draft: wip newsfeed mailer

examples/newsfeed-mailer/check-newsfeed.py

@@ -17,7 +17,12 @@
 
 If all arguments were provided correctly, this script will:
 
-[...]
+1. Scrapes newsfeed data from Matricula's website.
+`--schedule` in hours determines the last n days to fetch (e.g. 24: 48/24=2 => last 2 days will be fetched).
+
+2. It will look for substrings of `keywords` in the headlines and previews of the scraped articles.
+
+3. If matches were found, a mail will be sent to the user with the matches.
 
 EXAMPLE
 =======
@@ -45,18 +50,20 @@
 
 # -------------------- logging --------------------
 
-
 JOB_ID = uuid.uuid4()
 JOB_DATE = datetime.now()
-LOG_FILE = Path("matricula-newsfeed-mailer.log")
+APP_DIR = Path("~/.matricula-online-scraper/").expanduser().absolute()
+LOG_FILE = Path(APP_DIR, "matricula-newsfeed-mailer.log")
 
 logger = logging.getLogger(__name__)
 logger_extra = {
     "job_id": JOB_ID,
     "bot_version": VERSION,
 }
 logging.basicConfig(
-    filename=LOG_FILE,
+    handlers=[
+        logging.FileHandler(LOG_FILE),
+    ],
     encoding="utf-8",
     level=logging.DEBUG,
     format="[%(asctime)s] %(levelname)s (%(job_id)s @ v%(bot_version)s) : %(message)s",
@@ -214,7 +221,7 @@ def parse_args() -> Options:
 # -------------------- Data processing / CSV parsing --------------------
 
 # folder where scraped data is stored
-DATA_STORE = Path("~/matricula-newsfeed-scraper").expanduser()
+DATA_STORE = Path(APP_DIR, "scraper-data")
 
 
 def fetch_newsfeed(*, last_n_days: int) -> Path:
@@ -437,6 +444,10 @@ def send_mail(
         f"Found {len(matches)} matches for keywords {keywords} in: {file.absolute()}"
     )
 
+    if len(matches) == 0:
+        logger.debug("No matches found. Aborting.")
+        exit(0)
+
     # build message
     # history = History(LOG_FILE)
     subject = Subject(num_matches=len(matches))

examples/newsfeed-mailer/install-cronjob.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# ! ATTENTION !
+# =============
+#
+# This file automatically adds a cron job to the user's crontab.
+#
+# Please fill in the following variables with your data.
+#
+
+# email, e.g. your@email.com
+FROM=
+# your email's password
+PASSWORD=
+# to whom the email should be sent, to@me.com
+TO=
+# smtp server, e.g. smtp.gmail.com
+SMTP_SERVER=
+# smtp port, e.g. 465
+SMTP_PORT=
+# space separated keywords, e.g. "keyword1 keyword2"
+KEYWORDS=
+# int, e.g. 24 (it will look for news every 24 hours)
+SCHEDULE=
+# cron schedule, e.g. "0 16 * * *" (every day at 16:00)
+CRON=
+
+# -------------------------------------------- #
+# END OF USER VARIABLES | DO NOT CHANGE BELOW  #
+# -------------------------------------------- #
+
+# check variables are set
+if [ -z "$FROM" ] || [ -z "$PASSWORD" ] || [ -z "$TO" ] || [ -z "$SMTP_SERVER" ] || [ -z "$SMTP_PORT" ] || [ -z "$KEYWORDS" ] || [ -z "$SCHEDULE" ] || [ -z "$CRON" ]; then
+    echo "Error: Please fill in the variables in the script."
+    exit 1
+fi
+
+# check execution path is correct
+SCRIPT_PATH="$PWD/check-newsfeed.py"
+if [ ! -f "$SCRIPT_PATH" ]; then
+    echo "Error: Script not found at $SCRIPT_PATH"
+    exit 1
+fi
+
+CMD="$SCRIPT_PATH --from $FROM --password $PASSWORD --smtp-server $SMTP_SERVER -p $SMTP_PORT --to $TO --schedule $SCHEDULE -k $KEYWORDS"
+CRONJOB="$CRON $CMD"
+COMMENT="# cronjob for https://github.com/lsg551/matricula-online-scraper/tree/main/examples/newsfeed-mailer"
+COMMENT2="# see $SCRIPT_PATH for more details"
+
+# add cronjob to user's crontab
+TMP_FILE="user_crontab_l"
+crontab -l > $TMP_FILE
+echo "$COMMENT" >> $TMP_FILE
+echo "$COMMENT2" >> $TMP_FILE
+echo "$CRONJOB" >> $TMP_FILE
+crontab $TMP_FILE
+rm $TMP_FILE
+
+echo "Cronjob added successfully: $CRONJOB"