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 [[ "${url}" =~ ^https?://((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com/([^/]+/?(\?|$)|pages/[^/]+/[0-9]+/?(\?|$)|profile\.php\?id=[0-9]+(&|$)) ]]
	then
		if [[ "${url}" == *profile.php* ]]
		then
			url="${url%%&*}"
		else
			url="${url%%\?*}"
		fi
		page="$(curl -sL -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.facebook.com/${url#*facebook.com/}")"
		user="$(grep -Po '<div\s[^>]*(?<=\s)data-key\s*=\s*"tab_home".*?</div>' <<< "${page}" | grep -Po '<a\s[^>]*(?<=\s)href="/\K[^/]+')"
		if [[ "${user}" ]]
		then
			echo "https://www.facebook.com/${user}/"
			continue
		else
			if grep -q 'id="pagelet_loggedout_sign_up"' <<< "${page}"
			then
				# Profile page which is only visible when logged in
				# Extract canonical URL
				user="$(grep -Po '<link rel="canonical" href="\K[^"]+' <<< "${page}")"
				if [[ "${user}" ]]
				then
					echo "${user}"
					continue
				fi
			fi
		fi
		errorUrls+=("${url}")
		echo "${url}"
	elif [[ "${url}" =~ ^https?://(www\.)?twitter\.com/[^/]+/?(\?.*)?$ ]]
	then
		url="${url%%\?*}"
		url="${url%/}"
		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
		user="${url%/}"
		user="${user##*/}"
		echo "https://www.instagram.com/${user,,}/"
	else
		echo "${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