Save unique tweets

main.py

@@ -4,7 +4,7 @@
 import numpy as np
 import spacy
 from dotenv import load_dotenv
-from pymongo import MongoClient
+from pymongo import MongoClient, ASCENDING
 from sklearn.feature_extraction.text import TfidfVectorizer
 from art import tprint
 
@@ -73,6 +73,7 @@ def new_database():
     try:
         client = MongoClient(os.environ.get("mongo_uri"))
         db = client.twitter
+        db.tweets.create_index([('id', ASCENDING)], unique=True)
         return db
     except:
         print("Could not connect to MongoDB")
@@ -90,6 +91,7 @@ def get_tweets_from_twitter(client):
 def save_tweets(db, tweets):
     for tweet in tweets:
         tw = {
+            "id": tweet.id,
             "text": tweet.text,
             "user": tweet.user.screen_name,
             "location": tweet.user.location,
@@ -100,7 +102,7 @@ def save_tweets(db, tweets):
             tw_id = db.tweets.insert_one(tw).inserted_id
             print("Tweet inserted with id: ", tw_id)
         except:
-            print("Could not insert tweet")
+            print("Could not insert tweet", tweet.id)
 
 def clean_and_normalize_tweets(db, clean, nlp):
     tweets = db.tweets.find()

requirements.txt

@@ -1,11 +1,51 @@
+ansiwrap==0.8.4
+art==5.7
+blis==0.7.8
+catalogue==2.0.8
 certifi==2022.9.24
 charset-normalizer==2.1.1
+click==8.1.3
+confection==0.0.3
+cymem==2.0.6
 dnspython==2.2.1
+es-core-news-md @ https://github.com/explosion/spacy-models/releases/download/es_core_news_md-3.4.0/es_core_news_md-3.4.0-py3-none-any.whl
 idna==3.4
+Jinja2==3.1.2
+joblib==1.2.0
+langcodes==3.3.0
+MarkupSafe==2.1.1
+murmurhash==1.0.8
+nltk==3.7
+numpy==1.23.3
 oauthlib==3.2.1
+packaging==21.3
+pandas==1.5.0
+pathy==0.6.2
+preshed==3.0.7
+pydantic==1.9.2
 pymongo==4.2.0
+pyparsing==3.0.9
+python-dateutil==2.8.2
 python-dotenv==0.21.0
+pytz==2022.4
+regex==2022.9.13
 requests==2.28.1
 requests-oauthlib==1.3.1
+scikit-learn==1.1.2
+scipy==1.9.2
+six==1.16.0
+sklearn==0.0
+smart-open==5.2.1
+spacy==3.4.1
+spacy-legacy==3.0.10
+spacy-loggers==1.0.3
+srsly==2.4.4
+textwrap3==0.9.2
+thinc==8.1.3
+threadpoolctl==3.1.0
+tqdm==4.64.1
 tweepy==4.10.1
+typer==0.4.2
+typing_extensions==4.4.0
 urllib3==1.26.12
+wasabi==0.10.1