From af806c4f16fa72237a2215ecab7b739a6de824c4 Mon Sep 17 00:00:00 2001
From: Stefano Assenzo <stef58a@gmail.com>
Date: Thu, 5 Jan 2023 11:40:54 +0000
Subject: [PATCH] Now it works correctly, I just have to rename the file it
 downloads and I'm done

---
 .env.example                                 |  3 +-
 src/events/school_time/email_read.py         | 31 ++++++++++++++
 src/events/school_time/scraping_excelfile.py | 45 --------------------
 3 files changed, 32 insertions(+), 47 deletions(-)
 create mode 100644 src/events/school_time/email_read.py
 delete mode 100644 src/events/school_time/scraping_excelfile.py

diff --git a/.env.example b/.env.example
index da77629..854727a 100644
--- a/.env.example
+++ b/.env.example
@@ -5,5 +5,4 @@ EMAIL = "
 SMTP_SERVER = ""
 SMTP_PORT = ""
 EMAIL_SCHOOL = ""
-LINK_SCHOOL_TIME = ""
-FILE_DIRECTORY_SCHOOL = ""
\ No newline at end of file
+DOWNLOAD_FOLDER = ""
\ No newline at end of file
diff --git a/src/events/school_time/email_read.py b/src/events/school_time/email_read.py
new file mode 100644
index 0000000..4a30788
--- /dev/null
+++ b/src/events/school_time/email_read.py
@@ -0,0 +1,31 @@
+import os
+from imbox import Imbox
+import traceback
+
+
+host = os.getenv('SMTP_SERVER')
+username = os.getenv('EMAIL')
+password = os.getenv('PWD_EMAIL')
+download_folder = os.getenv('DOWNLOAD_FOLDER')
+EMAIL_SCHOOL = os.getenv('EMAIL_SCHOOL')
+
+if not os.path.isdir(download_folder):
+    os.makedirs(download_folder, exist_ok=True)
+    
+mail = Imbox(host, username=username, password=password, ssl=True, ssl_context=None, starttls=False)
+messages = mail.messages(sent_from=EMAIL_SCHOOL)
+
+for (uid, message) in messages:
+    mail.mark_seen(uid) # optional, mark message as read
+
+    for idx, attachment in enumerate(message.attachments):
+        try:
+            att_fn = attachment.get('filename')
+            download_path = f"{download_folder}/{att_fn}"
+            print(download_path)
+            with open(download_path, "wb") as fp:
+                fp.write(attachment.get('content').read())
+        except:
+            print(traceback.print_exc())
+
+mail.logout()
\ No newline at end of file
diff --git a/src/events/school_time/scraping_excelfile.py b/src/events/school_time/scraping_excelfile.py
deleted file mode 100644
index 6ec2680..0000000
--- a/src/events/school_time/scraping_excelfile.py
+++ /dev/null
@@ -1,45 +0,0 @@
-import subprocess
-import os
-import tabula
-from dotenv import load_dotenv
-from selenium import webdriver
-from selenium.webdriver.firefox.options import Options
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-
-load_dotenv()
-LINK_SCHOOL_TIME = os.getenv('LINK_SCHOOL_TIME')
-FILE_DIRECTORY_SCHOOL = os.getenv('FILE_DIRECTORY_SCHOOL')
-options = Options()
-options.add_argument("--headless")
-options.add_argument('--disable-gpu')
-options.add_argument('--disable-software-rasterizer')
-
-driver = webdriver.Firefox(options=options)
-#url launch
-driver.get(LINK_SCHOOL_TIME)
-#identify link with partial link text
-
-elems = driver.find_elements(By.XPATH, "/html/body/section[2]/div/div/main/div/div/div/div/div[2]/p[2]/a")
-
-for elem in elems:
-    link = elem.get_attribute("href")
-
-remove_things_in_front = link.split(FILE_DIRECTORY_SCHOOL, 1)[1]
-print(remove_things_in_front)
-subprocess.run(["wget", link])
-
-driver.close()
-
-namefile = remove_things_in_front
-df = tabula.read_pdf(namefile, pages = 'all')[0]
-tabula.convert_into(namefile, "test.csv", output_format="csv", pages='all')
-print(df)
-
-from pyexcel.cookbook import merge_all_to_a_book
-# import pyexcel.ext.xlsx # no longer required if you use pyexcel >= 0.2.2 
-import glob
-
-
-merge_all_to_a_book(glob.glob("*.csv"), "school_time.xlsx")
\ No newline at end of file