feat(integration): integration is fully finished, will refractor later

webscrape-bank/src/extract.py

@@ -12,7 +12,7 @@ LOGIN_LINK = os.getenv("LOGIN_LINK")
 ACCOUNT_LINK = os.getenv("ACCOUNT_LINK")
 
 def main(playwright: Playwright) -> None:
-    browser = playwright.chromium.launch(headless=False)
+    browser = playwright.chromium.launch(headless=True)
     context = browser.new_context()
 
     page = context.new_page()
@@ -28,10 +28,27 @@ def main(playwright: Playwright) -> None:
     page.get_by_role("button", name="Text").click()
     page.get_by_test_id("text-field").click()
 
-    # Bank prompts 2FA (hopefully only once)
-    two_fac = input("2FA Code: ")
+    # Bank prompts 2FA (hopefully only once) in this meantime
 
-    page.get_by_test_id("text-field").fill(two_fac)
+    two_fac_code = ""
+
+    # Write/Overwrite an empty 2FA file
+    with open("./2fa", "w") as two_fac:
+        two_fac.write("")
+
+    with open("./2fa", "r") as two_fac:
+        line = two_fac.readline()
+        print(line)
+        while line == "":
+            print("2FA code hasn't been entered, make sure to enter code in ./2fa !")
+            print("Retrying in 5 seconds...")
+            sleep(5)
+            line = two_fac.readline()
+
+        two_fac_code = line
+        print("2FA Code Found: " + two_fac_code)
+
+    page.get_by_test_id("text-field").fill(two_fac_code)
     page.get_by_test_id("private-button").click()
 
     # Wait for everything to load...

webscrape-bank/src/main.py

@@ -1,49 +1,87 @@
 from playwright.sync_api import sync_playwright
-from threading import Thread
 import os
 import extract
-#from datetime import datetime
-import difflib
+from datetime import datetime
+from time import sleep
+from multiprocessing import Process
 
 # Playwright in the background
 def playwright():
+    print("Starting Playwright")
     with sync_playwright() as playwright:
         extract.main(playwright)
 
 
 def revise():
-    # Removes the OLDEST file on the list ()
-    file_count = 0
-    for file in os.scandir("./qfx"):
-        print(file_count)
-        if file_count > 1:
-            #print(os.listdir("./qfx"))
-            print("Removed: " + os.listdir("./qfx")[0])
-            os.remove("./qfx/" + os.listdir("./qfx")[0])
+    print("Starting Revision")
+    while (True):
+        with open("./data/output", "w") as output:
+            output.write("")
 
 
-        if file.is_file():
-            file_count += 1
+        # Removes the OLDEST file on the list ()
+        file_count = 0
+        for file in os.scandir("./qfx"):
+            #print(file_count)
+            if file_count > 1:
+                #print(os.listdir("./qfx"))
+                print("Removed: " + os.listdir("./qfx")[0])
+                os.remove("./qfx/" + os.listdir("./qfx")[0])
 
-    # Get the last two files
-    oldest_file = open("./qfx/" + os.listdir("./qfx")[0])
-    newest_file = open("./qfx/" + os.listdir("./qfx")[-1])
 
-    # Differs the two files
-    diff = difflib.ndiff(oldest_file.readlines(), newest_file.readlines())
+            if file.is_file():
+                file_count += 1
+
+        # Thanks to: https://stackoverflow.com/a/33657921
+        # Find the <DTEND> for the newest files
+        # Grabs all starting and ending transaction indexes aswell as the time of the latest transaction
+        start = []
+        end = []
+        latest_trans_time = datetime.now()
+        with open("./qfx/" + os.listdir("./qfx")[-1]) as newest_file:
+            num = 0
+            # Find the number and line under a object that supports iteration
+            for num, line in enumerate(newest_file, 1):
+                if "DTEND" in line:
+                    time_string = line.strip()[7:-8]
+                    
+                    year = int(time_string[0:4])
+                    month = int(time_string[5:6])
+                    day = int(time_string[6:8])
+
+                    latest_trans_time.replace(year, month, day)
+                    num = str(num)
+
+                # TODO: The idea is to find a way to grab all data relating to latest_trans_time WITHIN <STMTTRN>
+                if "<STMTTRN>" in line:
+                    start.append(num-1)
+
+                if "</STMTTRN>" in line:
+                    end.append(num)
+
+        # Seperates all transactions to the latest ones to ./data/output
+        with open("./qfx/" + os.listdir("./qfx")[-1]) as newest_file:
+            lines = newest_file.read().splitlines()
+
+            for i in range(len(start)):
+                ST_BEGINS = start[i]
+                ST_ENDS = end[i]
+                
+                with open("./data/output", "a") as output:
+                    # NOTE: Puts all data from <STMTTRN> to </STMTTRN> into its individual line
+                    output.write("\n".join(lines[ST_BEGINS:ST_ENDS]).replace(" ", "").replace("\t", ""))
+                    output.write("\n")
+
+        # Wait a minute before executing again
+        print("Done with revision!")
+        sleep(60)
 
-    # Grabs only changes
-    # Thanks to: https://stackoverflow.com/a/15864920
-    changes = [l for l in diff if l.startswith("+ ") or l.startswith('- ')]
-    print("RESULT:")
-    for change in changes:
-        print(change[2:])
 
 def main():
-    revise_thread = Thread(target=revise())
-    #pw_thread = Thread(target=playwright())
-    #pw_thread.start()
-    revise_thread.start()
+    pw_proc = Process(target=playwright)
+    pw_proc.start()
+    revise_proc = Process(target=revise)
+    revise_proc.start()
 
 
 if __name__ == "__main__":