def _get_article_tag_from_url(url: str) -> Optional[ResultSet]:
response = session.get(url)
if response.status_code // 100 != 2:
logger.critical(
"Couldn't get response from habr.com - status code: %d",
response.status_code,
)
return None
return _get_article_tag_from_html(response.text)
def test_session_cookie():
# Fake method to verify that we can get the session_id
# from the request (cookie should have been set and sent along)
# Get the server-side session based on the client-side session_id
server_session_data = server_session.get(session.get(settings.SESSION_ID))
# Tokens should match
assert server_session_data.get("access_token") == ACCESS_TOKEN
assert server_session_data.get("id_token") == ID_TOKEN
return jsonify({}), 200
def get_session_data_or_abort():
session_id = session[settings.SESSION_ID]
_logger.debug("Found session_id %s in session, getting session data",
session_id)
session_data = server_session.get(session_id)
if not session_data:
_logger.warn("Cannot get session data, returning 401")
abort(401)
_logger.debug("Returning session data %s", session_data)
return session_data
def get_session_data_or_none():
"""
Return the server-side session data or None,
based on the client-side session id.
Server-side session is a dict containing an access_token, an id_token, and other
information.
"""
try:
session_data = server_session.get(session[settings.SESSION_ID])
return session_data
except Exception:
return None
def download_article(url: str, storage_path: Path) -> None:
logger.debug('Thread sent request to %s', url)
response = session.get(url)
if response.status_code // 100 != 2:
logger.critical(
"Couldn't get response from habr.com - status code: %d",
response.status_code,
)
title, text, img_tags = _parse_article(response.text)
logger.debug('Thread saving text and images')
store_text_and_images(storage_path,
title=title,
text=text,
img_tags=img_tags)
def store_text_and_images(storage_path: Path, title: str, text: str,
img_tags: ResultSet) -> None:
new_dir = storage_path / title
new_dir.mkdir(exist_ok=True)
filepath = new_dir / 'article.txt'
with filepath.open('w', encoding='utf-8') as f:
f.write(text)
for image_num, tag in enumerate(img_tags, 1):
logger.debug('Thread acquiring image %s', tag['src'])
src = tag['src']
response = session.get(src, stream=True)
img_type = src.split('.')[-1]
logger.debug('Thread saving that image')
img_path = new_dir / f'image-{image_num}.{img_type}'
with img_path.open('wb') as img:
shutil.copyfileobj(response.raw, img)
def _get_management_token(self):
if self.management_session_id:
# Get the payload from cache. Might be expired and not exist anymore.
payload = server_session.get(self.management_session_id)
if payload and "access_token" in payload:
return payload["access_token"]
payload = self._get_management_token_from_remote()
access_token = payload.get("access_token", None)
if not access_token:
raise Exception("Could not find access_token in response")
expires_in = payload.get("expires_in", None)
session_uuid = uuid.uuid4().hex
server_session.create_session(session_uuid,
payload,
expire_seconds=expires_in)
self.management_session_id = session_uuid
return access_token