Encoding Hell

3 files changed, 36 insertions, 15 deletions

diff --git a/imdb-lookup/README.md b/imdb-lookup/README.md
new file mode 100644
index 0000000..2512418
--- /dev/null
+++ b/imdb-lookup/README.md
@@ -0,0 +1,17 @@
+# movie tools
+
+
+imdblookup.py    Rename with Text gui
+
+
+imdbinfo.py      general tools
+
+
+
+# TMDB:
+for tmdb you need a Api-Key
+
+
+# IMDB:
+for imdb we use the mobile api.
+By executing the tool you are probably violating the imdb ToS.
diff --git a/imdb-lookup/imdbinfo.py b/imdb-lookup/imdbinfo.py
index 504528a..163cec9 100755
--- a/imdb-lookup/imdbinfo.py
+++ b/imdb-lookup/imdbinfo.py
@@ -13,7 +13,7 @@ import argparse
 import math
 import logging
 import hashlib
-from io import StringIO
+from io import BytesIO
 
 from urllib.parse import quote as urlencode
 
@@ -86,6 +86,7 @@ class TMDBCache(object):
             raise Exception("Failed to query movie with id {id}: {reason}".format(id=movie_id, reason=str(e)))
     
     def prune(self, movie_id):
+        self.logger.debug("prune {}".format(movie_id))
         keys = [
             "imdb_maindetails_{}".format(movie_id),
             movie_id + "movies.info",
@@ -93,8 +94,10 @@ class TMDBCache(object):
         ]
         for key in keys:
             if key in self.db:
-                print("Remove {}".format(key))
+                self.logger.warn("Remove {}".format(key))
                 del self.db[key]
+            else:
+                self.logger.debug("Key not in db {}".format(key))
 
     def poster(self, poster_path, format="w185"):
         self.logger.debug("poster %s", poster_path)
@@ -111,8 +114,8 @@ class TMDBCache(object):
         p = self.poster(poster_path, format)
         if not p: return None
         contentType, data = p
-        image = Image.open(StringIO(data))
-        buf = StringIO()
+        image = Image.open(BytesIO(data))
+        buf = BytesIO()
         image.save(buf, "JPEG", quality=10, optimize=True)
         data64 = "".join(map(lambda c: isinstance(c,int) and chr(c) or c, 
                     filter(lambda c: c!='\n', base64.encodestring(buf.getvalue()))))
@@ -137,13 +140,15 @@ class TMDBCache(object):
         }
         q = query.copy()
         q.update(PARAMS)
-        return requests.get("http://{}{}".format(BASE_URI, path), params=q, headers=HEADERS)
+        return requests.get("https://{}{}".format(BASE_URI, path), params=q, headers=HEADERS)
 
     def imdb_movie(self, movie_id):
         def do_request():
             r = self._imdb_request("/title/maindetails", {'tconst': movie_id})
             assert r.status_code == 200, "Request must return status-code 200"
-            return json.loads(r.content)
+            data = json.loads(r.text)
+            assert data != None and data['data'], "Data must not be empty"
+            return data
         key = "imdb_maindetails_{}".format(movie_id)
         return self._cache(key, do_request)
 
@@ -242,7 +247,7 @@ def do_index(args, imdb_ids):
         print("Failed to import jinja2 library for html-templating")
         sys.exit(1)
     template_file = os.path.join(os.path.dirname(__file__), "index.jinja2.html")
-    template = Template(open(template_file, "rb").read().decode('utf-8'))
+    template = Template(open(template_file, "r").read())
     with TMDBCache() as tmdbcache:
         mapping = {
             'gmtime' : time.gmtime(),
@@ -258,8 +263,7 @@ def do_index(args, imdb_ids):
         stream = template.generate(mapping)
         outfile = open("index.html", "wb")
         for output in stream:
-            output = output.encode("utf-8")
-            outfile.write(output.strip())
+            outfile.write(output.encode('utf-8'))
 
 class HelpAction(argparse._HelpAction):
     def __call__(self, parser, namespace, values, option_string=None):
@@ -340,6 +344,6 @@ if __name__ == "__main__":
     if "files" in args:
         ids = map(lambda filename: (lambda x: (filename, x.groups()[0]) if x else None)(re.match(".*#(tt[0-9]{7}).*", filename)),
                     args.files[0])
-        args.func(args, filter(lambda i: i is not None, ids))
+        args.func(args, list(filter(lambda i: i is not None, ids)))
     else:
         args.func(args)
diff --git a/imdb-lookup/index.jinja2.html b/imdb-lookup/index.jinja2.html
index a3e004e..82647c3 100644
--- a/imdb-lookup/index.jinja2.html
+++ b/imdb-lookup/index.jinja2.html
@@ -113,13 +113,13 @@
         </tr>
         <tr>
          <td colspan="2">
-          → <a href="http://www.themoviedb.org/movie/{{ info.id }}" rel="noreferrer">themoviedb.org</a>
+          -&gt; <a href="http://www.themoviedb.org/movie/{{ info.id }}" rel="noreferrer">themoviedb.org</a>
           &ensp;
-          → <a href="http://www.imdb.com/title/{{ info.imdb_id }}" rel="noreferrer">imdb.com</a>
+          -&gt; <a href="http://www.imdb.com/title/{{ info.imdb_id }}" rel="noreferrer">imdb.com</a>
           &ensp;
-          → <a href="http://letterboxd.com/tmdb/{{ info.id }}" rel="noreferrer">letterboxd.com</a>
+          -&gt; <a href="http://letterboxd.com/tmdb/{{ info.id }}" rel="noreferrer">letterboxd.com</a>
           &ensp;
-          → <a href="http://www.ofdb.de/view.php?page=suchergebnis&Kat=IMDb&SText={{ info.imdb_id }}" rel="noreferrer">ofdb.db</a>
+          -&gt; <a href="http://www.ofdb.de/view.php?page=suchergebnis&Kat=IMDb&SText={{ info.imdb_id }}" rel="noreferrer">ofdb.db</a>
          </td>
         </tr>
        </table>   
@@ -127,7 +127,7 @@
          {% for file in listMovieFiles(path) %}
          <li>
            <a href="{{urlencode(file)}}">
-             {{ u" → ".join(file.split("/")[1:]) }}
+             {{ " &gt; ".join(file.split("/")[1:]) }}
            </a>
          </li>
          {% endfor %}