little-things/snscrape-normalise

#!/bin/bash
# Read a list of URLs from stdin, replace suitable social media URLs with correctly capitalised version
errorUrls=()
while read -r url
do
	if [[ "${url}" =~ ^https?://(www|m|[a-z][a-z]-[a-z][a-z]).facebook.com/[^/]+/?$ ]]
	then
		user="$(curl -s -A 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36' -H 'Accept-Language: en-US,en;q=0.5' "https://www.${url#*.}" | grep -Po '<div\s[^>]*(?<=\s)data-key\s*=\s*"tab_home".*?</div>' | grep -Po '<a\s[^>]*(?<=\s)href="/\K[^/]+')"
		if [[ "${user}" ]]
		then
			echo "https://www.facebook.com/${user}/"
		else
			errorUrls+=("${url}")
			echo "${url}"
		fi
	elif [[ "${url}" =~ ^https?://twitter\.com/[^/]+$ ]]
	then
		user="$(snscrape --max-results 1 twitter-user "${url##*/}" | grep -Po '^https?://twitter\.com/\K[^/]+')"
		if [[ "${user}" ]]
		then
			echo "https://twitter.com/${user}"
		else
			errorUrls+=("${url}")
			echo "${url}"
		fi
	elif [[ "${url}" =~ ^https?://www\.instagram\.com/[^/]+/$ ]]
	then
		echo "${url,,}"
	else
		echo "${url}"
	fi
done

if [[ ${#errorUrls[@]} -gt 0 ]]
then
	echo "" >&2
	echo "Failed to process URLs:" >&2
	for errorUrl in "${errorUrls[@]}"
	do
		echo "${errorUrl}" >&2
	done
fi