Fixed xml escape issue

extras.py

@@ -1,5 +1,15 @@
 import os,re
 
+table = str.maketrans({
+    "<": "&lt;",
+    ">": "&gt;",
+    "&": "&amp;",
+    "'": "&apos;",
+    '"': "&quot;",
+})
+def xmlesc(txt):
+    return txt.translate(table)
+
 def get_size(file_path, unit='bytes'):
     file_size = os.path.getsize(file_path)
     exponents_map = {'bytes': 0, 'kb': 1, 'mb': 2, 'gb': 3}

main.py

@@ -267,23 +267,23 @@ def image(path):
 @app.route("/catalog/<path:path>")
 @auth.login_required
 def catalog(path=""):
-    #config._print("path: " + path)
-    #config._print("root_url: " + request.root_url)
-    #config._print("url: " + request.url)
-    #config._print("CONTENT_BASE_DIR: " + config.CONTENT_BASE_DIR)
+    config._print("path: " + path)
+    config._print("root_url: " + request.root_url)
+    config._print("url: " + request.url)
+    config._print("CONTENT_BASE_DIR: " + config.CONTENT_BASE_DIR)
     #print("PRESSED ON")
-    start_time = timeit.default_timer()
+    #start_time = timeit.default_timer()
     #print(request.root_url) 
     c = fromdir(request.root_url, request.url, config.CONTENT_BASE_DIR, path)
-    #print("c: ")
+    print("c: ")
     #pprint(vars(c))
-    #for x in c.entries:
-    #    for y in x.links:
-    #        pprint(y.href)
+    for x in c.entries:
+        for y in x.links:
+            pprint(y.href)
     #print("------")
-    elapsed = timeit.default_timer() - start_time
-    print("-----------------------------------------------------------------------------------------------------------------------")
-    print("RENDERED IN: " + str(round(elapsed,2))+"s")
+    #elapsed = timeit.default_timer() - start_time
+    #print("-----------------------------------------------------------------------------------------------------------------------")
+    #print("RENDERED IN: " + str(round(elapsed,2))+"s")
     
     return c.render()
 

opds/catalog.py

@@ -6,6 +6,7 @@ from .entry import Entry
 from .link import Link
 import sqlite3,json
 import config
+import extras
 
 class Catalog(object):
     def __init__(
@@ -47,8 +48,7 @@ def fromsearch(root_url, url, content_base_path, content_relative_path):
     return c
 
 def fromdir(root_url, url, content_base_path, content_relative_path):
-
-
+    
     path = os.path.join(content_base_path, content_relative_path)
 
     if os.path.basename(content_relative_path) == "":
@@ -59,7 +59,7 @@ def fromdir(root_url, url, content_base_path, content_relative_path):
             )
     else:
         c = Catalog(
-            title=os.path.basename(content_relative_path), 
+            title=extras.xmlesc(os.path.basename(content_relative_path)),
             root_url=root_url, 
             url=url
         )
@@ -94,7 +94,7 @@ def fromdir(root_url, url, content_base_path, content_relative_path):
                 rpath=path,
                 type="application/atom+xml;profile=opds-catalog;kind=acquisition",
             )
-            c.add_entry(Entry(title=dirname, id=uuid4(), links=[link]))
+            c.add_entry(Entry(title=extras.xmlesc(dirname), id=uuid4(), links=[link]))
 
     
     if c.url.endswith("/catalog"):
@@ -119,7 +119,10 @@ def fromdir(root_url, url, content_base_path, content_relative_path):
                 rpath=path,
                 type=mimetype(filename),
             )
-            c.add_entry(Entry(title=filename.rsplit(".",1)[0], id=uuid4(), links=[link]))
+
+            #c.add_entry(Entry(title=filename.rsplit(".",1)[0], id=uuid4(), links=[link]))
+            c.add_entry(Entry(title=extras.xmlesc(filename).rsplit(".",1)[0], id=uuid4(), links=[link]))
+        
             #fixed issue with multiple . in filename
             #print(c.render()) 
     else:

opds/entry.py

@@ -62,7 +62,7 @@ class Entry(object):
                 if os.path.exists(f): 
                     s = zipfile.ZipFile(f)
                     self.size = extras.get_size(f, 'mb')
-                    data=BeautifulSoup(s.open('ComicInfo.xml').read(), features="html.parser")
+                    data=BeautifulSoup(s.open('ComicInfo.xml').read(), features="lxml")
                     #self.cover=s.open('P00001.jpg').read()
 
                     if data.select('Writer') != []: