Getting 404 when trying to scrape hashtag #2144
Description
Describe the bug
I get JSON Query to explore/tags/foodie/: 404 Not Found [retrying; skip with ^C] when I try to scrape a hashtag.
Clearly, the https://www.instagram.com/explore/tags/foodie/ is a normal lively hashtag.
I've also tried other hashtags and get the same error.
To Reproduce
from instaloader import Instaloader, Hashtag
from secret import USER
L = Instaloader()
L.load_session_from_file(USER) # session file duly created
print(f"Logged in as: {L.test_login()}")
h = Hashtag.from_name(L.context, "foodie")
Expected behavior
I'd like to iterate over h.get_posts_resumable()
Error messages and tracebacks
JSON Query to explore/tags/foodie/: 404 Not Found [retrying; skip with ^C]
JSON Query to explore/tags/foodie/: 404 Not Found [retrying; skip with ^C]
---------------------------------------------------------------------------
QueryReturnedNotFoundException Traceback (most recent call last)
File /usr/local/lib/python3.10/dist-packages/instaloader/instaloadercontext.py:405, in InstaloaderContext.get_json(self, path, params, host, session, _attempt, response_headers)
404 if resp.status_code == 404:
--> 405 raise QueryReturnedNotFoundException("404 Not Found")
406 if resp.status_code == 429:
QueryReturnedNotFoundException: 404 Not Found
During handling of the above exception, another exception occurred:
QueryReturnedNotFoundException Traceback (most recent call last)
File /usr/local/lib/python3.10/dist-packages/instaloader/instaloadercontext.py:405, in InstaloaderContext.get_json(self, path, params, host, session, _attempt, response_headers)
404 if resp.status_code == 404:
--> 405 raise QueryReturnedNotFoundException("404 Not Found")
406 if resp.status_code == 429:
QueryReturnedNotFoundException: 404 Not Found
During handling of the above exception, another exception occurred:
QueryReturnedNotFoundException Traceback (most recent call last)
File /usr/local/lib/python3.10/dist-packages/instaloader/instaloadercontext.py:405, in InstaloaderContext.get_json(self, path, params, host, session, _attempt, response_headers)
404 if resp.status_code == 404:
--> 405 raise QueryReturnedNotFoundException("404 Not Found")
406 if resp.status_code == 429:
QueryReturnedNotFoundException: 404 Not Found
The above exception was the direct cause of the following exception:
QueryReturnedNotFoundException Traceback (most recent call last)
Cell In[5], line 6
2 hashtag = "foodie"
4 print(L.context)
----> 6 h = Hashtag.from_name(L.context, hashtag)
7 print(h)
8 h
File /usr/local/lib/python3.10/dist-packages/instaloader/structures.py:1662, in Hashtag.from_name(cls, context, name)
1660 # pylint:disable=protected-access
1661 hashtag = cls(context, {'name': name.lower()})
-> 1662 hashtag._obtain_metadata()
1663 return hashtag
File /usr/local/lib/python3.10/dist-packages/instaloader/structures.py:1676, in Hashtag._obtain_metadata(self)
1674 def _obtain_metadata(self):
1675 if not self._has_full_metadata:
-> 1676 self._node = self._query({"__a": 1, "__d": "dis"})
1677 self._has_full_metadata = True
File /usr/local/lib/python3.10/dist-packages/instaloader/structures.py:1671, in Hashtag._query(self, params)
1670 def _query(self, params):
-> 1671 json_response = self._context.get_json("explore/tags/{0}/".format(self.name), params)
1672 return json_response["graphql"]["hashtag"] if "graphql" in json_response else json_response["data"]
File /usr/local/lib/python3.10/dist-packages/instaloader/instaloadercontext.py:435, in InstaloaderContext.get_json(self, path, params, host, session, _attempt, response_headers)
433 if is_other_query:
434 self._rate_controller.handle_429('other')
--> 435 return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1,
436 response_headers=response_headers)
437 except KeyboardInterrupt:
438 self.error("[skipped by user]", repeat_at_end=False)
File /usr/local/lib/python3.10/dist-packages/instaloader/instaloadercontext.py:435, in InstaloaderContext.get_json(self, path, params, host, session, _attempt, response_headers)
433 if is_other_query:
434 self._rate_controller.handle_429('other')
--> 435 return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1,
436 response_headers=response_headers)
437 except KeyboardInterrupt:
438 self.error("[skipped by user]", repeat_at_end=False)
File /usr/local/lib/python3.10/dist-packages/instaloader/instaloadercontext.py:423, in InstaloaderContext.get_json(self, path, params, host, session, _attempt, response_headers)
421 if _attempt == self.max_connection_attempts:
422 if isinstance(err, QueryReturnedNotFoundException):
--> 423 raise QueryReturnedNotFoundException(error_string) from err
424 else:
425 raise ConnectionException(error_string) from err
QueryReturnedNotFoundException: JSON Query to explore/tags/foodie/: 404 Not Found
Instaloader version
4.10.2