Refactoring work to make this a real program

.idea/misc.xml

@@ -13,23 +13,7 @@
     <ConfirmationsSetting value="0" id="Add" />
     <ConfirmationsSetting value="0" id="Remove" />
   </component>
-  <component name="ProjectRootManager" version="2" languageLevel="JDK_1_6" default="true" assert-keyword="true" jdk-15="true" project-jdk-name="Python 3.5.1 (C:\Users\Bradlee Speice\Anaconda3\python.exe)" project-jdk-type="Python SDK">
+  <component name="ProjectRootManager" version="2" languageLevel="JDK_1_6" default="false" assert-keyword="true" jdk-15="true" project-jdk-name="Python 3.5.1 (C:\Users\Bradlee Speice\Anaconda3\python.exe)" project-jdk-type="Python SDK">
     <output url="file://$PROJECT_DIR$/out" />
   </component>
-  <component name="masterDetails">
-    <states>
-      <state key="ProjectJDKs.UI">
-        <settings>
-          <last-edited>Python 3.5.1 (C:\Users\Bradlee Speice\Anaconda3\python.exe)</last-edited>
-          <splitter-proportions>
-            <option name="proportions">
-              <list>
-                <option value="0.2" />
-              </list>
-            </option>
-          </splitter-proportions>
-        </settings>
-      </state>
-    </states>
-  </component>
 </project>

example_conf.yaml

@@ -1,12 +1,15 @@
-# Format: (all args are passed to __init__ as kwargs
+# Format (all args are passed to __init__ as kwargs:
 #
 # <mountpoint>:
 #   class: <feed_class>
 #   args:
 #     key: value
-subfactory-show:
-  package: bassdrive
-  class: BassdriveFeed
-  args:
-    url: http://archives.bassdrivearchive.com/1%20-%20Monday/Subfactory%20Show%20-%20DJ%20Spim/
-    logo: http://www.bassdrive.com/img/radio_schedule_entries/image/original/subfactory-web-add-56.jpg
+server:
+  port: 10000
+
+podcasts:
+  subfactory-show:
+    class: podcasters.BassdriveFeed
+    args:
+      url: http://archives.bassdrivearchive.com/1%20-%20Monday/Subfactory%20Show%20-%20DJ%20Spim/
+      logo: http://www.bassdrive.com/img/radio_schedule_entries/image/original/subfactory-web-add-56.jpg

repod.iml

@@ -2,7 +2,9 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager" inherit-compiler-output="true">
     <exclude-output />
-    <content url="file://$MODULE_DIR$" />
+    <content url="file://$MODULE_DIR$">
+      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
+    </content>
     <orderEntry type="inheritedJdk" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>

repod/conf_parser.py

@@ -1,30 +0,0 @@
-"""
-Given a configuration file, set up everything needed to kick
-off the server.
-"""
-from importlib import import_module
-import yaml
-from pyramid.config import Configurator
-from os.path import expanduser, join
-
-# Needed for import_module call
-# noinspection PyUnresolvedReferences
-import modules
-
-
-def build_configuration(conf=None) -> Configurator:
-    if conf is None:
-        conf = join(expanduser('~'), '.repodrc')
-
-    with open(conf) as conf_file:
-        conf_dict = yaml.load(conf_file)
-        server_conf = Configurator()
-        for mountpoint, feed in conf_dict.items():
-            feed_package = import_module('modules.' + feed['package'])
-            feed_class = getattr(feed_package, feed['class'])
-            feed_instance = feed_class(**feed['args'])
-
-            server_conf.add_route(mountpoint, '/' + mountpoint + '/')
-            server_conf.add_view(feed_instance.view, route_name=mountpoint)
-
-        return server_conf

repod/server.py

@@ -1,10 +0,0 @@
-from wsgiref.simple_server import make_server
-from conf_parser import build_configuration
-
-def start_server():
-    app = build_configuration().make_wsgi_app()
-    server = make_server('0.0.0.0', 8080, app)
-    server.serve_forever()
-
-if __name__ == '__main__':
-    start_server()

src/conf_parser.py

@@ -0,0 +1,38 @@
+"""
+Given a configuration file, set up everything needed to kick
+off the server.
+"""
+from importlib import import_module
+
+import yaml
+from pyramid.config import Configurator
+
+
+def build_configurator(podcasts: dict) -> Configurator:
+    server_conf = Configurator()
+    for mountpoint, feed in podcasts:
+        package, class_name = feed['class'].rsplit('.', 1)
+        feed_package = import_module(package)
+        feed_class = getattr(feed_package, class_name)
+        feed_instance = feed_class(**feed['args'])
+
+        server_conf.add_route(mountpoint, '/' + mountpoint + '/')
+        server_conf.add_view(feed_instance.view, route_name=mountpoint)
+
+
+def build_configuration_text(file_str: str) -> (dict, Configurator):
+    conf_dict = yaml.load(file_str)
+
+    server_opts = conf_dict.get('server', None)
+    podcasts = build_configurator(conf_dict['podcasts'])
+    return server_opts, podcasts
+
+
+def build_configuration(file_name) -> (dict, Configurator):
+    try:
+        with open(file_name) as conf_file:
+            return build_configuration_text(conf_file.read())
+    except FileNotFoundError:
+        print("Could not locate configuration file " +
+              "(does {} exist?)".format(file_name))
+        raise

src/podcasters/base.py

@@ -1,18 +1,19 @@
-"""
-Base skeleton for what needs to be implemented by a podcast provider
-"""
-from feedgen.feed import FeedGenerator
-from pyramid.response import Response
-
-
-class BasePodcast():
-
-    def build_feed(self) -> FeedGenerator:
-        "Return a list of all episodes, in descending date order"
-        pass
-
-    def view(self, request):
-        fg = self.build_feed()
-        response = Response(fg.rss_str(pretty=True))
-        response.content_type = 'application/rss+xml'
-        return response
+"""
+Base skeleton for what needs to be implemented by a podcast provider
+"""
+from feedgen.feed import FeedGenerator
+from pyramid.response import Response
+
+
+class BasePodcast():
+
+    def build_feed(self) -> FeedGenerator:
+        "Return a list of all episodes, in descending date order"
+        pass
+
+    # noinspection PyUnusedLocal
+    def view(self, request):
+        fg = self.build_feed()
+        response = Response(fg.rss_str(pretty=True))
+        response.content_type = 'application/rss+xml'
+        return response

src/podcasters/bassdrive.py

@@ -1,91 +1,94 @@
-"""
-Podcast provider for the Bassdrive Archives
-"""
-from html.parser import HTMLParser
-from urllib.parse import unquote
-
-import requests
-from feedgen.feed import FeedGenerator
-
-from podcast import BasePodcast
-from datetime import datetime
-from pytz import UTC
-
-
-class BassdriveParser(HTMLParser):
-    record_link_text = False
-    link_url = ''
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.links = []
-
-    def handle_starttag(self, tag, attrs):
-        href = ''
-        for attr, val in attrs:
-            if attr == 'href':
-                href = val
-
-        if tag == 'a' and href.find('mp3') != -1:
-            self.record_link_text = True
-            self.link_url = href
-
-    def handle_data(self, data):
-        if self.record_link_text:
-            self.links.append((data, self.link_url))
-            self.record_link_text = False
-
-    def get_links(self):
-        # Reverse to sort in descending date order
-        return self.links
-
-    def clear_links(self):
-        self.links = []
-
-
-class BassdriveFeed(BasePodcast):
-    def __init__(self, *args, **kwargs):
-        self.url = kwargs['url']
-        self.logo = kwargs['logo']
-        # Get the title and DJ while handling trailing slash
-        url_pretty = unquote(self.url)
-        elems = filter(lambda x: x, url_pretty.split('/'))
-        self.title, self.dj = list(elems)[-1].split(' - ')
-
-    def build_feed(self):
-        "Build the feed given our existing URL"
-        # Get all the episodes
-        page_content = str(requests.get(self.url).content)
-        parser = BassdriveParser()
-        parser.feed(page_content)
-        links = parser.get_links()
-
-        # And turn them into something usable
-        fg = FeedGenerator()
-        #fg.load_extension('podcast')
-        fg.id(self.url)
-        fg.title(self.title)
-        fg.description(self.title)
-        fg.author({'name': self.dj})
-        fg.language('en')
-        fg.link({'href': self.url, 'rel': 'alternate'})
-        fg.logo(self.logo)
-
-        for link in links:
-            fe = fg.add_entry()
-            fe.author({'name': self.dj})
-            fe.title(link[0])
-            fe.description(link[0])
-            fe.enclosure(self.url + link[1], 0, 'audio/mpeg')
-
-            # Bassdrive always uses date strings of
-            # [yyyy.mm.dd] with 0 padding, so that
-            # makes our lives easy
-            date_start = link[0].find('[')
-            date_str = link[0][date_start:date_start+12]
-            published = datetime.strptime(date_str, '[%Y.%m.%d]')
-            fe.pubdate(UTC.localize(published))
-            fe.guid((link[0]))
-
-        parser.clear_links()
-        return fg
+"""
+Podcast provider for the Bassdrive Archives
+"""
+from datetime import datetime
+from html.parser import HTMLParser
+from urllib.parse import unquote
+
+import requests
+from feedgen.feed import FeedGenerator
+from pytz import UTC
+
+from podcasters.base import BasePodcast
+
+
+class BassdriveParser(HTMLParser):
+    def error(self, message):
+        return super().error(message)
+
+    record_link_text = False
+    link_url = ''
+
+    def __init__(self, *args, **kwargs):
+        # noinspection PyArgumentList
+        super().__init__(*args, **kwargs)
+        self.links = []
+
+    def handle_starttag(self, tag, attrs):
+        href = ''
+        for attr, val in attrs:
+            if attr == 'href':
+                href = val
+
+        if tag == 'a' and href.find('mp3') != -1:
+            self.record_link_text = True
+            self.link_url = href
+
+    def handle_data(self, data):
+        if self.record_link_text:
+            self.links.append((data, self.link_url))
+            self.record_link_text = False
+
+    def get_links(self):
+        # Reverse to sort in descending date order
+        return self.links
+
+    def clear_links(self):
+        self.links = []
+
+
+class BassdriveFeed(BasePodcast):
+    def __init__(self, *args, **kwargs):
+        self.url = kwargs['url']
+        self.logo = kwargs['logo']
+        # Get the title and DJ while handling trailing slash
+        url_pretty = unquote(self.url)
+        elems = filter(lambda x: x, url_pretty.split('/'))
+        self.title, self.dj = list(elems)[-1].split(' - ')
+
+    def build_feed(self):
+        "Build the feed given our existing URL"
+        # Get all the episodes
+        page_content = str(requests.get(self.url).content)
+        parser = BassdriveParser()
+        parser.feed(page_content)
+        links = parser.get_links()
+
+        # And turn them into something usable
+        fg = FeedGenerator()
+        fg.id(self.url)
+        fg.title(self.title)
+        fg.description(self.title)
+        fg.author({'name': self.dj})
+        fg.language('en')
+        fg.link({'href': self.url, 'rel': 'alternate'})
+        fg.logo(self.logo)
+
+        for link in links:
+            fe = fg.add_entry()
+            fe.author({'name': self.dj})
+            fe.title(link[0])
+            fe.description(link[0])
+            fe.enclosure(self.url + link[1], 0, 'audio/mpeg')
+
+            # Bassdrive always uses date strings of
+            # [yyyy.mm.dd] with 0 padding on days and months,
+            # so that makes our lives easy
+            date_start = link[0].find('[')
+            date_str = link[0][date_start:date_start+12]
+            published = datetime.strptime(date_str, '[%Y.%m.%d]')
+            fe.pubdate(UTC.localize(published))
+            fe.guid((link[0]))
+
+        parser.clear_links()
+        return fg

src/server.py

@@ -0,0 +1,38 @@
+import argparse
+from wsgiref.simple_server import make_server
+from conf_parser import build_configuration
+from os.path import expanduser, join
+
+
+# noinspection PyUnresolvedReferences
+def start_server(cmd_args: dict):
+    try:
+        server_conf, configurator = build_configuration(cmd_args.configuration)
+        app = configurator.make_wsgi_app()
+        server = make_server(cmd_args.host, cmd_args.port, app)
+
+        server.serve_forever()
+    except FileNotFoundError:
+        print("Unable to find configuration file. Does {} exist?"
+              .format(cmd_args.configuration))
+    except AttributeError:
+        print("Unable to parse configuration file. Is {} a valid YML file?"
+              .format(cmd_args.configuration))
+    except KeyError:
+        print('Unable to parse configuration file. Is there a `podcasts`'
+              'section?')
+
+
+if __name__ == '__main__':
+    default_rc = join(expanduser('~'), '.repodrc')
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--verbose', help='Run server in verbose mode')
+    parser.add_argument('--port', type=int, default=10000,
+                        help='Port to use when starting the server')
+    parser.add_argument('--host', type=str, default='0.0.0.0',
+                        help='Host address to start the server')
+    parser.add_argument('--configuration', type=str, default=default_rc,
+                        help='Configuration file to start the server')
+
+    args = parser.parse_args()
+    start_server(args)

src/tests/test_build_configurator.py

@@ -0,0 +1,12 @@
+from unittest import TestCase
+import conf_parser
+
+
+class TestBuild_configurator(TestCase):
+    def test_build_configurator(self):
+        try:
+            # noinspection PyTypeChecker
+            conf_parser.build_configurator(None)
+            self.fail("Must have dictionary to set up configurator")
+        except TypeError:
+            pass