code finishup and cleanup

+ yaml composing ejabberd conformal
+ added README.md
+ added .gitignore
+ added requirements.txt

4 files changed, 195 insertions, 36 deletions

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..b934845
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,124 @@
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+### Python Patch ###
+.venv/
+.idea/
+
+### project specific ###
+blacklist.txt
+.etag
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..2d2ff33
--- /dev/null
+++ b/README.md
@@ -0,0 +1,31 @@
+## Blacklist import script
+
+### ejabberd config
+To use this script properly, a separate `yml` file is necessary, as the script will overwrite the file. To further 
+protect the config the `allow_only` sections defines only `acl` rules.
+```yaml
+  "/etc/ejabberd/blacklist.yml":
+    allow_only:
+      - acl
+```
+
+### script configuration
+
+The script is meant to be used in an automatic fashion.
+Arguments:
+
+- -dr , --dry-run : perform a dry run. `blacklist.txt` and `.etag` are written but no yaml file is overwritten.
+- -o , --outfile filepath : set path to output file
+
+The dry-run argument will output the file path, if set, in addition to the contents of the yaml file which would have be produced.
+
+### script workflow
+1. check if `.etag` file is present
+2. HEAD request
+	2.1 requests etag and `.etag` are equal
+	​	2.1.1 use local `blacklist.txt` file
+	2.2 requests etag and `.etag` are _not_ equal
+	​	2.2.1 request new `blacklist.txt`
+	​	2.2.2 save new `.etag` and `blacklist.txt` file
+3. process `blacklist.txt` and parse output file
+
diff --git a/main.py b/main.py
index 6608a85..949a80b 100644
--- a/main.py
+++ b/main.py
@@ -2,27 +2,28 @@
 # -*- coding: utf-8 -*-
 
 # workflow
-# start options main.py --ejabberd/prosody --dry-run --outfile file
+# start options main.py --dry-run --outfile file
 
 import requests
-import sys
 import os
+import sys
 import argparse
 import yaml
+from ruamel.yaml import YAML, scalarstring
 
 
 class BlacklistImporter:
 	def __init__(self, args):
-		self.server = args.software
 		self.outfile = args.outfile
 		self.dryrun = args.dryrun
 		self.url = "https://raw.githubusercontent.com/JabberSPAM/blacklist/master/blacklist.txt"
 		self.blacklist = None
+		self.change = False
 
 	def request(self):
 		# check if etag header is present if not set local_etag to ""
 		if os.path.isfile(".etag"):
-			with open(".etag") as file:
+			with open(".etag", "r") as file:
 				local_etag = file.read()
 		else:
 			local_etag = ""
@@ -32,24 +33,22 @@ class BlacklistImporter:
 			head = s.head(self.url)
 			etag = head.headers['etag']
 
-			# compare etag with local_etag if they match up no request is made
-			if local_etag == etag:
-				with open("blacklist.txt", "r") as file:
-					self.blacklist = file.readline()
-
-			# if the connection is not possible use cached xml if present
-			elif os.path.isfile("blacklist.txt") and head.status_code != 200:
-				with open("blacklist.txt", "r") as file:
-					self.blacklist = file.readline()
+			# if file is present
+			if os.path.isfile("blacklist.txt"):
+				# if etags match up or if a connection is not possible fall back to local cache
+				if local_etag == etag or head.status_code != 200:
+					with open("blacklist.txt", "r", encoding="utf-8") as file:
+						self.blacklist = file.readline()
 
 			# in any other case request a new file
 			else:
 				r = s.get(self.url)
 				r.encoding = 'utf-8'
 				local_etag = head.headers['etag']
+				self.blacklist = r.content.decode()
 
 				with open("blacklist.txt", "w") as file:
-					file.write(r.content.decode())
+					file.write(self.blacklist)
 
 				with open('.etag', 'w') as string:
 					string.write(local_etag)
@@ -60,23 +59,23 @@ class BlacklistImporter:
 
 		if self.dryrun:
 			# only output the selected software and outfile
-			print("server software selected: %s" % self.server)
 			print("outfile selected: %s" % self.outfile)
 
-		if self.server == "ejabberd":
-			# select ejabberd processing
-			self.ejabberd()
+		# select ejabberd processing
+		self.process()
 
-		elif self.server == "prosody":
-			# select prosody processing
-			self.prosody()
-		else:
-			# in any other case exit
-			sys.exit(3)
+		# reload config if changes have been applied
+		if self.change:
+			os.system("ejabberdctl reload_config")
 
-	def ejabberd(self):
+	def process(self):
 		# check if file was altered
-		local_file = yaml.load(open(self.outfile, "r"))
+		local_file = None
+		try:
+			if os.path.isfile(self.outfile):
+				local_file = yaml.load(open(self.outfile, "r", encoding="utf-8"))
+		except TypeError:
+			pass
 
 		remote_file = {
 			"acl": {
@@ -87,26 +86,28 @@ class BlacklistImporter:
 		}
 
 		for entry in self.blacklist.split():
+			entry = scalarstring.DoubleQuotedScalarString(entry)
 			remote_file["acl"]["spamblacklist"]["server"].append(entry)
 
+		yml = YAML()
+		yml.indent(offset=2)
+		yml.default_flow_style = False
+
 		if self.dryrun:
-			print(yaml.dump(remote_file))
+			# if dryrun true print expected content
+			yml.dump(remote_file, sys.stdout)
 
 		elif local_file != remote_file:
-			yaml.dump(remote_file, open(self.outfile, "w"))
-
-	def prosody(self):
-		pass
+			self.change = True
+			# only if the local_file and remote_file are different write new file
+			yml.dump(remote_file, open(self.outfile, "w"))
 
 
 if __name__ == "__main__":
 	parser = argparse.ArgumentParser()
-	parser.add_argument('-e', '--ejabberd', help='set server software to ejabberd', action='store_const', dest='software',
-						const="ejabberd", default=None)
-	parser.add_argument('-p', '--prosody', help='set server software to prosody', action='store_const', dest='software',
-						const="prosody", default=None)
 	parser.add_argument('-o', '--outfile', help='set path to output file', dest='outfile', default=None)
-	parser.add_argument('--dry-run', help='perform only a dry run', action='store_true', dest='dryrun', default=False)
+	parser.add_argument('-dr', '--dry-run', help='perform a dry run', action='store_true', dest='dryrun', default=False)
 	args = parser.parse_args()
 
+	# run
 	BlacklistImporter(args).main()
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..6d82745
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,3 @@
+PyYAML>=3.1.3
+ruamel.yaml>=0.15.80
+requests>=2.21.0