docs

docs/Changelog.rst

@@ -0,0 +1,4 @@
+Change log
+==========
+
+.. include:: ../CHANGELOG.txt

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SPHINXPROJ    = IMDbPY
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/conf.py

@@ -0,0 +1,161 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/stable/config
+
+# -- Path setup --------------------------------------------------------------
+
+# 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.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = 'IMDbPY'
+copyright = '2018, Davide Alberani, H. Turgut Uyar'
+author = 'Davide Alberani, H. Turgut Uyar'
+
+# The short X.Y version
+version = ''
+# The full version, including alpha/beta/rc tags
+release = '6.8'
+
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# 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(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path .
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# 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 = ['imdb.']
+
+# -- 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 = 'sphinx_rtd_theme'
+
+# 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 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']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'IMDbPYdoc'
+
+
+# -- 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': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# 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 = [
+    (master_doc, 'IMDbPY.tex', 'IMDbPY Documentation',
+     'Davide Alberani, H. Turgut Uyar', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'imdbpy', 'IMDbPY Documentation',
+     [author], 1)
+]
+
+
+# -- 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 = [
+    (master_doc, 'IMDbPY', 'IMDbPY Documentation',
+     author, 'IMDbPY', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Extension configuration -------------------------------------------------

docs/credits.rst

@@ -0,0 +1,10 @@
+Contributors
+============
+
+.. include:: ../CONTRIBUTORS.txt
+
+.. raw:: html
+
+   <h2>Credits</h2>
+
+.. include:: ../CREDITS.txt

docs/devel/extend.rst

@@ -0,0 +1,172 @@
+How to extend
+-------------
+
+To introduce a new data access system, you have to write a new package
+inside the "parser" package; this new package must provide a subclass
+of the imdb.IMDb class which must define at least the following methods:
+
+``_search_movie(title)``
+  To search for a given title; must return a list of (movieID, {movieData})
+  tuples.
+
+``_search_episode(title)``
+  To search for a given episode title; must return a list of
+  (movieID, {movieData}) tuples.
+
+``_search_person(name)``
+  To search for a given name; must return a list of (movieID, {personData})
+  tuples.
+
+``_search_character(name)``
+  To search for a given character's name; must return a list of
+  (characterID, {characterData}) tuples.
+
+``_search_company(name)``
+  To search for a given company's name; must return a list of
+  (companyID, {companyData}) tuples.
+
+``get_movie_*(movieID)``
+   A set of methods, one for every set of information defined for a Movie
+   object; should return a dictionary with the relative information.
+
+   This dictionary can contain some optional keys:
+
+   - 'data': must be a dictionary with the movie info
+   - 'titlesRefs': a dictionary of 'movie title': movieObj pairs
+   - 'namesRefs': a dictionary of 'person name': personObj pairs
+
+``get_person_*(personID)``
+  A set of methods, one for every set of information defined for a Person
+  object; should return a dictionary with the relative information.
+
+``get_character_*(characterID)``
+  A set of methods, one for every set of information defined for a Character
+  object; should return a dictionary with the relative information.
+
+``get_company_*(companyID)``
+  A set of methods, one for every set of information defined for a Company
+  object; should return a dictionary with the relative information.
+
+``_get_top_bottom_movies(kind)``
+  Kind can be one of 'top' and 'bottom'; returns the related list of movies.
+
+``_get_keyword(keyword)``
+  Return a list of Movie objects with the given keyword.
+
+``_search_keyword(key)``
+  Return a list of keywords similar to the given key.
+
+``get_imdbMovieID(movieID)``
+  Convert the given movieID to a string representing the imdbID, as used
+  by the IMDb web server (e.g.: '0094226' for Brian De Palma's
+  "The Untouchables").
+
+``get_imdbPersonID(personID)``
+  Convert the given personID to a string representing the imdbID, as used
+  by the IMDb web server (e.g.: '0000154' for "Mel Gibson").
+
+``get_imdbCharacterID(characterID)``
+  Convert the given characterID to a string representing the imdbID, as used
+  by the IMDb web server (e.g.: '0000001' for "Jesse James").
+
+``get_imdbCompanyID(companyID)``
+  Convert the given companyID to a string representing the imdbID, as used
+  by the IMDb web server (e.g.: '0071509' for "Columbia Pictures [us]").
+
+``_normalize_movieID(movieID)``
+  Convert the provided movieID in a format suitable for internal use
+  (e.g.: convert a string to a long int).
+
+  NOTE: As a rule of thumb you *always* need to provide a way to convert
+  a "string representation of the movieID" into the internally used format,
+  and the internally used format should *always* be converted to a string,
+  in a way or another. Rationale: A movieID can be passed from the command
+  line, or from a web browser.
+
+``_normalize_personID(personID)``
+  idem
+
+``_normalize_characterID(characterID)``
+  idem
+
+``_normalize_companyID(companyID)``
+  idem
+
+``_get_real_movieID(movieID)``
+  Return the true movieID; useful to handle title aliases.
+
+``_get_real_personID(personID)``
+  idem
+
+``_get_real_characterID(characterID)``
+  idem
+
+``_get_real_companyID(companyID)``
+  idem
+
+The class should raise the appropriate exceptions, when needed:
+
+- ``IMDbDataAccessError`` must be raised when you cannot access the resource
+  you need to retrieve movie info or you're unable to do a query (this is
+  *not* the case when a query returns zero matches: in this situation an
+  empty list must be returned).
+
+- ``IMDbParserError`` should be raised when an error occurred parsing
+  some data.
+
+Now you've to modify the ``imdb.IMDb`` function so that, when the right
+data access system is selected with the "accessSystem" parameter, an instance
+of your newly created class is returned.
+
+For example, if you want to call your new data access system "mysql"
+(meaning that the data are stored in a mysql database), you have to add
+to the imdb.IMDb function something like:
+
+.. code-block:: python
+
+   if accessSystem == 'mysql':
+       from parser.mysql import IMDbMysqlAccessSystem
+       return IMDbMysqlAccessSystem(*arguments, **keywords)
+
+where "parser.mysql" is the package you've created to access the local
+installation, and "IMDbMysqlAccessSystem" is the subclass of imdb.IMDbBase.
+
+Then it's possible to use the new data access system like:
+
+.. code-block:: python
+
+   from imdb import IMDb
+   i = IMDb(accessSystem='mysql')
+   results = i.search_movie('the matrix')
+   print(results)
+
+.. note::
+
+   This is a somewhat misleading example: we already have a data access system
+   for SQL database (it's called 'sql' and it supports MySQL, amongst others).
+   Maybe I'll find a better example...
+
+A specific data access system implementation can define its own methods.
+As an example, the IMDbHTTPAccessSystem that is in the parser.http package
+defines the method ``set_proxy()`` to manage the use a web proxy; you can use
+it this way:
+
+.. code-block:: python
+
+   from imdb import IMDb
+   i = IMDb(accessSystem='http') # the 'accessSystem' argument is not
+                                 # really needed, since "http" is the default.
+   i.set_proxy('http://localhost:8080/')
+
+A list of special methods provided by the imdb.IMDbBase subclass, along with
+their description, is always available calling the ``get_special_methods()``
+of the IMDb class:
+
+.. code-block:: python
+
+   i = IMDb(accessSystem='http')
+   print(i.get_special_methods())
+
+will print a dictionary with the format::
+
+  {'method_name': 'method_description', ...}