FS updates and corrections

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+    "python.linting.flake8Enabled": true,
+    "python.linting.enabled": false
+}

Dockerfile

@@ -2,7 +2,6 @@ FROM python:latest
 
 ENV TZ Euopre/Zurich
 
-
 RUN echo "deb http://deb.debian.org/debian/ unstable main contrib non-free" >> /etc/apt/sources.list
 RUN apt-get update && apt-get install -y \
 evince \

README.md

@@ -49,9 +49,15 @@ I also wrote a rudimentary docker compose file which makes running much more sim
 
 All relevant passthroughs and mounts are specified through the env-file, for which I configured 4 versions: production, debug (development in general), upload and check. These files will have to be adapted to your individual setup but can be reused more easily.
 
-> Note:
+For the debug env-file, you will likely want interactivity, so you need to run:
+
+`docker compose --env-file env/debug run auto_news`
+
+<!-- > Note:
 >
 > The `debug` requires additional input. Once `docker compose up` is running, in a new session run `docker compose --env-file env/debug exec bash`. The live-mounted code is then under `/code`. Note that the `DEBUG=true` environment variable is still set. If you want to test things on production, run `export DEBUG=false`.
+-->
+
 
 
 ## Building

app/configuration.py

@@ -8,7 +8,7 @@ from rich.logging import RichHandler
 logging.basicConfig(
     format='%(message)s',
     level=logging.INFO,
-    datefmt='%Y-%m-%d %H:%M:%S',
+    datefmt='%H:%M:%S', # add %Y-%m-%d if needed
     handlers=[RichHandler()]
     )
 logger = logging.getLogger(__name__)

app/utils_check/runner.py

@@ -158,10 +158,11 @@ def verify_unchecked():
         
         try:
             # close any previously opened windows:
-            subprocess.call("killall evince")
+            subprocess.call(["kill", "`pgrep evince`"])
             # then open a new one
             subprocess.Popen(["evince", f"file://{os.path.join(article.save_path, article.file_name)}"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
             # supress evince gtk warnings
+            print("done")
         except Exception as e:
             print(e)
             continue

app/utils_storage/models.py

@@ -207,7 +207,11 @@ class Thread(ChatBaseModel):
 
     @property
     def initiator_message(self):
+        try:
             return self.messages[0] # TODO check if this needs sorting
+        except IndexError:
+            logger.warning(f"Thread {self} is empty. How can that be?")
+            return None
 
     @property
     def message_count(self):
@@ -222,6 +226,9 @@ class Thread(ChatBaseModel):
     @property
     def is_fully_processed(self) -> bool:
         init_message = self.initiator_message
+        if init_message is None:
+            return False
+        
         if init_message.is_processed_override:
             return True
         # this override is set for instance, when no url was sent at all. Then set this thread to be ignored

app/utils_worker/download/browser.py

@@ -5,13 +5,13 @@ import os
 import base64
 import requests
 from selenium import webdriver
-from selenium.webdriver.firefox.options import Options
 import configuration
 import json
 
 config = configuration.parsed["DOWNLOADS"]
 blacklisted = json.loads(config["blacklisted_href_domains"])
 
+
 class PDFDownloader:
     """Saves a given url. Fills the object it got as a parameter"""
     logger = logging.getLogger(__name__)
@@ -19,10 +19,8 @@ class PDFDownloader:
     running = False
     
     def start(self):
-        try:
-            self.finish()
-        except:
-            self.logger.info("gecko driver not yet running")
+        self.finish() # clear up
+            
         options = webdriver.FirefoxOptions()
         options.profile = config["browser_profile_path"]
         # should be options.set_preference("profile", config["browser_profile_path"]) as of selenium 4 but that doesn't work
@@ -59,10 +57,12 @@ class PDFDownloader:
             self.start()  # relaunch the dl util
 
     def finish(self):
+        if self.running:
             self.logger.info("Exiting gecko driver")
             self.driver.quit()
             self.running = False
-
+        else:
+            self.logger.info("Gecko driver not yet running")
 
     def download(self, article_object):
         sleep_time = 1

docker-compose.yaml

@@ -5,6 +5,7 @@ version: "3.9"
 services:
   auto_news:
     build: .
+    image: auto_news:latest
     volumes:
       - ${CONTAINER_DATA}:/app/file_storage
       - ${HOSTS_FILE}:/etc/hosts
@@ -14,13 +15,17 @@ services:
     network_mode: host
     environment:
       - DISPLAY=$DISPLAY
+      - TERM=xterm-256color # colored logs
+      - COLUMNS=160 # for wider logs
       - DEBUG=${DEBUG}
       - CHECK=${CHECK}
       - UPLOAD=${UPLOAD}
       - HEADLESS=${HEADLESS}
       - REDUCEDFETCH=${REDUCEDFETCH}
+    entrypoint: ${ENTRYPOINT:-python3 runner.py} # by default launch workers as defined in the Dockerfile
+    stdin_open: ${INTERACTIVE:-false} # docker run -i
+    tty: ${INTERACTIVE:-false}        # docker run -t
 
-    entrypoint: ${ENTRYPOINT:-"python3 runner.py"} # by default launch workers as defined in the Dockerfile
 
   # geckodriver:
   #   image: selenium/standalone-firefox:100.0

env/check

@@ -1,7 +1,7 @@
 # Does not run any downloads but displays the previously downloaded but not yet checked files. Requires display-acces via xauth
 
-CONTAINER_DATA=/mnt/Data/COSS/Downloads/auto_news.container
-HOSTS_FILE=/mnt/Data/COSS/Downloads/auto_news.container/dependencies/hosts
+CONTAINER_DATA=~/Bulk/COSS/Downloads/auto_news.container
+HOSTS_FILE=~/Bulk/COSS/Downloads/auto_news.container/dependencies/hosts
 
 XAUTHORTIY=$XAUTHORTIY
 

env/debug

@@ -1,7 +1,7 @@
 # Runs in a debugging mode, does not launch anything at all but starts a bash process
 
-CONTAINER_DATA=/mnt/Data/COSS/Downloads/auto_news.container
-HOSTS_FILE=/mnt/Data/COSS/Downloads/auto_news.container/dependencies/hosts
+CONTAINER_DATA=~/Bulk/COSS/Downloads/auto_news.container
+HOSTS_FILE=~/Bulk/COSS/Downloads/auto_news.container/dependencies/hosts
 
 CODE=./
 XAUTHORTIY=$XAUTHORTIY
@@ -12,4 +12,5 @@ UPLOAD=false
 HEADLESS=false
 REDUCEDFETCH=false
 
-ENTRYPOINT="sleep infinity"
+ENTRYPOINT="/bin/bash"
+INTERACTIVE=true

env/production

@@ -1,7 +1,7 @@
 # Runs on the main slack channel with the full worker setup. If nothing funky has occured, reducedfetch is a speedup
 
-CONTAINER_DATA=/mnt/Data/Downloads/auto_news.container
-HOSTS_FILE=/mnt/Data/COSS/Downloads/auto_news.container/dependencies/hosts
+CONTAINER_DATA=~/Bulk/COSS/Downloads/auto_news.container
+HOSTS_FILE=~/Bulk/COSS/Downloads/auto_news.container/dependencies/hosts
 
 DEBUG=false
 CHECK=false

env/upload

@@ -1,7 +1,7 @@
 # Does not run any other workers and only upploads to archive the urls that weren't previously uploaded
 
-CONTAINER_DATA=/mnt/Data/COSS/Downloads/auto_news.container
-HOSTS_FILE=/mnt/Data/COSS/Downloads/auto_news.container/dependencies/hosts
+CONTAINER_DATA=~/Bulk/COSS/Downloads/auto_news.container
+HOSTS_FILE=~/Bulk/COSS/Downloads/auto_news.container/dependencies/hosts
 
 
 DEBUG=false

misc/gather_media_files.py

@@ -1,5 +1,3 @@
-from cmath import log
-from concurrent.futures import thread
 import sys
 sys.path.append("../app")
 import runner
@@ -8,14 +6,15 @@ logger = logging.getLogger()
 import json
 
 
-
-logger.info("Overwriting production values for single use media-fetch")
+logger.info("Overwriting production values for single time media-fetch")
 runner.configuration.models.set_db(
-    runner.configuration.SqliteDatabase("media_message_dummy.db"), # chat_db (not needed here)
-    runner.configuration.SqliteDatabase("media_downloads.db")
+    runner.configuration.SqliteDatabase("../.dev/media_message_dummy.db"),  # chat_db (not needed here)
+    runner.configuration.SqliteDatabase("../.dev/media_downloads.db")
 )
-runner.configuration.parsed["DOWNLOADS"]["local_storage_path"] = "."
+runner.configuration.parsed["DOWNLOADS"]["local_storage_path"] = "../.dev/"
 
+
+def fetch():
     coordinator = runner.Coordinator()
 
 
@@ -38,3 +37,16 @@ for u in url_list:
         dummy_thread = runner.models.Thread()
         msg = runner.models.Message(text= msg_text, thread=dummy_thread)
         coordinator.incoming_request(msg)
+
+
+def show():
+    sel = runner.models.ArticleDownload.select()
+    entries = ["title"]  #, "article_url", "archive_url"]
+
+    for e in entries:
+        r = [t.title for t in sel]
+        print(r)
+        # print([t for t in r])
+
+
+show()