Add fairly fine grained filtering support

Now the program can make only one query but it can accept multiple
optional filters based on the fields. Each extra argument is a filter
specification, and filters are all joined using a logical AND.

The individual filters have the format X:fitler, there X is a field
specification:
t = titulo
d = desc
a = autor
f = formato
c = comentarios
C = cds
F = fecha
D = downloads

And filter is a string that should be found on that field (case
insensitive). If the format specifier is not known (or there isn't one)
the filter string is looked in all the fields.

diff --git a/subdivxget b/subdivxget
index 4ebcca5a71abf2bd94aa04b9c93b1003af36f240..da731c48c610de7ccc8bf1460c9245fa0ecbac7d 100755 (executable)
--- a/subdivxget
+++ b/subdivxget
@@ -118,6 +118,56 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
                        self.cur[self.attr] = ''
 
 
+def filter_subtitles(subs, filters):
+       def is_good(sub, filter):
+               def is_any_good(sub, filter):
+                       for value in sub.values():
+                               if value.lower().find(filter) >= 0:
+                                       return True
+
+               field = None
+               if len(filter) > 2 and filter[1] == ':':
+                       field = filter[0]
+                       filter = filter[2:]
+               filter = filter.lower()
+
+               if field is None:
+                       return is_any_good(sub, filter)
+               elif field == 't':
+                       key = 'titulo'
+               elif field == 'd':
+                       key = 'desc'
+               elif field == 'a':
+                       key = 'autor'
+               elif field == 'f':
+                       key = 'formato'
+               elif field == 'c':
+                       key = 'comentarios'
+               elif field == 'C':
+                       key = 'cds'
+               elif field == 'F':
+                       key = 'fecha'
+               elif field == 'D':
+                       key = 'downloads'
+               else:
+                       # Not a recognizer field identifier, use the raw filter
+                       return is_any_good(sub, field + ':' + filter)
+
+               return sub[key].lower().find(filter) >= 0
+
+       if not filters:
+               return subs
+
+       result = []
+       for sub in subs:
+               for filter in filters:
+                       if not is_good(sub, filter):
+                               break
+               else:
+                       result.append(sub)
+       return result
+
+
 def subdivx_get_subs(query_str):
        page_number = 1
        subs = []
@@ -140,11 +190,14 @@ def subdivx_get_subs(query_str):
        return sorted(subs, key=lambda s: int(s['downloads']), reverse=True)
 
 
-def get_subs(query_str):
+def get_subs(query_str, filters):
        zip_exts = ('application/zip',)
        rar_exts = ('application/rar', 'application/x-rar-compressed')
 
-       for sub in subdivx_get_subs(query_str):
+       subs = subdivx_get_subs(query_str)
+       subs = filter_subtitles(subs, filters)
+
+       for sub in subs:
                print '''\
        - %(titulo)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
          %(desc)s
@@ -171,6 +224,5 @@ def get_subs(query_str):
                        print 'No Content-Type!'
 
 
-for q in sys.argv[1:]:
-       get_subs(q)
+get_subs(sys.argv[1], sys.argv[2:])