Adds function for returning all sections with given title

.deepsource.toml

@@ -5,10 +5,12 @@ test_patterns = [
 ]
 
 exclude_patterns = [
-  
+
 ]
 
 [[analyzers]]
 name = 'python'
 enabled = true
 runtime_version = '3.x.x'
+max_line_length = 90
+type_checker = "mypy"

.flake8

@@ -0,0 +1,3 @@
+[flake8]
+max-line-length = 90
+extend-ignore = E203, W503

.isort.cfg

@@ -0,0 +1,4 @@
+[settings]
+profile = "google"
+multi_line_output = 3
+include_trailing_comma = True

.mypy.ini

@@ -0,0 +1,4 @@
+[mypy]
+python_version = 3.10
+warn_return_any = True
+warn_unused_configs = True

.pre-commit-config.yaml

@@ -0,0 +1,62 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+
+exclude: original
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-docstring-first
+      - id: check-executables-have-shebangs
+      - id: check-yaml
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      # - id: double-quote-string-fixer
+      - id: check-yaml
+      # - id: check-added-large-files
+      - id: requirements-txt-fixer
+      - id: name-tests-test
+        args: ["--django"]
+
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v2.7.1"
+    hooks:
+      - id: prettier
+
+  #  - repo: https://github.com/pre-commit/mirrors-autopep8
+  #    rev: "v1.5.6"
+  #    hooks:
+  #      - id: autopep8
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.8.0
+    hooks:
+      - id: isort
+        args: ["--profile", "google", "--filter-files"]
+
+  #  - repo: https://github.com/asottile/pyupgrade
+  #    rev: v3.2.2
+  #    hooks:
+  #      - id: pyupgrade
+  #        args: [--py36-plus]
+
+  - repo: https://github.com/pycqa/flake8
+    rev: 6.0.0
+    hooks:
+      - id: flake8
+        additional_dependencies: [flake8-bugbear]
+
+  - repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+      - id: black
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.991
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          ["types-requests", "types-cachetools", "types-aiofiles"]

API.rst

@@ -15,7 +15,8 @@ WikipediaPage
 * ``text`` - returns text of the page
 * ``sections`` - list of all sections (list of ``WikipediaPageSection``)
 * ``langlinks`` - language links to other languages ({lang: ``WikipediaLangLink``})
-* ``section_by_title(name)`` - finds section by title (``WikipediaPageSection``)
+* ``section_by_title(name)`` - finds last section by title (``WikipediaPageSection``)
+* ``sections_by_title(name)`` - finds all section by title (``WikipediaPageSection``)
 * ``links`` - links to other pages ({title: ``WikipediaPage``})
 * ``categories`` - all categories ({title: ``WikipediaPage``})
 * ``displaytitle``
@@ -45,6 +46,7 @@ WikipediaPageSection
 * ``level``
 * ``text``
 * ``sections``
+* ``section_by_title(title)``
 
 ExtractFormat
 -------------

CHANGES.rst

@@ -1,6 +1,13 @@
 Changelog
 =========
 
+0.5.5
+-----
+
+* Adds support for retrieving all sections with given name - `Issue 39`_
+
+.. _Issue 39: https://github.com/martin-majlis/Wikipedia-API/issues/39
+
 0.5.4
 -----
 

README.rst

@@ -143,13 +143,45 @@ To get all top level sections of page, you have to use property ``sections``. It
 
 
 	print_sections(page_py.sections)
-	# *: History - Python was conceived in the late 1980s, 
+	# *: History - Python was conceived in the late 1980s,
 	# *: Features and philosophy - Python is a multi-paradigm programming l
 	# *: Syntax and semantics - Python is meant to be an easily readable
 	# **: Indentation - Python uses whitespace indentation, rath
 	# **: Statements and control flow - Python's statements include (among other
 	# **: Expressions - Some Python expressions are similar to l
 
+How To Get Page Section By Title
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To get last section of page with given title, you have to use function ``section_by_title``.
+It returns the last ``WikipediaPageSection`` with this title.
+
+.. code-block:: python
+
+	section_history = page_py.section_by_title('History')
+	print("%s - %s" % (section_history.title, section_history.text[0:40]))
+
+	# History - Python was conceived in the late 1980s b
+
+How To Get All Page Sections By Title
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To get all sections of page with given title, you have to use function ``sections_by_title``.
+It returns the all ``WikipediaPageSection`` with this title.
+
+.. code-block:: python
+
+	page_1920 = wiki_wiki.page('1920')
+	sections_january = page_1920.sections_by_title('January')
+	for s in sections_january:
+	    print("* %s - %s" % (s.title, s.text[0:40]))
+
+    # * January - January 1
+    # Polish–Soviet War in 1920: The
+    # * January - January 2
+    # Isaac Asimov, American author
+    # * January - January 1 – Zygmunt Gorazdowski, Polish
+
 How To Get Page In Other Languages
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -437,5 +469,3 @@ Other Pages
 .. |libraries-io-dependent-repos| image:: https://img.shields.io/librariesio/dependent-repos/pypi/Wikipedia-API.svg
 	:target: https://libraries.io/pypi/Wikipedia-API
 	:alt: Libraries.io - Dependent Repos
-
-

tests/extract_html_format_test.py

@@ -75,6 +75,26 @@ def test_subsubsection(self):
         )
         self.assertEqual(len(section.sections), 0)
 
+    def test_subsection_by_title_return_last(self):
+        page = self.wiki.page('Test_Nested')
+        section = page.section_by_title('Subsection B')
+        self.assertEqual(section.title, 'Subsection B')
+        self.assertEqual(section.text, '<p><b>Text for section 3.B</b>\n\n\n</p>')
+        self.assertEqual(len(section.sections), 0)
+
+    def test_subsections_by_title(self):
+        page = self.wiki.page('Test_Nested')
+        sections = page.sections_by_title('Subsection B')
+        self.assertEqual(len(sections), 3)
+        self.assertEqual(
+            [s.text for s in sections],
+            [
+                '<p><b>Text for section 1.B</b>\n\n\n</p>',
+                '<p><b>Text for section 2.B</b>\n\n\n</p>',
+                '<p><b>Text for section 3.B</b>\n\n\n</p>'
+            ]
+        )
+
     def test_text(self):
         page = self.wiki.page('Test_1')
         self.maxDiff = None

tests/mock_data.py

@@ -134,6 +134,50 @@ def wikipedia_api_request(page, params):
             }
         }
     },
+    'en:action=query&prop=extracts&titles=Test_Nested&': {
+        "batchcomplete": "",
+        "warnings": {
+            "extracts": {
+                "*": "\"exlimit\" was too large for a whole article extracts request, lowered to 1."
+            }
+        },
+        "query": {
+            "normalized": [
+                {
+                    "from": "Test_Nested",
+                    "to": "Test Nested"
+                }
+            ],
+            "pages": {
+                "4": {
+                    "pageid": 14,
+                    "ns": 0,
+                    "title": "Test Nested",
+                    "extract": (
+                            "<p><b>Summary</b> text\n\n</p>\n" +
+                            "<h2>Section 1</h2>\n" +
+                            "<p>Text for section 1</p>\n\n\n" +
+                            "<h3><span id=\"s1.1\">Subsection A</span></h3>\n" +
+                            "<p><b>Text for section 1.A</b>\n\n\n</p>" +
+                            "<h3>Subsection B</h3>\n" +
+                            "<p><b>Text for section 1.B</b>\n\n\n</p>" +
+                            "<h2><span id=\"s2\">Section 2</span></h2>\n" +
+                            "<p><b>Text for section 2</b>\n\n\n</p>" +
+                            "<h3><span id=\"s2.1\">Subsection A</span></h3>\n" +
+                            "<p><b>Text for section 2.A</b>\n\n\n</p>" +
+                            "<h3>Subsection B</h3>\n" +
+                            "<p><b>Text for section 2.B</b>\n\n\n</p>" +
+                            "<h2><span id=\'s3\'>Section 3</span></h2>\n" +
+                            "<p><b>Text for section 3</b>\n\n\n</p>" +
+                            "<h3><span id=\"s3.1\">Subsection A</span></h3>\n" +
+                            "<p><b>Text for section 3.A</b>\n\n\n</p>" +
+                            "<h3>Subsection B</h3>\n" +
+                            "<p><b>Text for section 3.B</b>\n\n\n</p>"
+                    )
+                }
+            }
+        }
+    },
     'en:action=query&prop=extracts&titles=Test_Edit&': {
         "batchcomplete": "",
         "warnings": {