initial commit

Dockerfile

@@ -0,0 +1,8 @@
+FROM python:3.8
+RUN mkdir /app
+WORKDIR /app
+ADD . /app/
+RUN pip install -r requirements.txt
+EXPOSE 5000
+ENV FLASK_APP=main
+CMD ["python", "main.py"]

config.py

@@ -0,0 +1,16 @@
+import os
+from werkzeug.security import generate_password_hash
+
+#CONTENT_BASE_DIR = os.getenv("CONTENT_BASE_DIR", "/library")
+CONTENT_BASE_DIR = os.getenv("CONTENT_BASE_DIR", "/home/drudoo/ComicsTest/Comics")
+
+TEENYOPDS_ADMIN_PASSWORD = os.getenv("TEENYOPDS_ADMIN_PASSWORD", None)
+users = {}
+if TEENYOPDS_ADMIN_PASSWORD:
+    users = {
+        "admin": generate_password_hash(TEENYOPDS_ADMIN_PASSWORD),
+    }
+else:
+    print(
+        "WANRNING: admin password not configured - catalog will be exposed was public"
+    )

main.py

@@ -0,0 +1,89 @@
+from flask import Flask, send_from_directory, request
+from flask_httpauth import HTTPBasicAuth
+from werkzeug.security import check_password_hash
+from gevent.pywsgi import WSGIServer
+import timeit
+import sqlite3
+import os
+import zipfile
+from bs4 import BeautifulSoup
+import re
+import datetime
+import sys
+
+from opds import fromdir
+import config
+
+app = Flask(__name__, static_url_path="", static_folder="static")
+auth = HTTPBasicAuth()
+
+
+@auth.verify_password
+def verify_password(username, password):
+    if not config.TEENYOPDS_ADMIN_PASSWORD:
+        return True
+    elif username in config.users and check_password_hash(
+        config.users.get(username), password
+    ):
+        return username
+
+
+@app.route("/")
+@app.route("/healthz")
+def healthz():
+    return "ok"
+
+@app.route('/import')
+def import2sql():
+    conn = sqlite3.connect('app.db')
+    list = []
+
+    for root, dirs, files in os.walk(os.path.abspath(config.CONTENT_BASE_DIR)):
+        for file in files:
+            f = os.path.join(root, file)
+            s = zipfile.ZipFile(f)
+            Bs_data = BeautifulSoup(s.open('ComicInfo.xml').read(), "xml")
+            #print(Bs_data.select('Series')[0].text, file=sys.stderr)
+            #print(Bs_data.select('Title')[0].text, file=sys.stderr)
+            CVDB=re.findall('(?<=\[CVDB)(.*)(?=].)', Bs_data.select('Notes')[0].text)
+            #list.append('CVDB'+CVDB[0] + ': '  + Bs_data.select('Series')[0].text + "(" + Bs_data.select('Volume')[0].text + ") : " + Bs_data.select('Number')[0].text  )
+            #print(list, file=sys.stdout)
+            
+            ISSUE=Bs_data.select('Number')[0].text
+            SERIES=Bs_data.select('Series')[0].text
+            VOLUME=Bs_data.select('Volume')[0].text
+            PUBLISHER=Bs_data.select('Publisher')[0].text
+            TITLE=Bs_data.select('Title')[0].text
+            PATH=f 
+            UPDATED=str(datetime.datetime.now())
+            print(UPDATED,file=sys.stdout)
+            sql="INSERT OR REPLACE INTO COMICS (CVDB,ISSUE,SERIES,VOLUME, PUBLISHER, TITLE, FILE,PATH,UPDATED) VALUES ("+CVDB[0]+",'"+ISSUE+"','"+SERIES+"','"+VOLUME+"','"+PUBLISHER+"','"+TITLE+"','"+file+"','" + f + "','" + UPDATED + "')"
+            print(sql,file=sys.stdout)
+            conn.execute(sql);
+            conn.commit()
+    
+    conn.close()
+    return "yay"
+
+@app.route("/content/<path:path>")
+@auth.login_required
+def send_content(path):
+    return send_from_directory(config.CONTENT_BASE_DIR, path)
+
+@app.route("/catalog")
+@app.route("/catalog/<path:path>")
+@auth.login_required
+def catalog(path=""):
+    start_time = timeit.default_timer()
+    print(request.root_url) 
+    c = fromdir(request.root_url, request.url, config.CONTENT_BASE_DIR, path)
+    elapsed = timeit.default_timer() - start_time
+    print(elapsed)
+    
+    return c.render()
+
+
+if __name__ == "__main__":
+    #http_server = WSGIServer(("", 5000), app)
+    #http_server.serve_forever()
+    app.run(debug=True,host='0.0.0.0')

metadata.py

@@ -0,0 +1,16 @@
+import requests
+
+
+def fromisbn(isbn: str):
+    isbn = "".join(filter(str.isnumeric, isbn))
+    api = f"https://www.googleapis.com/books/v1/volumes?q=isbn:{isbn}"
+    resp = requests.get(api)
+    return resp.json()["items"][0]
+
+
+if __name__ == "__main__":
+    from pprint import pprint
+
+    pprint(fromisbn("9780316029193"))
+    pprint(fromisbn("978-0316029193"))
+    pprint(fromisbn("0316029193"))

opds/__init__.py

@@ -0,0 +1 @@
+from .catalog import Catalog, fromdir

opds/catalog.py

@@ -0,0 +1,136 @@
+import os
+from uuid import uuid4
+from urllib.parse import quote
+from jinja2 import Environment, FileSystemLoader, select_autoescape
+from .entry import Entry
+from .link import Link
+import sqlite3
+
+
+class Catalog(object):
+    def __init__(
+        self,
+        title,
+        id=None,
+        author_name=None,
+        author_uri=None,
+        root_url=None,
+        url=None,
+    ):
+        self.title = title
+        self.id = id or uuid4()
+        self.author_name = author_name
+        self.author_uri = author_uri
+        self.root_url = root_url
+        self.url = url
+        self.entries = []
+
+    def add_entry(self, entry):
+        self.entries.append(entry)
+
+    def render(self):
+        env = Environment(
+            loader=FileSystemLoader(
+                searchpath=os.path.join(os.path.dirname(__file__), "templates")
+            ),
+            autoescape=select_autoescape(["html", "xml"]),
+        )
+        template = env.get_template("catalog.opds.jinja2")
+        return template.render(catalog=self)
+
+def fromsearch(root_url, url, content_base_path, content_relative_path):
+
+    c = Catalog(
+        title="test"
+    )
+        
+    return c
+
+def fromdir(root_url, url, content_base_path, content_relative_path):
+    
+    path = os.path.join(content_base_path, content_relative_path)
+    #print(path)
+    c = Catalog(
+        title=os.path.basename(os.path.dirname(path)), root_url=root_url, url=url
+    )
+    #print(c.url)
+    if not "search" in c.url:
+        onlydirs = [
+            f for f in os.listdir(path) if not os.path.isfile(os.path.join(path, f))
+        ]
+    #print(onlydirs)
+        for dirname in onlydirs:
+            link = Link(
+                href=quote(f"/catalog/{content_relative_path}/{dirname}"),
+                rel="subsection",
+                rpath=path,
+                type="application/atom+xml;profile=opds-catalog;kind=acquisition",
+            )
+            c.add_entry(Entry(title=dirname, id=uuid4(), links=[link]))
+
+    
+    if c.url.endswith("/catalog"):
+        link2 = Link(
+            href=quote(f"/catalog/search"),
+            rel="subsection",
+            rpath=path,
+            type="application/atom+xml;profile=opds-catalog;kind=acquisition",
+        )
+        c.add_entry(Entry(title="Search",id=uuid4(),links=[link2]))
+
+    if not "search" in c.url:
+        onlyfiles = [f for f in os.listdir(path) if os.path.isfile(os.path.join(path, f))]
+        #print(onlyfiles)
+        for filename in onlyfiles:
+            link = Link(
+                href=quote(f"/content/{content_relative_path}/{filename}"),
+                rel="http://opds-spec.org/acquisition",
+                rpath=path,
+                type=mimetype(filename),
+            )
+            c.add_entry(Entry(title=filename.rsplit(".",1)[0], id=uuid4(), links=[link]))
+            #fixed issue with multiple . in filename
+            #print(c.render()) 
+    else:
+        search="Man"
+        conn = sqlite3.connect('app.db')
+        sql="SELECT * from COMICS where SERIES like '%" + search+ "%' or Title like '%" + search+ "%';"
+    
+        s = conn.execute(sql)
+        list=[] 
+        for r in s:
+            #print(r)
+            tUrl=f""+r[7].replace("/home/drudoo/ComicsTest/Comics/","/content/")
+            tTitle=r[6]
+            link3 = Link(
+                #href=quote(f"/content/DC Comics/Earth Cities/Gotham City/Batgirl/Annual/(2012) Batgirl Annual/Batgirl Annual #001 - The Blood That Moves Us [December, 2012].cbz"),
+                href=quote(tUrl),
+                rel="http://opds-spec.org/acquisition",
+                rpath=path,
+                type="application/x-cbz",
+            )
+            c.add_entry(
+                Entry(
+                    title=tTitle,
+                    id=uuid4(),
+                    links=[link3]
+                    )
+                )
+
+
+    return c
+
+
+
+def mimetype(path):
+    extension = path.split(".")[-1].lower()
+    if extension == "pdf":
+        return "application/pdf"
+    elif extension == "epub":
+        return "application/epub"
+    elif extension == "mobi":
+        return "application/mobi"
+    elif extension == "cbz":
+        return "application/x-cbz"
+    else:
+        return "application/unknown"

opds/entry.py

@@ -0,0 +1,77 @@
+import zipfile
+from bs4 import BeautifulSoup
+import os
+
+class Entry(object):
+    valid_keys = (
+        "id",
+        "url",
+        "title",
+        "content",
+        "downloadsPerMonth",
+        "updated",
+        "identifier",
+        "date",
+        "rights",
+        "summary",
+        "dcterms_source",
+        "provider",
+        "publishers",
+        "contributors",
+        "languages",
+        "subjects",
+        "oai_updatedates",
+        "authors",
+        "formats",
+        "links",
+    )
+
+    required_keys = ("id", "title", "links")
+
+    def validate(self, key, value):
+        if key not in Entry.valid_keys:
+            raise KeyError("invalid key in opds.catalog.Entry: %s" % (key))
+
+    def __init__(self, **kwargs):
+        for key, val in kwargs.items():
+            self.validate(key, val)
+
+        for req_key in Entry.required_keys:
+            if not req_key in kwargs:
+                raise KeyError("required key %s not supplied for Entry!" % (req_key))
+        self.id = kwargs["id"]
+        self.title = kwargs["title"]
+        self.links = kwargs["links"]
+        self._data = kwargs
+        
+        #print(">>entry.py")
+        #print(kwargs)
+        #print(kwargs["links"][0].get("rpath"))
+        #print("--end entry.py")
+
+        if kwargs["links"][0].get("type") == 'application/x-cbz':
+            f=self.links[0].get("rpath")+"/"+self.title+".cbz"
+            if os.path.exists(f): 
+                s = zipfile.ZipFile(f)
+                data=BeautifulSoup(s.open('ComicInfo.xml').read(), "xml")
+            #print(data)
+            #print(kwargs["links"][0])
+            #print(data.select('Series')[0].text)
+            #print(kwargs["links"][0].get("rpath"))
+                if data.select('Series')[0].text in kwargs["links"][0].get("rpath"):
+                    releasedate=data.select('Year')[0].text+"-"+data.select('Month')[0].text.zfill(2)+"-"+data.select('Day')[0].text.zfill(2)
+                    self.title = "#"+data.select('Number')[0].text.zfill(2) + ": " + data.select('Title')[0].text + " (" + releasedate + ")"
+            #print(self.title)
+                else:
+                    self.title = kwargs["title"]
+            else:
+                self.title = kwargs["title"]
+            #self.title = data.select('Title')[0].text
+            
+
+    def get(self, key):
+        return self._data.get(key, None)
+
+    def set(self, key, value):
+        self.validate(key, value)
+        self._data[key] = value

opds/link.py

@@ -0,0 +1,31 @@
+class Link(object):
+    valid_keys = ("href", "type", "rel", "rpath", "price", "currencycode", "formats")
+    required_keys = ("href", "type", "rel")
+
+    def validate(self, key, value):
+        if key not in Link.valid_keys:
+            raise KeyError("invalid key in opds.Link: %s" % (key))
+
+    def __init__(self, **kwargs):
+        for key, val in kwargs.items():
+            self.validate(key, val)
+
+        for req_key in Link.required_keys:
+            if not req_key in kwargs:
+                raise KeyError("required key %s not supplied for Link!" % (req_key))
+
+        self.href = kwargs["href"]
+        self.type = kwargs["type"]
+        self.rel = kwargs["rel"]
+        self._data = kwargs
+        
+        #print(">>link.py")
+        #print(kwargs)
+        #print("--end link.py")
+
+    def get(self, key):
+        return self._data.get(key, None)
+
+    def set(self, key, value):
+        self.validate(key, value)
+        self._data[key] = value

opds/templates/catalog.opds.jinja2

@@ -0,0 +1,39 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<feed xmlns="http://www.w3.org/2005/Atom"
+      xmlns:dc="http://purl.org/dc/terms/"
+      xmlns:ov="http://open.vocab.org/terms/"
+      xmlns:oz="http://openzim.org/terms/"
+      xmlns:opds="http://opds-spec.org/2010/catalog">
+  <id>urn:uuid:{{ catalog.id }}</id>
+  <title>{{ catalog.title }}</title>
+  {% if catalog.author_name or catalog.author_url %}
+  <author>
+    {% if catalog.author_name %}
+    <name>{{ catalog.author_name }}</name>
+    {% endif %}
+    {% if catalog.author_url %}
+    <uri>{{ catalog.author_url }}</uri>
+    {% endif %}
+  </author>
+  {% endif %}
+  <link rel="start"
+        href="{{ catalog.root_url }}"
+        type="application/atom+xml;profile=opds-catalog;kind=acquisition"/>
+  <link rel="self"
+        href="{{ catalog.url }}"
+        type="application/atom+xml;profile=opds-catalog;kind=acquisition"/>
+
+  {% for entry in catalog.entries %}
+  <entry>
+    <title>{{ entry.title }}</title>
+    <id>{{ entry.id }}</id>
+    {% if entry.updated %} <updated>{{ entry.updated }}</updated> {% endif %}
+    {% for link in entry.links %}
+    <link rel="{{ link.rel }}"
+          href="{{ link.href }}"
+          type="{{ link.type }}"/>
+    {% endfor %}
+  </entry>
+  {% endfor %}
+
+</feed>

requirements.txt

@@ -0,0 +1,7 @@
+Flask==2.0.2
+Jinja2==3.0.2
+requests==2.26.0
+Flask-HTTPAuth==4.5.0
+gevent==21.8.0
+bs4
+lxml

static/robots.txt

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