added robots

Dockerfile

@@ -2,11 +2,9 @@ FROM python:3
 
 MAINTAINER tiyn tiyn@mail-mk.eu
 
-COPY src /blog
+ENV LANG en_US.UTF-8
-
+ENV LANGUAGE en_US:en
-WORKDIR /blog
+ENV LC_ALL en_US.UTF-8
-
-RUN pip3 install -r requirements.txt
 
 RUN apt-get update && \
     apt-get install -y locales && \
@@ -14,9 +12,13 @@ RUN apt-get update && \
     sed -i '/en_US.UTF-8/s/^# //g' /etc/locale.gen && \
     dpkg-reconfigure --frontend=noninteractive locales
 
-ENV LANG en_US.UTF-8
+RUN apt-get install -y espeak
-ENV LANGUAGE en_US:en
+
-ENV LC_ALL en_US.UTF-8
+COPY src /blog
+
+WORKDIR /blog
+
+RUN pip3 install -r requirements.txt
 
 VOLUME /blog/templates/entry
 

README.md

@@ -22,6 +22,7 @@ via plain text files.
   - [x] Links to standalone article
 - [x] Standalone article page
   - [x] Links to scrolling blog page
+  - [x] TTS Functionality
 - [x] RSS feed
 - [x] Navigation
   - [x] Header

src/app.py

@@ -1,4 +1,4 @@
-from flask import Flask, abort, make_response, render_template, request
+from flask import (Flask, abort, make_response, redirect, render_template, request, url_for)
 from flask_font_awesome import FontAwesome
 
 import config
@@ -28,8 +28,12 @@ def page_not_found(e):
                          language=LANGUAGE), 404
 
 
-@app.route("/")
 @app.route("/index.html")
+def index_re():
+  return redirect(url_for("index"))
+
+
+@app.route("/")
 def index():
   content = con_gen.gen_index_string()
   return render_template("index.html",
@@ -40,8 +44,12 @@ def index():
                          language=LANGUAGE)
 
 
-@app.route("/search", methods=["GET", "POST"])
 @app.route("/search.html", methods=["GET", "POST"])
+def search_re():
+  return redirect(url_for("search"))
+
+
+@app.route("/search", methods=["GET", "POST"])
 def search():
   form = SearchForm()
   if request.method == "POST":
@@ -63,8 +71,12 @@ def search():
                          language=LANGUAGE), 200
 
 
-@app.route("/imprint")
 @app.route("/imprint.html")
+def imprint_re():
+  return redirect(url_for("imprint"))
+
+
+@app.route("/imprint")
 def imprint():
   return render_template("imprint.html",
                          title=TITLE,
@@ -74,8 +86,12 @@ def imprint():
                          language=LANGUAGE)
 
 
-@app.route("/archive")
 @app.route("/archive.html")
+def archive_re():
+  return redirect(url_for("archive"))
+
+
+@app.route("/archive")
 def archive():
   content = con_gen.gen_arch_string()
   return render_template("archive.html",
@@ -101,17 +117,29 @@ def entry(path):
 
 @app.route("/feed.xml")
 @app.route("/rss.xml")
+@app.route("/rss")
+def feed_re():
+  return redirect(url_for("feed"))
+
+@app.route("/robots.txt")
+def robots():
+  return render_template("robots.txt")
+
+
+@app.route("/feed")
 def feed():
   content = con_gen.get_rss_string()
-  rss_xml = render_template("rss.xml",
+  feed_xml = render_template("feed.xml",
                              content_string=content,
                              title=TITLE,
                              description=DESCRIPTION,
-                            website=WEBSITE)
+                             website=WEBSITE,
-  response = make_response(rss_xml)
+                             language=LANGUAGE)
+  response = make_response(feed_xml)
   response.headers["Content-Type"] = "application/rss+xml"
   return response
 
 
 if __name__ == "__main__":
+  con_gen.prepare_tts()
   app.run(host="0.0.0.0")

src/config.py

@@ -21,3 +21,6 @@ MAIL = "dummy@mail.com"
 
 # Directory to store entries in
 ENTRY_DIR = "templates/entry"
+
+# Set the timezone of your blog
+TIMEZONE = "+0000"

src/content.py

@@ -1,17 +1,23 @@
+import glob
 import locale
 import os
 import pathlib
+import urllib.parse
 from datetime import datetime
 from os import path
 
 import markdown
+from bs4 import BeautifulSoup
+from gtts import gTTS, gTTSError
 
 import config
 import search
 
+WEBSITE = config.WEBSITE
 ENTRY_DIR = config.ENTRY_DIR
 LANGUAGE = config.LANGUAGE
 LOCAL = "de_DE.UTF-8" if LANGUAGE == "de-de" else "en_US.UTF-8"
+TIMEZONE = config.TIMEZONE
 
 locale.setlocale(locale.LC_TIME, LOCAL)
 
@@ -90,9 +96,32 @@ def gen_index_string():
       if file.endswith(".md"):
         content_string += gen_md_content(file, 2)
       content_string += "</div>"
+      content_string = absolutize_html(content_string)
   return content_string
 
 
+def absolutize_html(string):
+  """
+  Creates a html string from another string that only uses absolute links that use the full domain.
+
+  Parameters:
+  string: html-formatted string.
+
+  Returns:
+  string: html-formatted string with absolute linksn
+  """
+  soup = BeautifulSoup(string, "html.parser")
+  for a_tag in soup.find_all("a"):
+    href = str(a_tag.get("href"))
+    if href.startswith("/") or href.startswith("."):
+      a_tag["href"] = urllib.parse.urljoin(WEBSITE, href)
+  for img_tag in soup.find_all("img"):
+    src = str(img_tag.get("src"))
+    if src.startswith("/") or src.startswith("."):
+      img_tag["src"] = urllib.parse.urljoin(WEBSITE, src)
+  return str(soup)
+
+
 def gen_stand_string(path_ex):
   """
   Creates a html-string for a file.
@@ -117,11 +146,17 @@ def gen_stand_string(path_ex):
     content_string += "<a href=\"" + "/index.html#" + \
         filename_no_end + "\">" + curr_date + "</a>"
     content_string += "<br><br>\n"
+    if os.path.isfile("static/tmp/" + filename_no_end + ".mp3"):
+      content_string += "<audio controls>\n"
+      content_string += '<source src="/static/tmp/' + filename_no_end + '.mp3" type="audio/mp3">\n'
+      content_string += "</audio>\n"
+    content_string += "<br><br>\n"
     if filename.endswith(".html"):
       for line in text:
         content_string += line
     if filename.endswith(".md"):
       content_string += gen_md_content(filename, 1)
+    content_string = absolutize_html(content_string)
   return content_string
 
 
@@ -138,10 +173,8 @@ def gen_md_content(path_ex, depth):
   """
   content_string = ""
   if path.exists(path_ex):
-    filename = path_ex.split(".", 1)
-    fileend = filename[len(filename) - 1]
     header = "#"
-    for i in range(depth):
+    for _ in range(depth):
       header += "#"
     header += " "
     markdown_lines = open(path_ex, "r").readlines()[1:]
@@ -174,15 +207,19 @@ def get_rss_string():
         filename = filename.split(".", 1)[0]
       content_string += "<item>\n"
       content_string += "<title>" + title + "</title>\n"
-      content_string += "<guid>" + config.WEBSITE + \
+      content_string += "<guid>" + WEBSITE + \
           "/index.html#" + filename + "</guid>\n"
+      locale.setlocale(locale.LC_TIME, "en_US.UTF-8")
       content_string += "<pubDate>" + \
           datetime.fromtimestamp(os.path.getmtime(file)).strftime(
-              "%Y-%m-%d") + "</pubDate>\n"
+              "%a, %d %b %Y %H:%M:%S") + " " + TIMEZONE + "</pubDate>\n"
-      content_string += "<description>"
+      locale.setlocale(locale.LC_TIME, LOCAL)
+      content_string += "<description>\n<![CDATA[<html>\n<head>\n</head>\n<body>\n"
+      html_string = ""
       for line in text:
-        content_string += line
+        html_string += line
-      content_string += "</description>\n"
+      content_string += absolutize_html(html_string)
+      content_string += "\n</body></html>\n]]>\n</description>\n"
       content_string += "</item>\n"
   return content_string
 
@@ -231,20 +268,64 @@ def create_preview(path, is_markdown):
   string: html-formated preview
   """
   file = open(path, "r", encoding="utf-8")
-  first_lines = file.readlines()
+  lines = file.read()
-  preview = ""
-  preview_length = 3
-  for i, line in enumerate(first_lines):
-    if i == 0:
-      continue
-    if i > preview_length:
-      break
-    if not line.isspace():
   if is_markdown:
-        preview += markdown.markdown(line)
+    lines += markdown.markdown(lines)
-      else:
+  preview = ""
-        preview += line
+  first_p = BeautifulSoup(lines).find('p')
-    else:
+  if first_p is not None:
-      preview_length += 1
+    preview = "\n<p>" + first_p.text + "</p>\n"
-  preview += "<br>...<br>"
+  preview += "...<br>"
   return preview
+
+
+def get_text_only(filename):
+  """
+  Convert a file to text only to use in tts
+
+  Parameters:
+  path (string): path to the article
+
+  Returns:
+  string: unformatted string containing the contents of the file
+  """
+  # filename = os.path.join(ENTRY_DIR, path)
+  clean_text = ""
+  if path.exists(filename):
+    title = open(filename).readline().rstrip("\n")
+    text = open(filename).readlines()[1:]
+    filename_no_end = filename.split(".", 1)[0]
+    filename_no_end = filename_no_end.split("/")[-1]
+    content_string = ""
+    if filename.endswith(".html"):
+      for line in text:
+        content_string += line
+    if filename.endswith(".md"):
+      content_string += gen_md_content(filename, 1)
+    content_string = absolutize_html(content_string)
+    soup = BeautifulSoup(content_string, "html.parser")
+    tag_to_remove = soup.find("figure")
+    if tag_to_remove:
+      tag_to_remove.decompose()
+    clean_text = soup.get_text(separator=" ")
+    clean_text = title + "\n\n" + clean_text
+  return clean_text
+
+
+def prepare_tts():
+  files = glob.glob('static/tmp/*')
+  for f in files:
+    os.remove(f)
+  files = glob.glob('templates/entry/*')
+  clean_text = ""
+  for f in files:
+    clean_text = get_text_only(f)
+    _, tail = os.path.split(f)
+    new_filename = "static/tmp/" + os.path.splitext(tail)[0] + ".mp3"
+    try:
+      tts = gTTS(clean_text, lang=LANGUAGE.split("-")[0])
+      tts.save(new_filename)
+    except gTTSError as e:
+      print("Too many request to the google servers. Try it again later.")
+      os.remove(new_filename)
+      return e

src/requirements.txt

@@ -4,3 +4,5 @@ Whoosh
 WTForms
 Flask_WTF
 Font-Awesome-Flask
+BeautifulSoup4
+gTTS

src/search.py

@@ -14,7 +14,6 @@ ENTRY_DIR = config.ENTRY_DIR
 
 def createSearchableData(root):
   """
-
   Schema definition: title(name of file), path(as ID), content(indexed but not stored), textdata (stored text content)
   source:
   https://appliedmachinelearning.blog/2018/07/31/developing-a-fast-indexing-and-full-text-search-engine-with-whoosh-a-pure-pythhon-library/

src/static/css/light.css

@@ -76,7 +76,6 @@ span {
 }
 
 @media screen and (max-width:800px) {
-
   .main-menu {
     background: var(--menubg0);
   }

src/static/css/style.css

@@ -24,7 +24,6 @@ body {
 body,
 html {
   font-family: sans-serif;
-    height: 100%;
   max-width: 100%;
   overflow-x: hidden;
 }
@@ -32,6 +31,7 @@ html {
 footer {
   height: 100px;
   padding-top: 20px;
+  width: 100%;
 }
 
 footer .center {
@@ -39,11 +39,12 @@ footer .center {
 }
 
 .container {
-    min-height: 100%;
   padding-bottom: 50px;
   padding-left: 10%;
   padding-right: 10%;
-    padding-top: 5%;
+  padding-top: 5vh;
+  /* position: relative; */
+  min-height: calc(100vh - 50px - 5vh - 100px - 100px);
 }
 
 .container .flash {
@@ -80,6 +81,7 @@ footer .center {
 .main-menu-dropdown img {
   float: left;
 }
+
 .main-menu-dropdown span,
 .main-menu-dropdown a {
   float: left;
@@ -147,6 +149,7 @@ footer .center {
     transition: var(--transtime);
     width: 100%;
   }
+
   .main-menu a {
     display: block;
     padding: 20px;
@@ -161,8 +164,12 @@ form {
   margin-bottom: 40px;
 }
 
+.standalone {
+  min-height: 100vh;
+}
+
 .entry {
-    border-radius: 0 10px 30px 0;
+  /* border-radius: 0 10px 30px 0; */
   margin-bottom: 20px;
   padding-left: 20px;
 }
@@ -225,7 +232,7 @@ ol {
 }
 
 code {
-    border-radius: 25px;
+  /* border-radius: 25px; */
   padding-left: 20px;
   padding-right: 20px;
   page-break-inside: avoid;
@@ -246,7 +253,7 @@ form.search input[type=text] {
 form.search button[type=submit] {
   float: left;
   width: 5%;
-  padding: 12px;
+  padding: 10px;
   font-size: 17px;
   border: 1px solid grey;
   border-left: none; /* Prevent double borders */
@@ -258,3 +265,16 @@ form.search::after {
   clear: both;
   display: table;
 }
+
+.standalone img {
+  width: 50%;
+}
+
+.entry img {
+  width: 50%;
+}
+
+audio {
+    width: 50%;
+    height: 5vh;
+}

src/templates/feed.xml

@@ -5,8 +5,8 @@
     <title>{{ title }}</title>
     <description>{{ description }}</description>
     <language>{{ language }}</language>
-<link>{{ website }}/feed.xml</link>
+<link>{{ website }}</link>
-<atom:link href="/feed.xml" rel="self" type="application/rss+xml" />
+<atom:link href="{{ website }}{{ url_for('feed') }}" rel="self" type="application/rss+xml"/>
 
 {% autoescape off %}
 {{ content_string }}

src/templates/robots.txt

@@ -0,0 +1,2 @@
+User-agent: *
+Disallow: /static/

src/templates/template.html

@@ -1,11 +1,12 @@
-<html>
+<!DOCTYPE html>
+<html lang={% if language=="de-de" %}de{% else %}en{% endif %}>
 
 <head>
   <title>{{ title }}</title>
   <link href="{{ url_for('static', filename='css/' + style + '.css') }}" rel="stylesheet" type="text/css">
-  <link rel="icon" type="image/x-icon" href="{{ url_for('static', filename='graphics/logo.png') }}">
+  <link rel="icon" type="image/x-icon" href="{{ url_for('static', filename='graphics/logo.png')}}">
   <meta charset="utf-8">
-  <meta name="viewport" content="width=device-width" initial-scale=1.0>
+  <meta name="viewport" content="width=device-width">
   {{ font_awesome.load_js() }}
 </head>
 
@@ -13,7 +14,9 @@
   <!-- Menu -->
   <div class="main-menu-dropdown">
     <a href="{{ url_for('index') }}">
-      <img class="logo" src="{{ url_for('static', filename='graphics/logo.png') }}">
+      <img class="logo" src="{{ url_for('static', filename='graphics/logo.png') }}" alt="Logo von
+      Mittelerde mit Marten. Zu sehen sind 3 'M's mit Serifen, wobei die beiden Äußeren etwas
+      kleiner sind">
       {{ stitle }}
     </a>
     <input type="checkbox" id="main-menu-check">
@@ -32,9 +35,9 @@
   <!-- Content -->
   <footer>
     <div class="center">
-      <a href="{{ url_for('imprint') }}">
+      <a href="{{ url_for('imprint') }}">{% if language=="de-de" %}Impressum und Kontakt{% else %}Imprint and Contact{%
-        {% if language=="de-de" %}Impressum und Kontakt{% else %}Imprint and Contact{% endif %}
+        endif %}</a>.<br>
-      </a><br>
+      <a href="{{ url_for('feed') }}">{% if language=="de-de" %}RSS-Feed{% else %}RSS feed{% endif %}</a>.<br>
       Made with <a href="https://github.com/tiyn/beaker-blog">Beaker Blog</a>.
     </div>
   </footer>