v1 added

Author: ipsavitsky

Diff for: .gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# 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/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Diff for: .vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "python.formatting.provider": "none",
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter"
+    }
+}

Diff for: poetry.lock

@@ -0,0 +1,22 @@
+[tool.poetry]
+name = "wiki-search"
+version = "0.1.0"
+description = ""
+authors = ["Ilya Savitsky <[email protected]>"]
+readme = "README.md"
+packages = [{include = "wiki_search"}]
+
+[tool.poetry.dependencies]
+python = "^3.10"
+beautifulsoup4 = "^4.12.2"
+markdownify = "^0.11.6"
+rich = "^13.3.5"
+requests = "^2.29.0"
+
+
+[tool.poetry.group.dev.dependencies]
+black = "^23.3.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

Diff for: pyproject.toml

@@ -0,0 +1,32 @@
+import argparse
+from bs4 import BeautifulSoup
+from markdownify import MarkdownConverter
+from rich.console import Console
+from rich.markdown import Markdown
+from soup_filters import filter_soup
+from wikipedia import NoArticleFound, fetch_wiki_data
+
+console = Console()
+
+parser = argparse.ArgumentParser(description="Search a Wikipedia article and print it")
+parser.add_argument("keyword", type=str, help="The keyword to search")
+args = parser.parse_args()
+
+try:
+    page_info = fetch_wiki_data(args.keyword)
+except NoArticleFound as e:
+    console.print(f'No article "{e.fprompt}" found')
+    exit(1)
+
+soup = BeautifulSoup(page_info["text"]["*"], "html.parser")
+
+filtered_soup = filter_soup(page_info["title"], soup)
+
+md = MarkdownConverter(escape_underscores=False, autolinks=False).convert_soup(
+    filtered_soup
+)
+
+markdown = Markdown(md)
+
+with console.pager():
+    console.print(markdown)

Diff for: tests/__init__.py

@@ -0,0 +1,7 @@
+from dataclasses import dataclass
+
+
+@dataclass
+class Options:
+    class_prefix: str = "en"
+    skip_tables: bool = True

Diff for: wiki_search/__init__.py

@@ -0,0 +1,48 @@
+from bs4 import BeautifulSoup
+from options import Options
+
+
+def filter_soup(opts: Options, title: str, soup: BeautifulSoup) -> BeautifulSoup:
+    body = soup.find("div", class_="mw-parser-output")
+    for tag in body.find_all("table", class_="infobox"):
+        tag.decompose()
+
+    for tag in body.find_all("div", class_="navbox"):
+        tag.decompose()
+
+    if opts.skip_tables:
+        for tag in body.find_all("table"):
+            tag.decompose()
+    else:
+        for tag in body.find_all("table", class_="sidebar"):
+            tag.decompose()
+
+        for tag in body.find_all("table", class_="metadata"):
+            tag.decompose()
+
+    for tag in body.find_all("div", class_="metadata"):
+        tag.decompose()
+
+    for tag in body.find_all("style"):
+        tag.decompose()
+
+    for tag in body.find_all("span", class_="mw-editsection"):
+        tag.decompose()
+
+    for tag in body.find_all("span", class_="mw-cite-backlink"):
+        tag.decompose()
+
+    for tag in body.find_all("a"):
+        tag["href"] = f"https://{opts.class_prefix}.wikipedia.org" + tag["href"]
+
+    for tag in body.find_all("sup", class_="reference"):
+        if "a" in tag:
+            tag.string = tag["a"].text
+
+    final_soup = BeautifulSoup()
+    header_tag = final_soup.new_tag("h1")
+    header_tag.string = title
+    final_soup.append(header_tag)
+    final_soup.append(body)
+
+    return final_soup

Diff for: wiki_search/__main__.py

@@ -0,0 +1,22 @@
+import requests
+from options import Options
+
+
+class NoArticleFound(Exception):
+    def __init__(self, failed_prompt: str):
+        self.fprompt = failed_prompt
+
+
+def fetch_wiki_data(opts: Options, prompt: str) -> str:
+    url = f"https://{opts.class_prefix}.wikipedia.org/w/api.php"
+    params = {
+        "action": "parse",
+        "page": prompt,
+        "format": "json",
+        "prop": "text",
+        "redirects": "",
+    }
+    data = requests.get(url, params=params).json()
+    if "error" in data:
+        raise NoArticleFound(prompt)
+    return data["parse"]