ts": time_now_ms,
"filesystem_id": file_id,
"filename": fname,
"uri": uri,
"response_code": code,
# FIXME: we should calculate a proper expiration based on the
# Cache-Control and Expire headers. But for now, assume 1 hour.
"expires": 60 * 60 * 1000,
"etag": headers["ETag"][0] if "ETag" in headers else None,
})
