bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-07-05 08:08:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix instagram_extractor.py typo in config value.

Browse Source
This commit is contained in:
erinhmclark
2025-03-03 21:06:09 +00:00
parent 011ded2bde
commit a705a78632
2 changed files with 43 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
src/auto_archiver/modules/instagram_extractor/instagram_extractor.py
View File

@@ -3,7 +3,9 @@
highlights, and tagged posts. Authentication is required via username/password or a session file. highlights, and tagged posts. Authentication is required via username/password or a session file.
""" """
import re, os, shutil, traceback import re, os, shutil
from sys import exc_info
import instaloader import instaloader
from loguru import logger from loguru import logger
@@ -28,19 +30,27 @@ class InstagramExtractor(Extractor):
def setup(self) -> None: def setup(self) -> None:
self.insta = instaloader.Instaloader( self.insta = instaloader.Instaloader(
download_geotags=True, download_comments=True, compress_json=False, dirname_pattern=self.download_folder, filename_pattern="{date_utc}_UTC_{target}__{typename}" download_geotags=True,
download_comments=True,
compress_json=False,
dirname_pattern=self.download_folder,
filename_pattern="{date_utc}_UTC_{target}__{typename}"
) )
try: try:
self.insta.load_session_from_file(self.username, self.session_file) self.insta.load_session_from_file(self.username, self.session_file)
except Exception as e: except FileNotFoundError:
logger.error(f"Unable to login from session file: {e}\n{traceback.format_exc()}") logger.info("No existing session file found - Attempting login with use and password.")
try: try:
self.insta.login(self.username, config.instagram_self.password) self.insta.login(self.username, self.password)
# TODO: wait for this issue to be fixed https://github.com/instaloader/instaloader/issues/1758
self.insta.save_session_to_file(self.session_file) self.insta.save_session_to_file(self.session_file)
except Exception as e2: except Exception as e:
logger.error(f"Unable to finish login (retrying from file): {e2}\n{traceback.format_exc()}") logger.error(f"Failed to log in with Instaloader: {e}")
# TODO raise exception?
# raise Exception(f"Failed to log in with Instaloader: {e}")
except Exception as e:
logger.error(f"Error loading session file: {e}")
# TODO raise exception?
# raise Exception(f"Error loading session file: {e}")
def download(self, item: Metadata) -> Metadata: def download(self, item: Metadata) -> Metadata:

37
tests/extractors/test_instagram_extractor.py
View File

@@ -3,19 +3,30 @@ import pytest
from auto_archiver.modules.instagram_extractor import InstagramExtractor from auto_archiver.modules.instagram_extractor import InstagramExtractor
from .test_extractor_base import TestExtractorBase from .test_extractor_base import TestExtractorBase
class TestInstagramExtractor(TestExtractorBase):
@pytest.fixture
def intsagram_extractor(setup_module):
extractor_module: str = 'instagram_extractor' extractor_module: str = 'instagram_extractor'
config: dict = {} config: dict = {
"username": "user_name",
"password": "password123",
"download_folder": "instaloader",
"session_file": "secrets/instaloader.session",
}
return setup_module(extractor_module, config)
@pytest.mark.parametrize("url", [
"https://www.instagram.com/p/",
"https://www.instagram.com/p/1234567890/",
"https://www.instagram.com/reel/1234567890/", @pytest.mark.parametrize("url", [
"https://www.instagram.com/username/", "https://www.instagram.com/p/",
"https://www.instagram.com/username/stories/", "https://www.instagram.com/p/1234567890/",
"https://www.instagram.com/username/highlights/", "https://www.instagram.com/reel/1234567890/",
]) "https://www.instagram.com/username/",
def test_regex_matches(self, url): "https://www.instagram.com/username/stories/",
# post "https://www.instagram.com/username/highlights/",
assert InstagramExtractor.valid_url.match(url) ])
def test_regex_matches(url, instagram_extractor):
# post
assert instagram_extractor.valid_url.match(url)