Feature/parsing

.gitignore

@@ -105,3 +105,6 @@ venv.bak/
 
 # direnv
 .envrc
+
+# ideas
+.vscode

HOW TO RUN FLASK APP.md

@@ -0,0 +1,11 @@
+# HOW TO RUN FLASK APP
+```sh
+export FLASK_APP=eriwan_podcast.py
+export FLASK_DEBUG=1
+
+flask db init
+flask db migrate
+flask db upgrade
+
+flask run
+```

app/__init__.py

@@ -0,0 +1,43 @@
+# Creates the application object as an instance of class Flask
+
+
+from flask import Flask
+from flask_migrate import Migrate
+from flask_sqlalchemy import SQLAlchemy
+
+from config import Config
+
+
+app = Flask(__name__)
+
+# using Config class from ./config.py
+app.config.from_object(Config)
+
+# database
+db = SQLAlchemy(app)
+migrate = Migrate(app, db)
+
+# The routes module is imported at the bottom and not at the top of the script
+# as it is always done. The bottom import is a workaround to circular imports,
+# a common problem with Flask applications.
+from app import models
+import atexit
+from app.parser import parse_anekdot
+from apscheduler.schedulers.background import BackgroundScheduler
+
+def scheduler_parser():
+    '''
+    Starts the parser.
+    '''
+    parse_anekdot()
+
+# Scheduler settings and start.
+# Variables locate in config.Config
+
+scheduler = BackgroundScheduler()
+scheduler.add_job(func=scheduler_parser, trigger="interval", hours=Config.PARSE_TIME_HOURS)
+scheduler.start()
+
+# Shut down the scheduler when exiting the app
+atexit.register(lambda: scheduler.shutdown())
+

app/forms.py

@@ -0,0 +1 @@
+# Here will be Flask Web Forms

app/models.py

@@ -0,0 +1,77 @@
+import os
+from werkzeug.security import generate_password_hash, check_password_hash
+
+from app import app, db
+
+
+class User(db.Model):
+    id = db.Column(db.Integer, primary_key=True)
+    username = db.Column(db.String(64), index=True, unique=True, nullable=False)
+    email = db.Column(db.String(120), index=True, unique=True, nullable=False)
+    password_hash = db.Column(db.String(128), nullable=False)
+    is_admin = db.Column(db.Boolean, default=False, nullable=False)
+
+    def __repr__(self):
+        return f'<User {self.username}>'
+
+    def set_password(self, password):
+        self.password_hash = generate_password_hash(password)
+
+    def check_password(self, password):
+        return check_password_hash(self.password_hash, password)
+
+
+class Episode(db.Model):
+    id = db.Column(db.Integer, primary_key=True)
+    name = db.Column(db.String(255), nullable=False)
+    user_id = db.Column(db.Integer, db.ForeignKey('user.id'))
+
+    def __repr__(self):
+        return f'<Episode id: {self.id}>, name: {self.name}'
+
+    def get_file_path(self):
+        '''
+        Return wrapped in jingles file path
+        '''
+        static_path = os.path.join(app.config.get('STATIC_ROOT'), 'episodes')
+        file_path = f'{static_path}/{self.id}.mp3'
+        if os.path.exists(file_path):
+            return file_path
+
+    # todo: add to celery task
+    def generate_wrapped_file(self, upload_file):
+        '''
+        Return generate file with name of episode prefix from upload_file
+        '''
+        pass
+
+
+class Joke(db.Model):
+    id = db.Column(db.Integer, primary_key=True)
+    joke_text = db.Column(db.Text, nullable=False)
+    user_id = db.Column(db.Integer, db.ForeignKey('user.id'))
+
+    def __repr__(self):
+        return f'<Joke id: {self.id}>, joke_text: {self.joke_text}'
+
+    def get_file_path(self):
+        '''
+        Return wrapped in jingles file path
+        '''
+        static_path = os.path.join(app.config.get('STATIC_ROOT'), 'jokes')
+        file_path = f'{static_path}/{self.id}.mp3'
+        if os.path.exists(file_path):
+            return file_path
+
+    def generate_base_file(self):
+        '''
+        Return generate base audio file from joke_text
+        '''
+        pass
+
+    # todo: add to celery task
+    def generate_wrapped_file(self, upload_file):
+        '''
+        Return generate wrapped in jingles file from upload_file
+        '''
+        pass

app/parser.py

@@ -0,0 +1,29 @@
+# Parsing jokes from anekdotitut.ru and adds 
+# them to the database.
+import urllib.request
+from urllib.parse import quote
+from urllib.parse import unquote
+from bs4 import BeautifulSoup
+import re
+from app.models import Joke
+from app import db
+
+
+def parse_anekdot():
+    '''
+    Simple func for collecting jokes from anekdotitut.ru
+    and add them to DB.
+    '''
+    jokes_out = []
+    for i in range(1, 10):
+        url = url = 'https://anekdotitut.ru/pro_armyanskoe_radio' + str(
+            i) + '.php'
+        html_doc = urllib.request.urlopen(url)
+        soup_doc = BeautifulSoup(html_doc, 'html.parser')
+        jokes = soup_doc.body(class_='noselect', id=re.compile('anekdot\d+'))
+        for joke in jokes:
+            # Check for entry in DB.
+            if not bool(Joke.query.filter_by(joke_text = joke.text).first()):
+                j = Joke(joke_text = joke.text, user_id = 999)
+                db.session.add(j)
+        db.session.commit()

app/templates/index.html

@@ -0,0 +1 @@
+{{ feed_blank }}

app/tests.py

@@ -0,0 +1 @@
+# Here will be tests

config.py

@@ -0,0 +1,18 @@
+# Config Classes
+
+import os
+basedir = os.path.abspath(os.path.dirname(__file__))
+
+
+class Config(object):
+    SECRET_KEY = os.environ.get('SECRET_KEY') or 'Wo7GhuD2OWIv'
+    SQLALCHEMY_DATABASE_URI = os.environ.get('DATABASE_URL') or \
+        'sqlite:///' + os.path.join(basedir, 'app.db')
+    SQLALCHEMY_TRACK_MODIFICATIONS = False
+
+    ADMINS = ['your-email@example.com']
+
+    STATIC_ROOT = '/static/'
+
+    # Time period for parser
+    PARSE_TIME_HOURS = 40

eriwan_podcast.py

@@ -0,0 +1,2 @@
+# The top-level that defines the Flask application instance
+from app import app

migrations/README

@@ -0,0 +1 @@
+Generic single-database configuration.

migrations/alembic.ini

@@ -0,0 +1,45 @@
+# A generic, single database configuration.
+
+[alembic]
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

migrations/env.py

@@ -0,0 +1,96 @@
+from __future__ import with_statement
+
+import logging
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+logger = logging.getLogger('alembic.env')
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+from flask import current_app
+config.set_main_option(
+    'sqlalchemy.url', current_app.config.get(
+        'SQLALCHEMY_DATABASE_URI').replace('%', '%%'))
+target_metadata = current_app.extensions['migrate'].db.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url, target_metadata=target_metadata, literal_binds=True
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    # this callback is used to prevent an auto-migration from being generated
+    # when there are no changes to the schema
+    # reference: http://alembic.zzzcomputing.com/en/latest/cookbook.html
+    def process_revision_directives(context, revision, directives):
+        if getattr(config.cmd_opts, 'autogenerate', False):
+            script = directives[0]
+            if script.upgrade_ops.is_empty():
+                directives[:] = []
+                logger.info('No changes in schema detected.')
+
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section),
+        prefix='sqlalchemy.',
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=target_metadata,
+            process_revision_directives=process_revision_directives,
+            **current_app.extensions['migrate'].configure_args
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

migrations/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}