bellingcat/cisticola
1
0
Fork 0
mirror of https://github.com/bellingcat/cisticola.git synced 2026-06-12 21:38:33 +03:00
Code Issues Packages Projects Releases Wiki Activity

implemented deferred media archiving for all scrapers, and implemented tests for them. Refactored archiving methods of Instagram and Gettr scrapers to be able to use default archiving method

Browse Source
This commit is contained in:
Tristan Lee
2022-04-01 01:30:49 -05:00
parent 16aad4ef2c
commit 282f33eff3
26 changed files with 417 additions and 261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/scraper/telegram_snscrape.py
View File

@@ -3,12 +3,19 @@ import pytest
from cisticola.base import Channel
from cisticola.scraper import TelegramSnscrapeScraper
@pytest.mark.unarchived
def test_scrape_telegram_snscrape_channel_no_media(controller, channel_kwargs):
channels = [Channel(**channel_kwargs['telegram'])]
controller.register_scraper(scraper = TelegramSnscrapeScraper())
controller.scrape_channels(channels = channels, archive_media = False)
@pytest.mark.media
@pytest.mark.unarchived
def test_scrape_telegram_snscrape_channel_unarchived_media(controller):
controller.archive_unarchived_media()
@pytest.mark.media
def test_scrape_telegram_snscrape_channel(controller, channel_kwargs):