first commit

docs/source/authors.rst

@@ -0,0 +1,4 @@
+Authors
+=======
+
+Carl Chenet <chaica@ohmytux.com>

docs/source/conf.py

@@ -0,0 +1,261 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# feed2toot documentation build configuration file, created by
+# sphinx-quickstart on Wed Dec 17 18:25:26 2014.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys
+import os
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#sys.path.insert(0, os.path.abspath('.'))
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#needs_sphinx = '1.1'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The encoding of source files.
+#source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'feed2toot'
+copyright = '2017, Carl Chenet <chaica@ohmytux.com>'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+version = '1.0'
+# The full version, including alpha/beta/rc tags.
+release = '1.0'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#today = ''
+# Else, today_fmt is used as the format for a strftime call.
+#today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = []
+
+# The reST default role (used for this markup: `text`) to use for all
+# documents.
+#default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+#modindex_common_prefix = []
+
+# If true, keep warnings as "system message" paragraphs in the built documents.
+#keep_warnings = False
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = 'default'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#html_theme_options = {}
+
+# Add any paths that contain custom themes here, relative to this directory.
+#html_theme_path = []
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+#html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#html_logo = None
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Add any extra paths that contain custom files (such as robots.txt or
+# .htaccess) here, relative to this directory. These files are copied
+# directly to the root of the documentation.
+#html_extra_path = []
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+#html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+#html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#html_additional_pages = {}
+
+# If false, no module index is generated.
+#html_domain_indices = True
+
+# If false, no index is generated.
+#html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+#html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'feed2tootdoc'
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+# The paper size ('letterpaper' or 'a4paper').
+#'papersize': 'letterpaper',
+
+# The font size ('10pt', '11pt' or '12pt').
+#'pointsize': '10pt',
+
+# Additional stuff for the LaTeX preamble.
+#'preamble': '',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+  ('index', 'feed2toot.tex', 'feed2toot Documentation',
+   'Carl Chenet \\textless{}chaica@ohmytux.com.org\\textgreater{}', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#latex_use_parts = False
+
+# If true, show page references after internal links.
+#latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#latex_appendices = []
+
+# If false, no module index is generated.
+#latex_domain_indices = True
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    ('index', 'feed2toot', 'feed2toot Documentation',
+     ['Carl Chenet <chaica@ohmytux.com>'], 1)
+]
+
+# If true, show URL addresses after external links.
+#man_show_urls = False
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+  ('index', 'feed2toot', 'feed2toot Documentation',
+   'Carl Chenet <chaica@ohmytux.com>', 'feed2toot', 'One line description of project.',
+   'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#texinfo_appendices = []
+
+# If false, no module index is generated.
+#texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+#texinfo_no_detailmenu = False

docs/source/configure.rst

@@ -0,0 +1,116 @@
+Configure Feed2toot
+===================
+
+As a prerequisite to use Feed2toot, you need to authorize a Mastodon app for your account.
+
+Just use the script register_feed2toot_app to register the feed2toot app for your account.::
+
+    $ ./register_feed2toot_app 
+
+    This app generates Mastodon app credentials needed by Feed2toot.
+    feed2toot_clientcred.txt and feed2toot_usercred.txt will be written in the current dir /home/chaica/progra/python/feed2toot.
+    One connection is initiated to create the app.
+    Your password is *not* stored.
+
+    Mastodon instance url (defaults to https://mastodon.social):
+    Mastodon login:chaica@ohmytux.com
+    Mastodon password:
+    The feed2toot app was added to your preferences=>authorized apps page
+
+As described above, two files were created. You'll need them in the feed2toot configuration.
+
+In order to configure Feed2toot, you need to create a feed2toot.ini file (or any name you prefer, finishing with the extension .ini) with the following parameters::
+
+    [mastodon]
+    ; Here you need the two files created by register_feed2toot_app
+    user_credentials=/etc/feed2toot/credentials/feed2toot_usercred.txt
+    client_credentials=/etc/feed2toot/credentials/feed2toot_clientcred.txt
+
+    [cache]
+    cachefile=/var/lib/feed2toot/feed2toot.db
+    cache_limit=10000
+
+    [rss]
+    uri: https://www.journalduhacker.net/rss
+    uri_list: /etc/feed2toot//rsslist.txt
+    tweet: {title} {link}
+    title_pattern: Open Source
+    title_pattern_case_sensitive: true
+    no_uri_pattern_no_global_pattern=true
+
+    [hashtaglist]
+    several_words_hashtags_list: /etc/feed2toot/hashtags.txt
+
+For the [mastodon] section:
+
+- user_credentials: a file with the user credentials, generated by the command register_feed2toot_app
+- client_credentials: a file with the client credentials, generated by the command register_feed2toot_app
+
+For the [cache] section:
+
+- cachefile: the path to the cache file storing ids of already tweeted links. Absolute path is mandatory. This file should always use the .db extension.
+- cache_limit: length of the cache queue. defaults to 100.
+
+For the [rss] section:
+
+- uri: the url of the rss feed to parse
+- uri_list: a path to a file with several adresses of rss feeds, one by line. Absolute path is mandatory.
+- tweet: format of the tweet you want to post. It should use existing entries of the RSS fields like {title} or {link}. Launch it with this field empty to display all available entries.
+- {one field of the rss feed}_pattern: takes a string representing a pattern to match for a specified field of each rss entry of the rss feed, like title_pattern or summary_pattern.
+- {one field of the rss feed}_pattern_case_sensitive: either the pattern matching for the specified field should be case sensitive or not. Default to true if not specified.
+- no_uri_pattern_no_global_pattern: don't apply global pattern (see above) when no pattern-by-uri is defined in the uri_list. Allows to get all entries of a rss in the uri_list because no pattern is defined so we match them all. Defaults to false, meaning the global patterns will be tried on every rss in the uri_list NOT HAVING specific patterns and so ONLY entries from the specific uri in the uri_list matching the global patterns will be considered.
+
+For the [hashtaglist] section:
+
+- several_words_hashtags_list: a path to the file containing hashtags in two or more words. Absolute path is mandatory. By default Feed2toot adds a # before every words of a hashtag.
+
+List of rss feeds
+=================
+Simple list of rss feeds
+------------------------
+With the parameter **uri_list**, you can define a list of uri to use. Starting from 0.10, Feed2toot is now able to match specific patterns for each of the rss feeds from this list. Consider the following rss section of the configuration file::
+
+    [rss]
+    uri_list=/home/john/feed2toot/rsslist.txt
+    tweet={title} {link}
+
+Now let's have a look at the =/home/john/feed2toot/rsslist.txt file::
+
+    https://www.journalduhacker.net/rss
+    https://carlchenet.com/feed
+
+Each line of this file is a url to a rss feed. Pretty simple.
+
+Match specific patterns of rss feeds in the uri_list files
+----------------------------------------------------------
+You can use specific pattern matching for uri in the uri_list file to filter some of the rss entries of a rss feed. Lets modify the previous file::
+
+https://www.journalduhacker.net/rss|title|hacker,psql
+https://carlchenet.com/feed|title|gitlab
+
+Each line of this file starts with an uri, followed by a pipe (|), followed by the name of the available section to parse (see below), again followed by a pipe (|), followed by patterns, each pattern being separated from the other one by a semi-colon (,).
+
+In the example file above wee get every rss entries from the feed available at https://www.journalduhacker.net/rss where a substring in the title section of this entry matches either "hacker" or "psql". Specific patterns are not case sensitive. For the second line, we match every rss entries from the feed available at https://carlchenet.com/feed where a substring in the title section of this entry matches "gitlab".
+
+Consider every entries of a rss feed from a uri in the uri_list file
+--------------------------------------------------------------------
+It is possible to get all entries from a rss feed available in the uri_list file. You need an option to deactivate the global pattern matching for uri in the uri_list NOT having specific patterns::
+
+    [rss]
+    ...
+    no_uri_pattern_no_global_pattern=true
+
+In you rsslist.txt, just don't give anything else than the needed feed url to get all the entries::
+
+https://www.journalduhacker.net/rss|title|hacker,psql
+https://carlchenet.com/feed|title|gitlab
+https://blog.linuxjobs.fr/feed.php?rss
+
+The last line of the file above only has the url of a rss feed. All entries from this feed will be tweeted.
+
+How to display available sections of the rss feed
+=================================================
+Feed2toot offers the **--rss-sections** command line option to display the available section of the rss feed and exits::
+
+    $ feed2toot --rss-sections -c feed2toot.ini
+    The following sections are available in this RSS feed: ['title', 'comments', 'authors', 'link', 'author', 'summary', 'links', 'tags', id', 'author_detail', 'published'].

docs/source/index.rst

@@ -0,0 +1,27 @@
+Documentation for the Feed2toot project
+=======================================
+
+Feed2toot parses a RSS feed, extracts the last entries and sends them to Mastodon.
+You'll find below anything you need to install, configure or run Feed2toot.
+
+Guide
+=====
+
+.. toctree::
+   :maxdepth: 2
+
+   install
+   configure
+   use
+   plugins
+   license
+   authors
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

docs/source/install.rst

@@ -0,0 +1,36 @@
+How to install Feed2toot
+========================
+From PyPI
+^^^^^^^^^
+    $ pip3 install feed2toot
+
+From sources
+^^^^^^^^^^^^
+* You need at least Python 3.4.
+
+* On some Linux Distribution **setuptools** package does not come with default python install, you need to install it.
+
+* Install **PIP**::
+
+    	$ wget https://bootstrap.pypa.io/get-pip.py -O - | sudo python3
+    
+    
+* Install **setuptools** module::    
+  
+    $ wget https://bootstrap.pypa.io/ez_setup.py -O - | sudo python3
+    
+Alternatively, Setuptools may be installed to a user-local path::
+	  
+	       $ wget https://bootstrap.pypa.io/ez_setup.py -O - | python3 - --user
+
+* Untar the tarball and go to the source directory with the following commands::
+
+    $ tar zxvf feed2toot-0.1.tar.gz
+    $ cd feed2toot
+
+* Next, to install Feed2toot on your computer, type the following command with the root user::
+
+    $ python3 setup.py install
+    $ # or
+    $ python3 setup.py install --install-scripts=/usr/bin
+

docs/source/license.rst

@@ -0,0 +1,4 @@
+License
+=======
+
+This software comes under the terms of the **GPLv3+**. It was previously under the **MIT** license. See the LICENSE file for the complete history of the license and the full text of the past and current licenses.

docs/source/plugins.rst

@@ -0,0 +1,38 @@
+Plugins
+=======
+Feed2toot supports plugins. Plugins offer optional features, not supported by default. Optional means you need a dedicated configuration and sometimes a dedicated external dependencies. What you need for each module is specified below.
+
+InfluxDB
+--------
+The InfluxDB plugin allows to store already published tweets in a InfluxDB database.
+
+Install the InfluxDB plugin
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+To install Feed2toot with the InfluxDB plugin, execute the following command.
+
+From scratch::
+
+    # pip3 install feed2toot[influxdb]
+
+Upgrading from a previous version, execute the followin command::
+
+    # pip3 install feed2toot[influxdb] --upgrade
+
+Configuration
+^^^^^^^^^^^^^
+Below is the block of configuration to add in your feed2toot.ini::
+
+    [influxdb]
+    ;host=127.0.0.1
+    ;port=8086
+    user=influxuser
+    pass=V3ryS3cr3t
+    database=influxdb
+    measurement=tweets
+
+- host: the host where the influxdb instance is. Defaults to 127.0.0.1
+- port: the port where the influxdb instance is listening to. Defaults to 8086
+- user: the user authorized to connect to the database. Mandatory (no default)
+- pass: the password needed to connect to the database. Mandatory (no default)
+- database: the name of the influxdb database to connect to. Mandatory (no default)
+- measurement: the measurement to store the value into. Mandatory (no default)

docs/source/use.rst

@@ -0,0 +1,56 @@
+Use Feed2toot
+==============
+After the configuration of Feed2toot, just launch the following command::
+
+    $ feed2toot -c /path/to/feed2toot.ini
+
+Run Feed2toot on a regular basis
+=================================
+Feed2toot should be launche on a regular basis in order to efficiently send your new RSS entries to Mastodon. It is quite easy to achieve with adding a line to your user crontab, as described below::
+
+    @hourly feed2toot -c /path/to/feed2toot.ini
+
+will execute feed2toot every hour. Or without the syntactic sugar in the global crontab file /etc/crontab::
+
+    0 * * * * johndoe feed2toot -c /path/to/feed2toot.ini
+
+Test option
+===========
+In order to know what's going to be sent to Mastodon without actually doing it, use the **--dry-run** option::
+
+    $ feed2toot --dry-run -c /path/to/feed2toot.ini
+
+Debug option
+============
+In order to increase the verbosity of what's Feed2toot is doing, use the **--debug** option followed by the level of verbosity see [the the available different levels](https://docs.python.org/3/library/logging.html)::
+
+    $ feed2toot --debug -c /path/to/feed2toot.ini
+
+Populate the cache file without posting tweets
+==============================================
+Starting from 0.8, Feed2toot offers the **--populate-cache** command line option to populate the cache file without posting to Mastodon::
+
+    $ feed2toot --populate-cache -c feed2toot.ini
+    populating RSS entry https://www.journalduhacker.net/s/65krkk
+    populating RSS entry https://www.journalduhacker.net/s/co2es0
+    populating RSS entry https://www.journalduhacker.net/s/la2ihl
+    populating RSS entry https://www.journalduhacker.net/s/stfwtx
+    populating RSS entry https://www.journalduhacker.net/s/qq1wte
+    populating RSS entry https://www.journalduhacker.net/s/y8mzrp
+    populating RSS entry https://www.journalduhacker.net/s/ozjqv0
+    populating RSS entry https://www.journalduhacker.net/s/6ev8jz
+    populating RSS entry https://www.journalduhacker.net/s/gezvnv
+    populating RSS entry https://www.journalduhacker.net/s/lqswmz
+
+How to display available sections of the rss feed
+=================================================
+Starting from 0.8, Feed2toot offers the **--rss-sections** command line option to display the available section of the rss feed and exits::
+
+    $ feed2toot --rss-sections -c feed2toot.ini
+    The following sections are available in this RSS feed: ['title', 'comments', 'authors', 'link', 'author', 'summary', 'links', 'tags', id', 'author_detail', 'published'].
+
+Using syslog
+============
+Feed2toot is able to send its log to syslog. You can use it with the following command::
+
+    $ feed2toot --syslog=WARN -c /path/to/feed2toot.ini