From 5962146a1681f43af56a9239f6b026ee65d58431 Mon Sep 17 00:00:00 2001
From: Nemo <commits@captnemo.in>
Date: Sun, 10 Jul 2022 15:20:48 +0530
Subject: [PATCH] [distrowatch] Distrowatch update script

---
 .github/workflows/update.yml | 10 +++---
 src/distowatch.py            | 61 ++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+), 5 deletions(-)
 create mode 100644 src/distowatch.py

diff --git a/.github/workflows/update.yml b/.github/workflows/update.yml
index 7c77a045..11bf6c30 100644
--- a/.github/workflows/update.yml
+++ b/.github/workflows/update.yml
@@ -39,15 +39,15 @@ jobs:
       with:
         ruby-version: 3.1
         bundler-cache: true
-    - name: Update Release data
+    - name: Setup Release Script
       run: |
         git config --global init.defaultBranch main
         git config --global extensions.partialClone true
-
         pip install -r requirements.txt
-        for i in src/*.py; do python $i;done
-
-        bundle exec ruby update.rb ./website ~/.cache releases
+    - name: Custom Updates
+      run: for i in src/*.py; do python $i;done
+    - name: Git and DockerHub Updates
+      run: bundle exec ruby update.rb ./website ~/.cache releases
       id: update_releases
     - uses: stefanzweifel/git-auto-commit-action@v4
       name: Commit and update new releases
diff --git a/src/distowatch.py b/src/distowatch.py
new file mode 100644
index 00000000..3d2c570d
--- /dev/null
+++ b/src/distowatch.py
@@ -0,0 +1,61 @@
+from glob import glob
+import os
+import re
+import json
+import frontmatter
+import urllib.request
+from bs4 import BeautifulSoup
+from html.parser import HTMLParser
+from liquid import Template
+
+# Same as used in Ruby (update.rb)
+DEFAULT_TAG_TEMPLATE = "{{major}}{% if minor %}.{{minor}}{% if patch %}.{{patch}}{%endif%}{%endif%}"
+
+def get_versions_from_headline(regex, headline, template):
+  if not isinstance(regex, list):
+    regex = [regex]
+  for r in regex:
+    matches = re.match(r.strip(), headline)
+    if matches:
+        match_data = matches.groupdict()
+        version_string = template.render(**match_data)
+        return version_string.split("\n")
+
+  return {}
+
+def fetch_releases(distrowatch_id, regex, template):
+    releases = {}
+    l_template = Template(template)
+    url = "https://distrowatch.com/index.php?distribution=%s" % distrowatch_id
+    with urllib.request.urlopen(url, data=None, timeout=5) as response:
+        soup = BeautifulSoup(response, features="html5lib")
+        for table in soup.select("td.News1>table.News"):
+            headline = table.select_one("td.NewsHeadline a[href]").get_text().strip()
+            date = table.select_one("td.NewsDate").get_text()
+            for v in get_versions_from_headline(regex, headline, l_template):
+              print("%s: %s" % (v, date))
+              releases[v] = date
+    return releases
+
+def update_releases():
+  for product_file in glob("website/products/*.md"):
+      product_name = os.path.splitext(os.path.basename(product_file))[0]
+      with open(product_file, "r") as f:
+          data = frontmatter.load(f)
+          if "auto" in data:
+              for config in data["auto"]:
+                  for key, d_id in config.items():
+                      if key == "distrowatch":
+                          update_product(product_name, config)
+
+def update_product(product_name, config):
+  t = config.get("template", DEFAULT_TAG_TEMPLATE)
+  if "regex" in config:
+      print("::group::%s" % product_name)
+      r = fetch_releases(config['distrowatch'], config["regex"], t)
+      with open("releases/%s.json" % product_name, "w") as f:
+          f.write(json.dumps(r, indent=2))
+      print("::endgroup::")
+
+if __name__ == "__main__":
+  update_releases()