From 916fcf1bab87dbb78c2658adf8ac2b7276829fc5 Mon Sep 17 00:00:00 2001
From: Vladan Popovic <vladanovic@gmail.com>
Date: Fri, 4 Sep 2020 19:45:18 +0200
Subject: [PATCH] Add logging

---
 config.yaml            | 19 ++++++++++++++++++-
 src/chweb/cmd.py       | 17 +++++++++++++----
 src/chweb/collector.py |  9 ++++++++-
 3 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/config.yaml b/config.yaml
index 6ba901c..6ceffae 100644
--- a/config.yaml
+++ b/config.yaml
@@ -9,7 +9,7 @@ postgres:
   dbuser: "vladan"
   dbpass: ""
 sites:
-- url: "https://example.com"
+- url: "https://dsadakjhkjsahkjh.com"
   regex: "domain"
   check_interval: 5
 - url: "https://example.com"
@@ -17,3 +17,20 @@ sites:
   check_interval: 8
 - url: "https://example.com/404"
   check_interval: 13
+logging:
+  version: 1
+  formatters:
+    standard:
+      format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+    error:
+      format: "%(levelname)s <PID %(process)d:%(processName)s> %(name)s.%(funcName)s(): %(message)s"
+  handlers:
+    console:
+      class: logging.StreamHandler
+      level: DEBUG
+      formatter: standard
+      stream: ext://sys.stdout
+  root:
+    level: DEBUG
+    handlers: [console]
+    propogate: yes
diff --git a/src/chweb/cmd.py b/src/chweb/cmd.py
index 7336e6b..ac470e5 100644
--- a/src/chweb/cmd.py
+++ b/src/chweb/cmd.py
@@ -3,6 +3,10 @@ A module containing all console script functions.
 """
 import argparse
 import asyncio
+import logging
+import logging.config
+from logging import Logger
+from typing import Tuple
 import yaml
 
 from chweb.collector import Collector
@@ -10,7 +14,7 @@ from chweb.consumer import Consumer
 from chweb.models import Config
 
 
-def configure() -> Config:
+def configure(name) -> Tuple[Config, Logger]:
     """
     Gets the configuration and creates a Pydantic model from the parsed YAML.
     """
@@ -23,7 +27,9 @@ def configure() -> Config:
     args = parser.parse_args()
     with open(args.config, 'r') as conf_file:
         config = yaml.load(conf_file, Loader=yaml.FullLoader)
-        return Config(**config)
+        logging.config.dictConfig(config['logging'])
+        logger = logging.getLogger("chweb.{}".format(name))
+        return (Config(**config), logger)
 
 
 def run(Service):
@@ -32,8 +38,11 @@ def run(Service):
     """
     loop = asyncio.get_event_loop()
     queue = asyncio.Queue()
-    config = configure()
-    service = Service(config, loop, queue)
+    config, logger = configure(Service.__name__)
+    logger.info(("Starting service on kafka [cluster]/topic: "
+                 "{}/{}").format(config.kafka.servers,
+                                 config.kafka.topic))
+    service = Service(config, logger, loop, queue)
     service.run()
 
 
diff --git a/src/chweb/collector.py b/src/chweb/collector.py
index dc8f022..dcec68f 100644
--- a/src/chweb/collector.py
+++ b/src/chweb/collector.py
@@ -56,7 +56,12 @@ class Collector:
         :param site: A site object from the config.
         """
         while True:
-            data = await self.check(site.url, site.regex)
+            try:
+                data = await self.check(site.url, site.regex)
+            except Exception as exc:
+                errmsg = "{}; {}".format(site.url, exc)
+                self.logger.error(errmsg)
+                break #  Break the loop and destroy the Task.
             self.queue.put_nowait(data)
             await asyncio.sleep(site.check_interval)
 
@@ -77,6 +82,7 @@ class Collector:
                 msg = bytes(check.json().encode("utf-8"))
                 await producer.send_and_wait(self.config.kafka.topic, msg)
         finally:
+            self.logger.warning("Kafka producer destroyed!")
             await producer.stop()
 
     def run(self):
@@ -88,3 +94,4 @@ class Collector:
         tasks = list(map(create_task, self.config.sites))
         tasks.append(self.loop.create_task(self.produce()))
         self.loop.run_until_complete(asyncio.gather(*tasks))
+        self.logger.info("Checker stopped ...")