fix(main): Fixed error in hashtag display

.chglog/CHANGELOG.tpl.md

@@ -0,0 +1,38 @@
+{{ with index .Versions 0 }}
+<a name="{{ .Tag.Name }}"></a>
+## {{ if .Tag.Previous }}[{{ .Tag.Name }}]({{ $.Info.RepositoryURL }}/compare/{{ .Tag.Previous.Name }}...{{ .Tag.Name }}){{ else }}{{ .Tag.Name }}{{ end }} ({{ datetime "2006-01-02" .Tag.Date }})
+
+{{ range .CommitGroups -}}
+### {{ .Title }}
+
+{{ range .Commits -}}
+* {{ if .Scope }}**{{ .Scope }}:** {{ end }}{{ .Subject }} ([{{ .Hash.Short }}]({{ $.Info.RepositoryURL }}/commit/{{ .Hash.Short }}))
+{{ end }}
+{{ end -}}
+
+{{- if .RevertCommits -}}
+### Reverts
+
+{{ range .RevertCommits -}}
+* {{ .Revert.Header }} ([{{ .Hash.Short }}]({{ $.Info.RepositoryURL }}/commit/{{ .Hash.Short }}))
+{{ end }}
+{{ end -}}
+
+{{- if .MergeCommits -}}
+### Pull Requests
+
+{{ range .MergeCommits -}}
+* {{ .Header }} ([{{ .Hash.Short }}]({{ $.Info.RepositoryURL }}/commit/{{ .Hash.Short }}))
+{{ end }}
+{{ end -}}
+
+{{- if .NoteGroups -}}
+{{ range .NoteGroups -}}
+### {{ .Title }}
+
+{{ range .Notes }}
+{{ .Body }}
+{{ end }}
+{{ end -}}
+{{ end -}}
+{{ end }}

.chglog/config.yml

@@ -0,0 +1,37 @@
+style: github
+template: CHANGELOG.tpl.md
+
+info:
+  title: CHANGELOG
+  repository_url: https://dev.ksite.de/ralf.kirchner/BlueMastoFeed
+
+options:
+  commits:
+    sort_by: "date"           # Optional, default is OK too
+    exclude_merge_commits: false
+
+  commit_groups:
+    group_by: "Type"
+    title_maps:
+      feat: Features
+      fix: Bug Fixes
+      perf: Performance Improvements
+      refactor: Code Refactoring
+      docs: Documentation
+      chore: Maintenance
+      test: Tests
+      build: Build System
+      ci: Continuous Integration
+      style: Code Style
+
+  header:
+    pattern: "^(\\w*)(?:\\(([\\w\\$\\.\\-\\*\\s]*)\\))?\\:\\s(.*)$"
+    pattern_maps:
+      - Type
+      - Scope
+      - Subject
+
+  notes:
+    keywords:
+      - BREAKING CHANGE
+      - DEPRECATED

.gitea/workflows/release.yml

@@ -0,0 +1,100 @@
+name: Create Release
+
+on:
+  push:
+    tags:
+      - 'v*'  # Nur bei Tags wie v1.0.0, v2.0.0
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Enable debug output
+        run: set -x
+
+      - name: Checkout full history including tags
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Show environment variables for debugging
+        run: |
+          echo "GIT_REMOTE_URL=$(git config --get remote.origin.url)"
+          echo "GITHUB_REF=$GITHUB_REF"
+
+      - name: Extract OWNER and REPO from git remote URL
+        id: repo-info
+        run: |
+          REMOTE_URL=$(git config --get remote.origin.url)
+          OWNER=$(echo "$REMOTE_URL" | sed -E 's#.*/([^/]+)/([^/]+)(\.git)?#\1#')
+          REPO=$(echo "$REMOTE_URL" | sed -E 's#.*/([^/]+)/([^/]+)(\.git)?#\2#')
+          echo "OWNER=$OWNER" >> $GITHUB_ENV
+          echo "REPO=$REPO" >> $GITHUB_ENV
+
+      - name: Install git-chglog binary (no Go needed)
+        run: |
+          GIT_CHGLOG_VERSION="0.15.1"
+          curl -sSL "https://github.com/git-chglog/git-chglog/releases/download/v${GIT_CHGLOG_VERSION}/git-chglog_${GIT_CHGLOG_VERSION}_linux_amd64.tar.gz" -o git-chglog.tar.gz
+          tar -xzf git-chglog.tar.gz
+          chmod +x git-chglog
+          sudo mv git-chglog /usr/local/bin/
+
+      - name: Determine current and previous tag
+        id: tags
+        run: |
+          CURRENT_TAG="${GITHUB_REF##*/}"
+          PREVIOUS_TAG=$(git describe --tags --abbrev=0 "${CURRENT_TAG}^" 2>/dev/null || true)
+
+          echo "CURRENT_TAG=$CURRENT_TAG"
+          echo "PREVIOUS_TAG=$PREVIOUS_TAG"
+
+          echo "CURRENT_TAG=$CURRENT_TAG" >> $GITHUB_ENV
+          echo "PREVIOUS_TAG=$PREVIOUS_TAG" >> $GITHUB_ENV
+
+      - name: Generate CHANGELOG.md
+        run: |
+          # Optional: kompletter Changelog (nicht für Release-Body)
+          git-chglog -o CHANGELOG.md
+
+          # Nur der relevante Abschnitt zwischen Tags
+          if [ -n "$PREVIOUS_TAG" ]; then
+            git-chglog "$PREVIOUS_TAG..$CURRENT_TAG" > RELEASE_BODY.md
+          else
+            git-chglog "$CURRENT_TAG" > RELEASE_BODY.md
+          fi
+
+          echo "Release changelog content:"
+          cat RELEASE_BODY.md
+
+      - name: Replace issue references with Markdown links
+        env:
+          OWNER: ${{ env.OWNER }}
+          REPO: ${{ env.REPO }}
+        run: |
+          sed -i -E "s/([^\\[])#([0-9]+)/\1[#\2](https:\/\/dev.ksite.de\/${OWNER}\/${REPO}\/issues\/\2)/g" RELEASE_BODY.md
+
+      - name: Create Gitea Release via API
+        env:
+          TOKEN: ${{ secrets.TOKEN }}
+          OWNER: ${{ env.OWNER }}
+          REPO: ${{ env.REPO }}
+          CURRENT_TAG: ${{ env.CURRENT_TAG }}
+        run: |
+          # Base64-encode und sicher escapen für JSON
+          BODY=$(base64 -w0 RELEASE_BODY.md)
+          DECODED_BODY=$(echo "$BODY" | base64 -d | jq -Rs .)
+
+          echo "Creating release for tag $CURRENT_TAG"
+
+          curl -s -X POST "https://dev.ksite.de/api/v1/repos/${OWNER}/${REPO}/releases" \
+            -H "Content-Type: application/json" \
+            -H "Authorization: token $TOKEN" \
+            -d @- <<EOF
+          {
+            "tag_name": "${CURRENT_TAG}",
+            "name": "${REPO} ${CURRENT_TAG}",
+            "body": ${DECODED_BODY}
+          }
+          EOF

.gitignore

@@ -2,3 +2,12 @@
 data/*
 !data/.gitkeep
 
+# Config & meta
+CHANGELOG.md
+ENVIRONMENT.md
+
+# IDEs / Editor
+.vscode/
+.idea/
+.DS_Store
+

Dockerfile

@@ -1,5 +1,5 @@
 FROM python:3.11-slim
-LABEL version="0.9.0"
+LABEL version="0.9.6"
 
 RUN apt-get update && apt-get install -y curl && apt-get clean && rm -rf /var/lib/apt/lists/*
 
@@ -15,3 +15,5 @@ HEALTHCHECK --interval=1m --timeout=5s --start-period=10s --retries=3 \
 
 EXPOSE 8000
 
+
+

README.md

@@ -2,7 +2,19 @@
 
 **BlueMastoFeed** ist ein Docker-basiertes Tool, das regelmäßig einen RSS-Feed ausliest und neue Beiträge automatisch auf **Mastodon** und **Bluesky** veröffentlicht. 
 
-Es prüft, ob ein Beitrag bereits gepostet wurde, und speichert diese Information lokal in einer Datei (`/data/seen_posts.txt`). Optional werden OpenGraph-Daten (Titel, Vorschau-Bild etc.) der verlinkten Seiten extrahiert, um die Posts ansprechender zu gestalten.
+
+
+## Features
+
+- RSS-Feed regelmäßig auslesen
+- Postfilterung nach Alter (`MAX_POST_AGE_DAYS`)
+- Verhindert doppelte Posts mit Hilfe einer persistierten ID-Liste
+- Posten auf:
+  - ✅ Mastodon
+  - ✅ Bluesky
+  - ✅ Beides (konfigurierbar über `.env`)
+- Optionaler E-Mail-Versand bei Erfolg oder Fehler
+- Healthcheck-Endpoint auf Port 8000
 
 
 
@@ -87,6 +99,7 @@ Die folgenden Umgebungsvariablen steuern das Verhalten des Containers. Sie könn
 | ----------------------- | ------------------------------------------------------------ | -------------------------- | -------------- |
 | `FEED_URL`              | URL zum RSS- oder Atom-Feed                                  | `https://example.com/feed` | _erforderlich_ |
 | `MAX_POST_AGE_DAYS`     | Maximales Alter eines Beitrags (in Tagen), der gepostet werden darf | `0` = nur heutige Beiträge | `0`            |
+| `POST_TARGETS`          | Zielplattform(en): `mastodon`, `bluesky`, `both`             | `mastodon` = nur Mastodon  | `both`         |
 | `MASTODON_API_BASE_URL` | Basis-URL deiner Mastodon-Instanz                            | `https://mastodon.social`  | _erforderlich_ |
 | `MASTODON_ACCESS_TOKEN` | Access Token für die Mastodon API                            | `abc123...`                | _erforderlich_ |
 | `BSKY_IDENTIFIER`       | Bluesky-Handle                                               | `name.bsky.social`         | _erforderlich_ |

bluemastofeed.py

@@ -1,11 +1,12 @@
 import os
 import time
 import feedparser
-import json
 import logging
 import requests
 import threading
 import smtplib
+import re
+import unicodedata
 from bs4 import BeautifulSoup
 from io import BytesIO
 from mastodon import Mastodon
@@ -18,6 +19,7 @@ from dateutil import parser as date_parser
 from datetime import datetime, timezone, timedelta
 
 load_dotenv()
+
 FEED_URL = os.getenv("FEED_URL")
 SEEN_POSTS_FILE = "/data/seen_posts.txt"
 MASTODON_BASE_URL = os.getenv("MASTODON_API_BASE_URL")
@@ -25,6 +27,7 @@ MASTODON_TOKEN = os.getenv("MASTODON_ACCESS_TOKEN")
 BSKY_HANDLE = os.getenv("BSKY_IDENTIFIER")
 BSKY_PASSWORD = os.getenv("BSKY_PASSWORD")
 MAX_POST_AGE_DAYS = int(os.getenv("MAX_POST_AGE_DAYS", 0))
+POST_TARGETS = os.getenv("POST_TARGETS", "both").lower()
 
 logger = logging.getLogger()
 logger.setLevel(logging.INFO)
@@ -35,7 +38,6 @@ logger.addHandler(handler)
 
 
 class HealthHandler(BaseHTTPRequestHandler):
-    """Handles HTTP GET requests for the health check endpoint."""
     def do_GET(self):
         if self.path == "/health":
             self.send_response(200)
@@ -46,26 +48,99 @@ class HealthHandler(BaseHTTPRequestHandler):
             self.end_headers()
 
     def log_message(self, format, *args):
-        """Suppress default HTTP request logging."""
         pass
 
 
 def start_health_server():
-    """Starts the health check HTTP server in a background thread."""
     server = HTTPServer(("0.0.0.0", 8000), HealthHandler)
     thread = threading.Thread(target=server.serve_forever, daemon=True)
     thread.start()
-    logger.info("Healthcheck server is running on port 8000.")
+    logger.info(f"💡 Healthcheck server running on port 8000.")
 
 
 def should_send_email(on_success: bool):
-    """Determines whether to send a status email based on mode and success."""
     mode = os.getenv("EMAIL_MODE", "errors").lower()
     return (mode == "all") or (mode == "errors" and not on_success)
 
 
+def extract_facets_utf8(text: str):
+    import re
+    facets = []
+    def get_byte_range(char_start, char_end):
+        byte_start = len(text[:char_start].encode("utf-8"))
+        byte_end = len(text[:char_end].encode("utf-8"))
+        return byte_start, byte_end
+
+    # Hashtags
+    for match in re.finditer(r"#(\w+)", text):
+        tag = match.group(1)
+        char_start, char_end = match.span()
+        byte_start, byte_end = get_byte_range(char_start, char_end)
+
+        facets.append({
+            "index": {"byteStart": byte_start, "byteEnd": byte_end},
+            "features": [{
+                "$type": "app.bsky.richtext.facet#tag",
+                "tag": tag
+            }]
+        })
+
+    # Links
+    for match in re.finditer(r"https?://[^\s]+", text):
+        url = match.group(0)
+        char_start, char_end = match.span()
+        byte_start, byte_end = get_byte_range(char_start, char_end)
+
+        facets.append({
+            "index": {"byteStart": byte_start, "byteEnd": byte_end},
+            "features": [{
+                "$type": "app.bsky.richtext.facet#link",
+                "uri": url
+            }]
+        })
+
+    return facets
+
+
+def generate_email_html(status: str, title: str, link: str, error_message: str = None) -> str:
+    color = "#2e7d32" if status == "success" else "#d32f2f"
+    bg_color = "#f5f5f5" if status == "success" else "#fff3f3"
+    border_color = "#ccc" if status == "success" else "#e57373"
+    emoji = "✅" if status == "success" else "❌"
+    heading = "Post Published" if status == "success" else "Error Posting Entry"
+    meta = "This is an automated success notification." if status == "success" else "Please check logs or configuration."
+
+    error_html = f"""
+        <p><strong>Error:</strong></p>
+        <div class=\"error\">{error_message}</div>
+    """ if error_message else ""
+
+    return f"""
+    <html>
+    <head>
+        <style>
+            body {{ font-family: 'Courier New', monospace; background-color: {bg_color}; color: #333; padding: 20px; }}
+            .container {{ background-color: #ffffff; border: 1px solid {border_color}; border-radius: 8px; padding: 20px; max-width: 600px; margin: auto; }}
+            h2 {{ color: {color}; }}
+            a {{ color: #1a73e8; text-decoration: none; }}
+            .error {{ font-family: monospace; background-color: #fce4ec; padding: 10px; border-radius: 4px; color: #b71c1c; }}
+            .meta {{ font-size: 14px; color: #777; }}
+        </style>
+    </head>
+    <body>
+        <div class=\"container\">
+            <h2>{emoji} {heading}</h2>
+            <p><strong>Title:</strong><br>{title}</p>
+            <p><strong>Link:</strong><br><a href=\"{link}\">{link}</a></p>
+            {error_html}
+            <p class=\"meta\">{meta}</p>
+        </div>
+    </body>
+    </html>
+    """
+
+
 def send_status_email(subject, html_content):
-    """Sends a formatted HTML email with the given subject and content."""
     try:
         smtp_host = os.getenv("SMTP_HOST")
         smtp_port = int(os.getenv("SMTP_PORT", 587))
@@ -84,13 +159,13 @@ def send_status_email(subject, html_content):
             server.starttls()
             server.login(smtp_user, smtp_password)
             server.sendmail(email_from, email_to, msg.as_string())
-        logger.info("Status email sent.")
+
+        logger.info(f"✅ Status email sent successfully.")
     except Exception as e:
-        logger.error(f"Error sending status email: {e}")
+        logger.error(f"❌ Error sending email: {e}")
 
 
 def load_seen_ids():
-    """Loads the set of already seen post IDs from file."""
     os.makedirs(os.path.dirname(SEEN_POSTS_FILE), exist_ok=True)
     if not os.path.exists(SEEN_POSTS_FILE):
         open(SEEN_POSTS_FILE, "w").close()
@@ -99,19 +174,20 @@ def load_seen_ids():
 
 
 def save_seen_id(post_id):
-    """Appends a new post ID to the seen posts file."""
     with open(SEEN_POSTS_FILE, "a") as f:
         f.write(post_id + "\n")
 
 
-def post_to_mastodon(message):
-    """Posts a message to Mastodon."""
+def post_to_mastodon(title, link, tags):
     mastodon = Mastodon(access_token=MASTODON_TOKEN, api_base_url=MASTODON_BASE_URL)
+    hashtags = " ".join(f"#{tag}" for tag in tags) if tags else ""
+    message = f"{title}\n\n{link}"
+    if hashtags:
+        message += f"\n\n{hashtags}"
     mastodon.toot(message)
 
 
 def fetch_og_data(url):
-    """Fetches Open Graph title and image URL from a web page."""
     try:
         resp = requests.get(url, timeout=10)
         resp.raise_for_status()
@@ -122,20 +198,25 @@ def fetch_og_data(url):
         image_url = og_image["content"] if og_image and og_image.has_attr("content") else None
         return title, image_url
     except Exception as e:
-        logger.error(f"Error loading OG data: {e}")
+        logger.error(f"❌ Error fetching OG data: {e}")
         return None, None
 
 
-def post_to_bluesky(message, link):
-    """Posts a message and optional preview to Bluesky."""
+def post_to_bluesky(title, link, tags):
     client = Client()
     client.login(BSKY_HANDLE, BSKY_PASSWORD)
 
-    title, image_url = fetch_og_data(link)
-    text = title or message
+    hashtags = " ".join(f"#{tag}" for tag in tags) if tags else ""
+    message = f"{title}\n\n{link}"
+    if hashtags:
+        message += f"\n\n{hashtags}"
 
-    if title and image_url:
-        try:
+    facets = extract_facets_utf8(message)  # <-- NEU
+
+    # Versuche OG-Vorschau
+    try:
+        og_title, image_url = fetch_og_data(link)
+        if og_title and image_url:
             embed = {
                 "$type": "app.bsky.embed.external",
                 "external": {
@@ -156,18 +237,19 @@ def post_to_bluesky(message, link):
             blob = client.upload_blob(BytesIO(img_resp.content))
             embed["external"]["thumb"] = blob.blob
 
-            client.send_post(text=text, embed=embed)
-            logger.info("Posted with OG preview.")
+            client.send_post(text=message, embed=embed, facets=facets)  # <-- facets hier
+            logger.info(f"✅ Posted to Bluesky with preview.")
             return
-        except Exception as e:
-            logger.error(f"Error uploading OG preview: {e}")
+    except Exception as e:
+        logger.error(f"❌ Error uploading preview to Bluesky: {e}")
+
+    # Fallback: Nur Text, aber mit Facets
+    client.send_post(text=message, facets=facets)  # <-- facets hier
+    logger.info(f"💡 Posted to Bluesky without preview.")
 
-    client.send_post(f"{text}\n{link}")
-    logger.info("Posted without preview.")
 
 
 def extract_post_date(entry):
-    """Extracts the oldest available date from various RSS date fields."""
     date_fields = [
         entry.get("published"),
         entry.get("updated"),
@@ -185,13 +267,12 @@ def extract_post_date(entry):
                     dt = dt.replace(tzinfo=timezone.utc)
                 dates.append(dt)
             except Exception as e:
-                logger.warning(f"⚠️ Cannot parse date field: {d} ({e})")
+                logger.warning(f"⚠️ Could not parse date: {d} ({e})")
 
     return min(dates) if dates else datetime.now(timezone.utc)
 
 
 def main():
-    """Main function to process feed entries and post new items."""
     seen_ids = load_seen_ids()
     feed = feedparser.parse(FEED_URL)
     now = datetime.now(timezone.utc)
@@ -206,37 +287,60 @@ def main():
         age = now - post_date
         age_days = age.days
         age_hours = age.seconds // 3600
-        logger.info(f"Post '{entry.get('title', '').strip()}' is {age_days} days and {age_hours} hours old.")
+        #logger.info(f"Post '{entry.get('title', '').strip()}' is {age_days} days and {age_hours} hours old.")
 
         if post_date < now - max_age:
-            logger.info(f"⏩ Skipping old post (older than {MAX_POST_AGE_DAYS} days): {post_id}")
+            logger.info(f"⏩ Skipping old post ({MAX_POST_AGE_DAYS}+ days): {post_id}")
             continue
 
         title = entry.get("title", "").strip()
         link = entry.get("link", "").strip()
-        message = link
 
-        logger.info(f"New post: {title}")
+        def sanitize_tag(tag):
+            tag = tag.lower()
+            tag = unicodedata.normalize("NFKD", tag).encode("ascii", "ignore").decode("ascii")
+            tag = re.sub(r"\W+", "", tag)
+            return tag
+
+        tags = []
+        if "tags" in entry:
+            raw_tags = [
+                tag.get("term") if isinstance(tag, dict) else getattr(tag, "term", None)
+                for tag in entry.tags
+            ]
+            tags = [sanitize_tag(t) for t in raw_tags if t]
+
+        if tags:
+            hashtags = " ".join(f"#{tag}" for tag in tags)
+            message = f"{link} {hashtags}"
+        else:
+            message = link
+
+        logger.info(f"💡 New post found: {title}")
 
         try:
-            post_to_mastodon(message)
-            time.sleep(2)
-            post_to_bluesky(message, link)
+            if POST_TARGETS in ("mastodon", "both"):
+                post_to_mastodon(title, link, tags)
+                time.sleep(2)
+
+            if POST_TARGETS in ("bluesky", "both"):
+                post_to_bluesky(title, link, tags)
+
             save_seen_id(post_id)
-            logger.info("✅ Successfully posted.")
+            logger.info(f"✅ Post successfully published.")
 
             if should_send_email(on_success=True):
                 send_status_email(
-                    f"✅ Successfully posted: {title}",
-                    f"<html><body><h2>Post successfully published</h2><p><b>Title:</b> {title}</p><p><b>Link:</b> <a href='{link}'>{link}</a></p></body></html>"
+                    f"✅ Post published: {title}",
+                    generate_email_html("success", title, link)
                 )
 
         except Exception as e:
-            logger.error(f"❌ Error posting: {e}")
+            logger.error(f"❌ Posting failed: {e}")
             if should_send_email(on_success=False):
                 send_status_email(
                     f"❌ Error posting: {title}",
-                    f"<html><body><h2>Error posting</h2><p><b>Title:</b> {title}</p><p><b>Link:</b> <a href='{link}'>{link}</a></p><p><b>Error message:</b> {str(e)}</p></body></html>"
+                    generate_email_html("error", title, link, str(e))
                 )
 
         time.sleep(5)
@@ -244,7 +348,7 @@ def main():
 
 if __name__ == "__main__":
     INTERVAL_MINUTES = int(os.getenv("INTERVAL_MINUTES", 30))
-    logger.info(f"Start feed check every {INTERVAL_MINUTES} minutes.")
+    logger.info(f"🔁 Starting feed check every {INTERVAL_MINUTES} minutes.")
 
     start_health_server()
 
@@ -252,7 +356,7 @@ if __name__ == "__main__":
         try:
             main()
         except Exception as e:
-            logger.error(f"Error in main execution: {e}")
-        logger.info(f"Wait {INTERVAL_MINUTES} minutes until next execution...")
+            logger.error(f"Unhandled error during execution: {e}")
+        logger.info(f"⏳ Waiting {INTERVAL_MINUTES} minutes until next run...")
         time.sleep(INTERVAL_MINUTES * 60)
 

env

@@ -9,6 +9,9 @@ MASTODON_ACCESS_TOKEN=your_mastodon_access_token
 BSKY_IDENTIFIER=your_handle.bsky.social
 BSKY_PASSWORD=your_bluesky_password
 
+# mögliche Werte: mastodon, bluesky, both
+POST_TARGETS=both
+
 # Intervall in Minuten für Feedprüfung
 INTERVAL_MINUTES=30
 

requirements.txt

@@ -5,3 +5,4 @@ python-dotenv
 beautifulsoup4
 python-dateutil
 requests
+