From b1a7b9607f5294ec3f2a51fbfa3468e8f21df50b Mon Sep 17 00:00:00 2001
From: JustAnotherArchivist <JustAnotherArchivist@users.noreply.github.com>
Date: Wed, 7 Oct 2020 01:27:26 +0000
Subject: [PATCH] Skip individual Telegram photo/video links

---
 snscrape/modules/telegram.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/snscrape/modules/telegram.py b/snscrape/modules/telegram.py
index 8ecbb32..5e83917 100644
--- a/snscrape/modules/telegram.py
+++ b/snscrape/modules/telegram.py
@@ -1,12 +1,14 @@
 import bs4
 import datetime
 import logging
+import re
 import snscrape.base
 import typing
 import urllib.parse
 
 
 logger = logging.getLogger(__name__)
+_SINGLE_MEDIA_LINK_PATTERN = re.compile(r'^https://t\.me/[^/]+/\d+\?single$')
 
 
 class LinkPreview(typing.NamedTuple):
@@ -89,6 +91,9 @@ class TelegramChannelScraper(snscrape.base.Scraper):
 					if link['href'] == rawUrl or link['href'] == url:
 						# Generic filter of links to the post itself, catches videos, photos, and the date link
 						continue
+					if _SINGLE_MEDIA_LINK_PATTERN.match(link['href']):
+						# Individual photo or video link
+						continue
 					href = urllib.parse.urljoin(pageUrl, link['href'])
 					if href not in outlinks:
 						outlinks.append(href)