From 2f9c0457df7c2dc916bfa314e7d9cd3e3827d9b6 Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Thu, 17 Feb 2022 01:50:15 +0000 Subject: [PATCH] Convert t.co card URLs to unshortened when possible --- snscrape/modules/twitter.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/snscrape/modules/twitter.py b/snscrape/modules/twitter.py index f2879a0..485b0e9 100644 --- a/snscrape/modules/twitter.py +++ b/snscrape/modules/twitter.py @@ -600,6 +600,14 @@ class _TwitterAPIScraper(snscrape.base.Scraper): kwargs['cashtags'] = [o['text'] for o in tweet['entities']['symbols']] if card: kwargs['card'] = card + # Try to convert the URL to the non-shortened/t.co one + try: + i = kwargs['tcooutlinks'].index(card.url) + except ValueError: + _logger.warning('Could not find card URL in tcooutlinks') + pass + else: + card.url = kwargs['outlinks'][i] return Tweet(**kwargs) def _make_card(self, card, apiType):