From eda17f2ad01d3f41eaf837d86463d5f1218d31ac Mon Sep 17 00:00:00 2001
From: Hykilpikonna <me@hydev.org>
Date: Wed, 24 Nov 2021 10:58:15 -0500
Subject: [PATCH] [M] Move constants to constants.py

---
 src/constants.py               |  6 ++++++
 src/main.py                    | 17 ++++++++---------
 src/process/twitter_process.py |  2 +-
 src/raw_collect/twitter.py     |  2 +-
 4 files changed, 16 insertions(+), 11 deletions(-)
 create mode 100644 src/constants.py

diff --git a/src/constants.py b/src/constants.py
new file mode 100644
index 0000000..d3b2669
--- /dev/null
+++ b/src/constants.py
@@ -0,0 +1,6 @@
+# Constants (The instructors said that we can use global constants here:
+# https://piazza.com/class/ksovzjrlsye72f?cid=1664
+# They should not end with "/"
+DATA_DIR = './data'
+TWEETS_DIR = f'{DATA_DIR}/twitter/user-tweets'
+USER_DIR = f'{DATA_DIR}/twitter/user'
diff --git a/src/main.py b/src/main.py
index d8c8a0e..17580da 100644
--- a/src/main.py
+++ b/src/main.py
@@ -4,13 +4,6 @@ from process.twitter_process import *
 from raw_collect.twitter import *
 from utils import *
 
-# Constants (The instructors said that we can use global constants here:
-# https://piazza.com/class/ksovzjrlsye72f?cid=1664
-# They should not end with "/"
-DATA_DIR = './data'
-TWEETS_DIR = f'{DATA_DIR}/twitter/user-tweets'
-USER_DIR = f'{DATA_DIR}/twitter/user'
-
 
 if __name__ == '__main__':
     # Load config and create API
@@ -18,7 +11,7 @@ if __name__ == '__main__':
     api = tweepy_login(conf)
 
     #####################
-    # Data collection - Step C1
+    # Data collection - Step C1.1
     # Download a wide range of users from Twitter using follow-chaining starting from a single user.
     # download_users_start(api, 'voxdotcom')
 
@@ -26,6 +19,11 @@ if __name__ == '__main__':
     # you want to stop the process, you can resume it later using the following line:
     # download_users_resume_progress(api)
 
+    ####################
+    # Data collection - Step C1.2
+    # Download all tweets from twitternews
+    download_all_tweets(api, 'twitternews')
+
     #####################
     # Data processing - Step P1
     # (After step C1) Process the downloaded twitter users, extract screen name, popularity, and
@@ -35,7 +33,7 @@ if __name__ == '__main__':
     #####################
     # Data processing - Step P2
     # (After step P1) Select 500 most popular users and 500 random users who meet a particular
-    # criteria as our sample.
+    # criteria as our sample, also find news channels
     # select_user_sample()
 
     # Just curious, who are the 20 most popular individuals on twitter?
@@ -66,6 +64,7 @@ if __name__ == '__main__':
 
     # Who posted the most covid tweets? (covid vs non-covid ratio)
     # - Graph histogram of this ratio
+
     # Who has the most covid tweet popularity (popularity of covid vs non-covid tweets ratio)
     # - Graph histogram of this ratio
 
diff --git a/src/process/twitter_process.py b/src/process/twitter_process.py
index c9064de..636b5b7 100644
--- a/src/process/twitter_process.py
+++ b/src/process/twitter_process.py
@@ -7,7 +7,7 @@ from dataclasses import dataclass
 
 from py7zr import SevenZipFile
 
-from main import DATA_DIR, TWEETS_DIR, USER_DIR
+from constants import DATA_DIR, TWEETS_DIR, USER_DIR
 from utils import *
 
 
diff --git a/src/raw_collect/twitter.py b/src/raw_collect/twitter.py
index 40aeda5..a982cee 100644
--- a/src/raw_collect/twitter.py
+++ b/src/raw_collect/twitter.py
@@ -9,7 +9,7 @@ from typing import List
 import tweepy
 from tweepy import API, TooManyRequests, User, Tweet, Unauthorized
 
-from main import TWEETS_DIR, USER_DIR
+from constants import TWEETS_DIR, USER_DIR
 from utils import *