init

.gitignore

@@ -0,0 +1,163 @@
+# Project
+/static
+data/
+*.ipynb
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+env*
+*.csv
+.idea/
+.DS_Store
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+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/
+.coveage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+pytestdebug.log
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+#*.log
+local_settings.py
+*.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+doc/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pythonenv*
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# profiling data
+.prof
+
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+.venv
+pip-selfcheck.json
+
+
+# End of https://www.toptal.com/developers/gitignore/api/python

feed2json.py

@@ -0,0 +1,70 @@
+import json
+import feedparser
+
+
+def feed2json(feed_file_path: str = None, feed_url: str = None, feed_string: str = None) -> dict:
+    if feed_file_path or feed_url or feed_string is None:
+        raise ValueError("Must provide one of feed_file_path, feed_url, or feed_string")
+
+    feed = None
+    if feed_file_path:
+        feed = feedparser.parse(feed_file_path)
+    elif feed_url:
+        feed = feedparser.parse(feed_url)
+    elif feed_string:
+        feed = feedparser.parse(feed_string)
+
+    if not feed:
+        raise ValueError("No feed provided")
+
+    json_feed = {
+        "version": "https://jsonfeed.org/version/1.1",
+        "title": feed.feed.title,
+        "feed_url": feed.feed.id,
+        "home_page_url": feed.feed.get("link", None)
+    }
+
+    if hasattr(feed.feed, "subtitle"):
+        json_feed["description"] = feed.feed.subtitle
+    if hasattr(feed.feed, "updated"):
+        json_feed["updated"] = feed.feed.updated
+
+    json_feed["items"] = []
+    for entry in feed.entries:
+        item = {
+            "id": entry.id,
+            "url": entry.link,
+            "title": entry.title,
+        }
+        if hasattr(entry, "summary"):
+            item["content_html"] = entry.summary
+        if hasattr(entry, "published"):
+            item["date_published"] = entry.published
+        if hasattr(entry, "updated"):
+            item["date_modified"] = entry.updated
+        if hasattr(entry, "author"):
+            authors = entry.author
+            if not isinstance(authors, list):
+                authors = [authors]
+            item["authors"] = [{"name": author} for author in authors]
+        if hasattr(entry, "content"):
+            item["content_html"] = ""
+            for content in entry.content:
+                if content["type"] == "text/html":
+                    item["content_html"] += content["value"]
+                elif content["type"] == "text/plain":
+                    item["content_text"] = content["value"]
+
+        if hasattr(entry, "categories"):
+            item["tags"] = [{"name": category} for category in entry.categories]
+
+        if hasattr(entry, "enclosures"):
+            item["attachments"] = [{"url": enclosure["href"], 'length': enclosure["length"], 'type': enclosure["type"]}
+                                   for enclosure in entry.enclosures]
+
+        if hasattr(entry, "summary"):
+            item["summary"] = entry.summary
+
+        json_feed["items"].append(item)
+
+    return json_feed