Python3 config and plugins

CONTRIBUTORS.md

@@ -0,0 +1,2 @@
+Ankit Singh https://github.com/Griffintaur
+Tom Faulkner https://github.com/TomFaulkner

README.md

@@ -1,5 +1,3 @@
-## Please note that I have made changes that invalidate the information in the readme. To run create the saved_articles directory, if it isn't pulled from the repo, then use Python 3.6+ and run `python3 news.py`. I'll fix the readme soon, and provide a better way to install and run. Thanks. - Tom
-
 # News at the Command line
 ### Want to be kept updated without visiting the news portals every now and then
 
@@ -9,19 +7,24 @@
 # Modules Requirements
 
 - **Python 3.6+**
-- **Requests** 
-- **Beautiful Soup** 
+- **Requests**
+- **Beautiful Soup**
 - **PyYAML**
 
-To install the module dependencies before running the application, simply navigate into the project folder and run `pip install -r requirements.txt`.
+# Installation
+1. `git clone` the repository, preferably into a virtual environment.
+2. Copy `config.yml` into your home directory.
+3. Run with `newsctl`
+
+At present `config.yml` is only read from pwd when the script is run, I'll fix this soon.
 
 # Working
 - All sample input images are placed under the **Images** folder.
 - You can change the maximum number of posts in **config.yml**. Look for **Limit** attribute.
 
 # How To Use
  Make sure you have installed required libraries, instructions above.
- Just run the main.py, do this by typing `py main.py`. 
+ Just run the main.py, do this by typing `py main.py`.
  The rest is quite straight forward.
 
 # Contributing
@@ -32,4 +35,3 @@ Please open an issue on GitHub if you'd like to report a bug or request a featur
 
 ## License
 The code is released under MIT license and free to use.
-

config.yml

@@ -1,15 +1,13 @@
-WebsiteSupported:
-    - the-huffington-post
-    - the-new-york-times
-    - bbc-news
-    - bloomberg
-    - the-guardian-uk
-    - the-hindu
-    - the-times-of-india
-
-# Posts shown   
-Limit: 10
-
-Apikey: bda5818cc2af461e98330ccdf6fb9cbe
-
-
+WebsiteSupported:
+    - the-huffington-post
+    - the-new-york-times
+    - bbc-news
+    - bloomberg
+    - the-guardian-uk
+    - the-hindu
+    - the-times-of-india
+
+# Posts shown
+Limit: 10
+
+Apikey: bda5818cc2af461e98330ccdf6fb9cbe

news/__version__.py

@@ -0,0 +1,2 @@
+__app_name__ = 'newsctl'
+__version__ = '0.0.1'

news/config_reader.py

@@ -0,0 +1,26 @@
+import os
+from contextlib import suppress
+
+import yaml
+from appdirs import AppDirs
+
+from .__version__ import __app_name__
+from .constants import constants
+
+dirs = AppDirs(__app_name__)
+
+
+class ConfigurationReader:
+    def __init__(self):
+        try:
+            with open(f'{dirs.user_config_dir}/config.yml') as ymlfile:
+                cfg = yaml.load(ymlfile)
+        except FileNotFoundError:
+            with suppress(FileExistsError):
+                os.makedirs(dirs.user_config_dir)
+            with open(f'{dirs.user_config_dir}/config.yml', 'w') as ymlfile:
+                ymlfile.write(yaml.dump(constants['config_defaults']))
+            cfg = constants['config_defaults']
+
+        self.APIKEY = cfg['api_key']
+        self.limit = cfg['article_limit']

news/constants.py

@@ -0,0 +1,6 @@
+constants = {
+    'config_defaults': {
+        'api_key': 'bda5818cc2af461e98330ccdf6fb9cbe',
+        'article_limit': 10,
+    }
+}

extract_main_content.py → news/extract_main_content.py

@@ -1,61 +1,50 @@
-import requests
-from config_reader import ConfigurationReader
-from extractor import *
-import textwrap
-
-
-class ExtractMainContent:
-    def __init__(self, source, articleurl):
-        self.extractorlist = [HuffingtonPost(), NYT(), BBC(
-        ), BloomBerg(), Guardian(), TheHindu(), TimesOfIndia()]
-        websites = ConfigurationReader().websites_supported
-        self.Mapping = {}
-        for index, website in enumerate(websites):
-            self.Mapping[website] = self.extractorlist[index]
-        self.Source = source
-        self.url = articleurl
-        self.textWrap = textwrap.TextWrapper(
-            initial_indent='\t', subsequent_indent='\t', width=100)
-
-    def download(self):
-        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
-                                 'AppleWebKit/537.36 (KHTML, like Gecko) '
-                                 'Chrome/59.0.3071.115 Safari/537.36'}
-        req = requests.get(self.url, headers=headers)
-        return req.text
-
-    # unused, but may be useful in the future
-    # def AddExtractorList(self, extractor):
-    #     self.extractorlist.append(extractor)
-
-    def _extract(self):
-        self.ExtractStrategy = self.Mapping[self.Source]
-        text = self.download()
-        return self.ExtractStrategy.extractor(text)
-
-    def beautify(self):
-        title, output = self._extract()
-        print("=" * (len(title) + 15))
-        print("\t" + title)
-        print("=" * (len(title) + 15))
-
-        print((self.textWrap.fill(output)))  # wrap of the line
-        print("*" * 80)
-        if len(output) == 0:
-            print("Sorry :(")
-            print("There isn't much text on the site besides video/image. To "
-                  "further view the media post, Go to the below link")
-            print(self.url)
-            print('*' * 80)
-            print("\n\n")
-
-    def save(self):
-        title, output = self._extract()
-
-        # Remove Chars not allowed in filenames
-        for char in ['<', '>', "/", ":", '"', "\\", "|", "?", "*"]:
-            if char in title:
-                title = title.replace(char, "")
-
-        with open(f'saved_articles/{title}.txt', "w+") as f:
-            f.write(output)
+import requests
+import textwrap
+
+from .reader_plugins.plugin_registration import sites
+
+
+class ExtractMainContent:
+    def __init__(self, source, articleurl):
+        self.source = source
+        self.url = articleurl
+        self.textWrap = textwrap.TextWrapper(
+            initial_indent='\t', subsequent_indent='\t', width=100)
+
+    def download(self):
+        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
+                                 'AppleWebKit/537.36 (KHTML, like Gecko) '
+                                 'Chrome/59.0.3071.115 Safari/537.36'}
+        req = requests.get(self.url, headers=headers)
+        return req.text
+
+    def _extract(self):
+        text = self.download()
+        return sites[self.source]().extractor(text)
+
+    def beautify(self):
+        title, output = self._extract()
+        print("=" * (len(title) + 15))
+        print("\t" + title)
+        print("=" * (len(title) + 15))
+
+        print((self.textWrap.fill(output)))  # wrap of the line
+        print("*" * 80)
+        if len(output) == 0:
+            print("Sorry :(")
+            print("There isn't much text on the site besides video/image. To "
+                  "further view the media post, Go to the below link")
+            print(self.url)
+            print('*' * 80)
+            print("\n\n")
+
+    def save(self):
+        title, output = self._extract()
+
+        # Remove Chars not allowed in filenames
+        for char in ['<', '>', "/", ":", '"', "\\", "|", "?", "*"]:
+            if char in title:
+                title = title.replace(char, "")
+
+        with open(f'saved_articles/{title}.txt', "w+") as f:
+            f.write(output)