diff --git a/tools/scraper/.gitignore b/tools/scraper/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..952980996a469f37f22b11f630b19c0e9b3a996e
--- /dev/null
+++ b/tools/scraper/.gitignore
@@ -0,0 +1,154 @@
+# 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
+
+# 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
+.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 maintainted 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/
+
+articles
diff --git a/tools/scraper/requirements.txt b/tools/scraper/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3e4836142e360e5cf4c554972b138c754c2683a9
--- /dev/null
+++ b/tools/scraper/requirements.txt
@@ -0,0 +1,14 @@
+autopep8==1.6.0
+beautifulsoup4==4.10.0
+bs4==0.0.1
+certifi==2021.10.8
+charset-normalizer==2.0.9
+idna==3.3
+lxml==4.7.1
+markdownify==0.10.1
+pycodestyle==2.8.0
+requests==2.26.0
+six==1.16.0
+soupsieve==2.3.1
+toml==0.10.2
+urllib3==1.26.7
diff --git a/tools/scraper/scrape-wordpress-blogs.py b/tools/scraper/scrape-wordpress-blogs.py
new file mode 100644
index 0000000000000000000000000000000000000000..b4c809ee85b3227175925efd767263bce73db7ed
--- /dev/null
+++ b/tools/scraper/scrape-wordpress-blogs.py
@@ -0,0 +1,74 @@
+import requests
+from bs4 import BeautifulSoup
+from datetime import datetime
+import os
+from pathlib import Path
+import markdownify
+
+article_base_dir = "articles"
+dir_path = os.path.dirname(os.path.realpath(__file__))
+base_path = Path(str(os.path.join(dir_path, article_base_dir)))
+
+base_path.mkdir(exist_ok=True)
+
+base_url = "https://kszk.bme.hu"
+headers = {
+ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"}
+
+for page in range(1, 29):
+ base_request = None
+ if (page==1):
+ base_request = requests.get(
+ base_url, headers=headers)
+ else:
+ base_request = requests.get(
+ base_url + "/page/" + str(page) + "/", headers=headers)
+ base_soup = BeautifulSoup(base_request.content, features='lxml')
+
+ articles = base_soup.find_all("article", class_="post")
+
+ for article in articles:
+ article_link = article.find("a", href=True)['href']
+ article_title = article.find("a", href=True).getText()
+ print(article_title)
+ article_tags = []
+ try:
+ article_tags = map(lambda tag_link: tag_link.getText(), article.find(
+ "span", class_="tags-links").find_all("a", rel="tag"))
+ except:
+ pass
+
+ article_slug = article_link.rsplit('/', 2)[1]
+ article_date = datetime.strptime(article.find(
+ "time")['datetime'], '%Y-%m-%dT%H:%M:%S%z')
+ article_author_link = article.find(
+ "a", rel="author", href=True)['href']
+
+ article_folder_path = Path.joinpath(
+ base_path, str(article_date.year), str(
+ article_date.month).zfill(2), str(article_date.day).zfill(2))
+ article_path = Path.joinpath(article_folder_path, article_slug + ".md")
+
+ article_folder_path.mkdir(parents=True, exist_ok=True)
+
+ article_request = requests.get(article_link, headers=headers)
+ article_soup = BeautifulSoup(article_request.content, features='lxml')
+ article_content_as_html = article_soup.find(
+ "div", class_="entry-content")
+ article_content_as_md = markdownify.markdownify(
+ str(article_content_as_html), heading_style="ATX")
+
+ content = """\
+---
+slug: {slug}
+title: {title}
+authors: {author_link}
+tags: [{tags}]
+---
+
+{content}
+""".format(slug=article_slug, title=article_title, author_link=article_author_link, tags=", ".join(list(article_tags)), content=article_content_as_md)
+
+ article_file = open(str(article_path), "w")
+ article_file.write(content)
+ article_file.close()