From 83a67c06183029095d4759fb64396f058a70c93a Mon Sep 17 00:00:00 2001
From: Steven Ly <6807939+orcsly@users.noreply.github.com>
Date: Fri, 16 Oct 2020 12:58:50 -0700
Subject: [PATCH] DIV-1192: Add link checker.

---
 .github/workflows/linkcheck.yml               | 28 ++++++++++
 .gitignore                                    |  1 +
 .../core/management/commands/link_check.py    | 54 +++++++++++++++++++
 requirements.txt                              |  2 +
 4 files changed, 85 insertions(+)
 create mode 100644 .github/workflows/linkcheck.yml
 create mode 100644 edivorce/apps/core/management/commands/link_check.py

diff --git a/.github/workflows/linkcheck.yml b/.github/workflows/linkcheck.yml
new file mode 100644
index 00000000..948f1225
--- /dev/null
+++ b/.github/workflows/linkcheck.yml
@@ -0,0 +1,28 @@
+name: eDivorce - Link Check
+
+on:
+  schedule:
+  - cron: "*/2 * * * *"
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 4
+      matrix:
+        python-version: [3.6]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install Dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+    - name: Run Link Checker
+      run: |
+        python manage.py link_check
diff --git a/.gitignore b/.gitignore
index 38c3a5e0..df78405b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -32,6 +32,7 @@ var/
 .installed.cfg
 *.egg
 .python-version
+pyvenv.cfg
 
 # PyInstaller
 #  Usually these files are written by a python script from a template
diff --git a/edivorce/apps/core/management/commands/link_check.py b/edivorce/apps/core/management/commands/link_check.py
new file mode 100644
index 00000000..6d8dcebe
--- /dev/null
+++ b/edivorce/apps/core/management/commands/link_check.py
@@ -0,0 +1,54 @@
+import os
+import sys
+from urllib.request import urlopen
+
+from bs4 import BeautifulSoup
+
+from django.conf import settings
+from django.core.management.base import BaseCommand
+
+
+class Command(BaseCommand):
+    help = 'Checks links in the eDivorce application.'
+
+    def _check_link(self, address):
+        try:
+            resp = urlopen(address)
+            if resp.status in [400, 404, 403, 408, 409, 501, 502, 503]:
+                return f"{resp.status} - {resp.reason}"
+        except Exception as e:
+            return f"{e}"
+        return None
+
+    def handle(self, *args, **options):
+        errors = []
+
+        for root, directory, files in os.walk(settings.BASE_DIR + '/apps/core/templates/'):
+            for file in files:
+                if '.html' in file:
+                    file_path = os.path.join(root, file)
+
+                    fs = open(file_path)
+                    soup = BeautifulSoup(fs, 'html.parser')
+                    links = soup.find_all('a', href=True)
+                    for link in links:
+                        if link is None:
+                            continue
+                        if link['href'].startswith('http'):
+                            filename = str(file_path.name)
+
+                            status = self._check_link(link['href'])
+                            if status:
+                                errors.append({
+                                    'link': link['href'],
+                                    'error': status,
+                                    'file': filename
+                                })
+
+        if len(errors) > 0:
+            for error in errors:
+                print('-------------------------------------------------------------')
+                print(f'File: {error["file"]}')
+                print(f'link: {error["link"]}')
+                print(f'Error: {error["error"]}\r\n')
+            sys.exit(1)
diff --git a/requirements.txt b/requirements.txt
index 31d972b5..d468105f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,5 @@
 aniso8601==7.0.0
+beautifulsoup4==4.9.3
 certifi==2020.6.20
 chardet==3.0.4
 clamd==1.0.2
@@ -31,6 +32,7 @@ rjsmin==1.1.0
 Rx==1.6.1
 singledispatch==3.4.0.3
 six==1.15.0
+soupsieve==2.0.1
 sqlparse==0.3.1
 Unidecode==1.1.1
 Unipath==1.1