From 72818019bca249d22ab55461507a9c279a369566 Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Thu, 16 May 2019 22:54:45 +0000 Subject: [PATCH] Extract external links from Twitter --- snscrape-twitter-hashtag | 2 +- snscrape-twitter-user | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/snscrape-twitter-hashtag b/snscrape-twitter-hashtag index 0abb7fa..2869dff 100755 --- a/snscrape-twitter-hashtag +++ b/snscrape-twitter-hashtag @@ -6,5 +6,5 @@ shift echo "https://twitter.com/hashtag/${hashtag}?src=hash" echo "https://twitter.com/hashtag/${hashtag}?f=tweets&vertical=default" echo "https://twitter.com/hashtag/${hashtag}?f=tweets&vertical=default&src=hash" - snscrape "$@" twitter-hashtag "${hashtag}" + snscrape --format '{url} {tcooutlinksss} {outlinksss}' "$@" twitter-hashtag "${hashtag}" | tr ' ' '\n' | grep -v '^$' | awk '!seen[$0]++' } > "twitter-#${hashtag}" diff --git a/snscrape-twitter-user b/snscrape-twitter-user index de86688..9134076 100755 --- a/snscrape-twitter-user +++ b/snscrape-twitter-user @@ -7,6 +7,6 @@ then if [[ "${user}" != "${origUser}" ]]; then echo "Username fix: ${origUser} -> ${user}" >&2; fi { echo "https://twitter.com/${user}" - snscrape "$@" twitter-user "${user}" - } > "twitter-@${user}" + snscrape --format '{url} {tcooutlinksss} {outlinksss}' "$@" twitter-user "${user}" + } | tr ' ' '\n' | grep -v '^$' | awk '!seen[$0]++' > "twitter-@${user}" fi