From 0168d50f62df65ad829384986a07fb89c7ea9b3a Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Tue, 2 Apr 2019 14:25:43 +0000 Subject: [PATCH] Automatically fix capitalisation of Facebook and Twitter usernames --- facebook-user-capitalisation | 2 -- snscrape-facebook-user | 14 +++++++++++++- snscrape-twitter-user | 11 ++++++++++- 3 files changed, 23 insertions(+), 4 deletions(-) delete mode 100755 facebook-user-capitalisation diff --git a/facebook-user-capitalisation b/facebook-user-capitalisation deleted file mode 100755 index fa66648..0000000 --- a/facebook-user-capitalisation +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -curl -s "https://www.facebook.com/${1}/" | grep -Po ' ${user}" >&2; fi + { + echo "https://www.facebook.com/${user}/" + snscrape -v facebook-user "${user}" | \ + perl -pe 's,[?&]\K__xts__%5B0%5D=[^&]+?(&|$),,; s,[?&]\K__tn__=[^&]+?(&|$),,; s,[?&]\Keid=[^&]+?(&|$),,; s,[?&]$,,;' | \ + awk '{print} /\?type=/ {print substr($0, 1, index($0, "?type=") - 1)}' | \ + awk '!seen[$0]++' + } > "facebook-@${user}" +fi diff --git a/snscrape-twitter-user b/snscrape-twitter-user index a822644..321f988 100755 --- a/snscrape-twitter-user +++ b/snscrape-twitter-user @@ -1,2 +1,11 @@ #!/bin/bash -user="$1"; { echo "https://twitter.com/${user}"; snscrape -v twitter-user "${user}"; } > "twitter-@${user}" +origUser="$1" +user="$(snscrape --max-results 1 twitter-user "${origUser}" | grep -Po '^https?://twitter\.com/\K[^/]+')" +if [[ "${user}" ]] +then + if [[ "${user}" != "${origUser}" ]]; then echo "Username fix: ${origUser} -> ${user}" >&2; fi + { + echo "https://twitter.com/${user}" + snscrape -v twitter-user "${user}" + } > "twitter-@${user}" +fi