Last active
December 15, 2015 10:29
-
-
Save csinchok/5246201 to your computer and use it in GitHub Desktop.
Trying to find the "unique" tweets for a URL.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import sys | |
import pprint | |
import re | |
from difflib import SequenceMatcher | |
from requests_oauthlib import OAuth1 | |
def clean_tweet(text): | |
return " ".join(re.sub(r"http://t.co/\w+", "", text).split()) | |
if len(sys.argv) != 2: | |
raise Exception("You need to provide a parameter") | |
oauth = OAuth1( | |
"CONSUMER_KEY", | |
client_secret="CONSUMER_SECRET", | |
resource_owner_key="ACCESS_TOKE", | |
resource_owner_secret="ACCESS_SECRET") | |
search_endpoint = "https://api.twitter.com/1.1/search/tweets.json" | |
url = sys.argv[1] | |
params = {'q': url, 'count': 100, 'result_type': 'recent', 'include_entities': 0} | |
response = requests.get(url=search_endpoint, params=params, auth=oauth) | |
unique_tweets = [] | |
for x in xrange(2): | |
for status in response.json()['statuses']: | |
clean_text = clean_tweet(status['text']) | |
for match in unique_tweets: | |
seq = SequenceMatcher(None, match['text'], clean_text) | |
if seq.ratio() > 0.8: | |
match['tweets'].append(clean_text) | |
min_seq = SequenceMatcher(None, clean_text, match['min']) | |
blocks = min_seq.get_matching_blocks()[:-1] | |
match['min'] = "".join([clean_text[block[0]:block[0]+block[2]] for block in blocks]) | |
break | |
else: | |
unique_tweets.append({ | |
'text': clean_text, | |
'tweets': [], | |
'min': clean_text | |
}) | |
next_results = response.json()['search_metadata'].get('next_results') | |
if next_results: | |
response = requests.get(url=search_endpoint + next_results, auth=oauth) | |
else: | |
break | |
for match in unique_tweets: | |
printed_min = match['min'].strip() | |
if len(printed_min) > 0: | |
print(match['min']) | |
else: | |
continue | |
additions = [] | |
for tweet in match['tweets']: | |
seq = SequenceMatcher(None, printed_min, tweet) | |
addition = "" | |
for opcode in seq.get_opcodes(): | |
if opcode[0] == 'insert': | |
addition += tweet[opcode[3]:opcode[4]] | |
if addition not in additions: | |
additions.append(addition) | |
for addition in additions: | |
if len(addition) > 0: | |
print(" + %s" % addition) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment