Get all available pages

[software/subdivxget.git] / subdivxget

diff --git a/subdivxget b/subdivxget
index 5c5cc7a49cfab50003860880a380ff6737f67fdd..5f67edbfeb8852a47a2cbfcf89b1e83c522dc8d1 100755 (executable)
--- a/subdivxget
+++ b/subdivxget
@@ -7,12 +7,13 @@ import subprocess
 import HTMLParser
 
 class SubDivXQuery:
-       def __init__(self, to_search):
+       def __init__(self, to_search, page_number):
                self.host = "www.subdivx.com"
                self.page = "/index.php"
                self.down_page = "/bajar.php"
                self.query = dict(
                        buscar = to_search,
+                       pg = page_number,
                        accion = 5,
                        masdesc = '',
                        subtitulos = 1,
@@ -29,8 +30,6 @@ class SubDivXQuery:
        def down_uri(self):
                return 'http://' + self.host + self.down_page
 
-class Subtitle:
-       pass
 
 class SubDivXHTMLParser(HTMLParser.HTMLParser):
 
@@ -48,7 +47,6 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
        def handle_starttag(self, tag, attrs):
                attrs = dict(attrs)
                if tag == 'div' and attrs.get('id') == 'menu_detalle_buscador':
-                       #self.cur = Subtitle()
                        self.cur = dict()
                        self.subs.append(self.cur)
                        self.parsing = True
@@ -79,8 +77,6 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
                        if self.attr is not None and data:
                                self.cur[self.attr] = data
                                self.attr = None
-                               #self.cur[self.attr] = self.cur.get(self.attr, '') + data.strip()
-                               #setattr(self.cur, self.attr, data.strip())
                        elif data in ('Downloads:', 'Cds:', 'Comentarios:',
                                        'Formato:'):
                                self.attr = data[:-1].lower()
@@ -90,22 +86,33 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
                                self.attr = 'fecha'
 
 
-def get_subs(query_str):
-       query = SubDivXQuery(query_str)
+def subdivx_get_subs(query_str):
+       page_number = 1
+       subs = []
+       while True:
+               query = SubDivXQuery(query_str, page_number)
+               url = urllib.urlopen(query.url)
+               parser = SubDivXHTMLParser(query.down_uri)
+
+               for line in url:
+                       parser.feed(line)
 
-       url = urllib.urlopen(query.url)
+               url.close()
 
-       parser = SubDivXHTMLParser(query.down_uri)
+               if not parser.subs:
+                       break
 
-       for line in url:
-               parser.feed(line)
+               subs.extend(parser.subs)
+               page_number += 1
 
-       url.close()
+       return sorted(subs, key=lambda s: int(s['downloads']), reverse=True)
 
+
+def get_subs(query_str):
        zip_exts = ('application/zip',)
        rar_exts = ('application/rar', 'application/x-rar-compressed')
 
-       for sub in sorted(parser.subs, key=lambda s: int(s['downloads']), reverse=True):
+       for sub in subdivx_get_subs(query_str):
                print '''\
        - %(title)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
          %(desc)s