Merge pull request #1 from FelixMertin/poetry_linters

[add] poetry as dependency management and linters for code quality

.gitignore

@@ -0,0 +1,163 @@
+# Ignore all generated CSV files
+*.csv
+
+# 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/

.pre-commit-config.yaml

@@ -0,0 +1,26 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-merge-conflict
+      - id: check-yaml
+        args: [--unsafe]
+      - id: check-json
+      - id: detect-private-key
+      - id: end-of-file-fixer
+
+  - repo: https://github.com/timothycrosley/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+
+  - repo: https://github.com/psf/black
+    rev: 22.8.0
+    hooks:
+      - id: black
+
+  - repo: https://gitlab.com/pycqa/flake8
+    rev: 3.9.2
+    hooks:
+      - id: flake8

README.md

@@ -5,9 +5,10 @@ At the end, it saves a CSV file in the current working directory. By default, al
 
 ## Running:
 1. Install Python
-2. Run `pip install requests bs4`
-3. Run as `python WpBrokenCheck.py [Domain] [CSV_FileName]`
-4. Example: `python WpBrokenCheck.py example.com example.csv`
+2. Install [Poetry](https://python-poetry.org/docs/#installation)
+3. Run `poetry install`
+4. Run as `poetry run python WpBrokenCheck.py [Domain] [CSV_FileName]`
+5. Example: `poetry run python WpBrokenCheck.py example.com example.csv`
 <p align="center">
   <img src="https://res.cloudinary.com/suleman/image/upload/v1665055858/WpBrokenCheck.png">
 </p>
@@ -16,6 +17,16 @@ At the end, it saves a CSV file in the current working directory. By default, al
 
 **Tip** : If target website has large number of posts then change `max_workers` from 5 to 10 at line 60.
 
+## Linters:
+
+There are the following Python linters:
+- black for code formatting
+- flake8 code formatting and line brakes (PEP8)
+- isort for reordering imports
+
+They are run via pre-commit as you commit the code to the repository. You can also run it manually on all files by:
+`pre-commit run --all-files`
+
 ### To Do:
 - Make it filter specific codes.
 - Make it run on customized WP sites

WpBrokenCheck.py

@@ -1,73 +1,95 @@
-import requests
-import csv
 import concurrent.futures
-from concurrent.futures import as_completed
+import csv
 import sys
+from concurrent.futures import as_completed
+
 import bs4
+import requests
 
 domain = sys.argv[1]
 csv_file = sys.argv[2]
 sess = requests.Session()
 links404 = []
 
 headers = {
-    'authority': 'www.'+domain,
-    'referer': 'https://'+domain,
-    'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Mobile Safari/537.36',
-    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
-    'sec-fetch-dest': 'document',
-    'accept-language': 'en-US,en;q=0.9,tr;q=0.8',
+    "authority": "www." + domain,
+    "referer": "https://" + domain,
+    "user-agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Mobile Safari/537.36",
+    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
+    "sec-fetch-dest": "document",
+    "accept-language": "en-US,en;q=0.9,tr;q=0.8",
 }
-pages = int(sess.get('https://' + domain + '/wp-json/wp/v2/posts', headers=headers).headers['X-WP-TotalPages'])
+pages = int(
+    sess.get("https://" + domain + "/wp-json/wp/v2/posts", headers=headers).headers[
+        "X-WP-TotalPages"
+    ]
+)
+
 
 def prepare_csv_data(id, post_link, data):
-           for i in data:
-              links404.append({
+    for i in data:
+        links404.append(
+            {
                 "Post ID": id,
                 "Post Link": post_link,
                 "Broken Link": i[0][0],
-                "Status Code":i[1],
-                "Link Text":i[0][1]
-                })
-
+                "Status Code": i[1],
+                "Link Text": i[0][1],
+            }
+        )
+
+
 def generate_csv_report(csv_file, csv_data):
-   with open(csv_file, 'w+',encoding="utf-8") as file:
-       csvwriter = csv.DictWriter(file, fieldnames=list(csv_data[0].keys()))
-       csvwriter.writeheader()
-       csvwriter.writerows(csv_data)
-
+
+    if csv_data:
+        with open(csv_file, "w+", encoding="utf-8") as file:
+            csvwriter = csv.DictWriter(file, fieldnames=list(csv_data[0].keys()))
+            csvwriter.writeheader()
+            csvwriter.writerows(csv_data)
+
+        print("Report saved in file: ", csv_file)
+
+    if not csv_data:
+        print("There were no broken links!")
+
+
 def getLinks(rendered_content):
-    soup = bs4.BeautifulSoup(rendered_content, 'html.parser')
-    return [(link['href'],link.text) for link in soup('a') if 'href' in link.attrs]
-
+    soup = bs4.BeautifulSoup(rendered_content, "html.parser")
+    return [(link["href"], link.text) for link in soup("a") if "href" in link.attrs]
+
+
 def getStatusCode(link, headers, timeout=5):
     print("	checking: ", link[0])
     try:
         r = sess.head(link[0], headers=headers, timeout=timeout)
-    except (requests.exceptions.SSLError,
-            requests.exceptions.HTTPError,
-            requests.exceptions.ConnectionError,
-            requests.exceptions.MissingSchema,
-            requests.exceptions.Timeout,
-            requests.exceptions.InvalidSchema
-            ) as errh:
+    except (
+        requests.exceptions.SSLError,
+        requests.exceptions.HTTPError,
+        requests.exceptions.ConnectionError,
+        requests.exceptions.MissingSchema,
+        requests.exceptions.Timeout,
+        requests.exceptions.InvalidSchema,
+    ) as errh:
         print("Error in URL, ", link)
         return link, errh.__class__.__name__
     else:
         return link, str(r.status_code)
-
+
+
 def executeBrokenLinkCheck(links):
     with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
         futures = [executor.submit(getStatusCode, link, headers) for link in links]
         return [future.result() for future in as_completed(futures)]
 
+
 for i in range(pages):
-    post_data = sess.get('https://' + domain + '/wp-json/wp/v2/posts?page='+str(i+1), headers=headers).json()
+    post_data = sess.get(
+        "https://" + domain + "/wp-json/wp/v2/posts?page=" + str(i + 1), headers=headers
+    ).json()
     for data in post_data:
-        print("Checking post: ",data["link"])
+        print("Checking post: ", data["link"])
         post_links = getLinks(data["content"]["rendered"])
         checked_urls = executeBrokenLinkCheck(post_links)
         prepare_csv_data(data["id"], data["link"], checked_urls)
-        
+
 generate_csv_report(csv_file, links404)
-print("Report saved in file: ", csv_file)