A script to parse a quote tweet chain and reveal all tweets/users.

nestedTweets.py

# Can try it out with this command:
# $ python nestedTweets.py https://twitter.com/aantonop/status/1082420365291388928

import re, requests, sys

def currentTweet(url):
	data = requests.get(url)
	try:
		tweet = re.findall("og:description.*“(.*)”", data.text)[0]
		user = re.findall("og.url.*\/(.*)\/status", data.text)[0]
	except IndexError:
		print("Sorry, invalid tweet url entered. Exiting...")
		sys.exit(1)
	return tweet, user

def getNextTweet(url):
	tweet, user = currentTweet(url)
	try:
	    link = re.findall("https?\S+t.co\S+", tweet)[0]
	    return link, tweet, user
	except IndexError:
	    return "", tweet, user

def getChain(url):
	link = url
	tweet, user = currentTweet(url)
	chain = [(link, user, tweet)]

	link, tweet, user = getNextTweet(url)
	while link:
		print(f"{len(chain)}) @{chain[-1][1]}: {chain[-1][2]}")
		prev_link = link
		link, tweet, user = getNextTweet(link)
		chain.append((prev_link, user, tweet))		
	else:
		print(f"{len(chain)}) @{chain[-1][1]}: {chain[-1][2]}")
		print(f"\nEnd of chain, {len(chain)} tweets deep.")

	return chain

def getChainParticipants(chain):
	return [u for (l,u,t) in chain]

def getFirstTweet(user_input):
	i, tweet_link = 0, []
	url_regex = '(https?://twitter.com/\S*)'
	tweet_link = re.findall(url_regex, user_input)
	
	while not(tweet_link):
		i += 1
		if i > 5:
			print("Sorry too many invalid attempts. Exiting...")
			sys.exit(1)
		user_input = input("Invalidt tweet link, please try again:\n")
		tweet_link = re.findall(url_regex, user_input)

	return tweet_link[0]

if __name__ == "__main__":
	user_input = sys.argv[1]
	tweet_link = getFirstTweet(user_input)
	print("\n----\n\nProcessing:\n")
	chain = getChain(tweet_link)
	print(f"\n----\n\nChain starts at: {chain[-1][0]}\n")
	participants = getChainParticipants(chain)
	print(f"Participants:\n{participants}")

reverseNestedTweets.py

'''
BUILDS A CHAIN FROM THE ROOT INSTEAD OF THE TIP
'''
# Can try it out with this command:
# $ python reverseNestedTweets.py https://twitter.com/matt_odell/status/1083205056407764992

import re, requests
import sys, json

def parseTweet(url):	
	data = requests.get(url)
	# If valid tweet, pulls tweet info
	try:
		tweet = re.findall("og:description.*“(.*)”", data.text)[0]
		user = re.findall("og.url.*\/(.*)\/status", data.text)[0]
	except IndexError:
		print("Sorry, invalid tweet url entered. Exiting...")
		sys.exit(1)	
	# Searches tweet for links present
	try:
	    link = re.findall("https?\S+t.co\S+", tweet)[0]
	    return link, tweet, user
	except IndexError:
	    return "", tweet, user

# Returns a searchable url of the tweet
def linkToSearchable(url):
	urlArray = [i for i in url]
	for i, lett in enumerate(urlArray):
		if lett == ':':
			urlArray[i] = '%3A'
		elif lett == '/':
			urlArray[i] = '%2F'
	return ''.join(urlArray)

# Returns a list of tweets from search for `searchUrl`
def searchTwitter(searchUrl):
	data = requests.get(searchUrl)
	regex_for_results = '"(\S*)\?p=p'
	tweetsFound = re.findall(regex_for_results, data.text)
	tweetPrefix = 'https://twitter.com'
	return [tweetPrefix + id for id in tweetsFound]

# Propagates one chain by returning only the first tweet found.
# Stretch goal could be to explore multiple branches for longest chain.
def buildChain(url):
	allResults = []    # Initialise
	tweetsFound = [url]    # Initialise
	while tweetsFound:
		allResults.append(tweetsFound[0])
		searchUrl = 'https://mobile.twitter.com/search?q=' + linkToSearchable(tweetsFound[0])
		tweetsFound = searchTwitter(searchUrl)
	return allResults

# Validates user input
def validateTweetUrl(user_input):
	i, tweet_link = 0, []
	url_regex = '(https?://twitter.com/\S*)'
	tweet_link = re.findall(url_regex, user_input)	
	while not(tweet_link):
		i += 1
		if i > 5:
			print("Sorry too many invalid attempts. Exiting...")
			sys.exit(1)
		user_input = input("Invalid tweet link, please try again:\n")
		tweet_link = re.findall(url_regex, user_input)
	return tweet_link[0]


if __name__ == "__main__":
	user_input = sys.argv[1]
	tweet_link = validateTweetUrl(user_input)
	print("\n----\n\nProcessing:\n")
	chain = buildChain(tweet_link)	
	print(f"{json.dumps(chain, indent=2)}\n" \
		  f"\nChain is {len(chain)} tweets deep. Build from:\n" \
		  f"{chain[-1]}\n")