update,

jason78989/project/src/discover.py

@@ -0,0 +1,67 @@
+import os,sys
+from twscrape import API, gather
+from twscrape.logger import set_log_level
+from pprint import pprint
+import json
+
+TW_USERNAME = os.getenv('TW_USERNAME')
+TW_PASSWORD = os.getenv('TW_PASSWORD')
+TW_EMAIL = os.getenv('TW_EMAIL')
+TW_EMAIL_PASSWORD = os.getenv('TW_EMAIL_PASSWORD')
+URL_IGNORE_FILE = './url_ignore.txt'
+
+MAX_LENGTH = 50
+
+async def insertAccount():
+  api = API()
+  await api.pool.add_account(TW_USERNAME, TW_PASSWORD, TW_EMAIL, TW_EMAIL_PASSWORD)
+  sys.exit(999)
+
+async def discover(user_login = "LouiscklawLouis"):
+  api = API()
+  await api.pool.login_all()
+  
+  user = await api.user_by_login(user_login)
+  print(user.id)
+
+  user_id = user.id
+  test_list = await gather(api.user_tweets(user_id, limit=5))
+
+  # from pprint import pprint
+  # pprint(test_list)
+  # sys.exit()
+
+  url_list = []
+  
+  for i in range(0, len(test_list)):
+    for j in range(0, len(test_list[i].links)):
+      extracted_url = test_list[i].links[j].url
+      print(f'push into list: {extracted_url}')
+      url_list.append(extracted_url)
+
+  return url_list
+
+def read_url_ignore_list():
+  url_ignore_list = []
+  with open(URL_IGNORE_FILE,'r') as f_url_ignore:
+    url_ignore_list = list(map(lambda x: x.strip(), f_url_ignore.readlines()))
+
+  return url_ignore_list
+
+
+def update_ignore_list(url_to_ignore):
+  print("update url ignore list")
+  
+  url_ignore_list = read_url_ignore_list()
+  print(url_ignore_list)
+
+  with open(URL_IGNORE_FILE,'r+') as f_url_ignore:
+    f_url_ignore.truncate(0)
+    url_ignore_list.append(url_to_ignore)
+    
+    if (len(url_ignore_list )> MAX_LENGTH):
+      url_ignore_list = url_ignore_list[1:MAX_LENGTH]
+    f_url_ignore.writelines("\n".join(url_ignore_list))
+
+def helloworld():
+  print("Helloworld")