upgrade to browser2

modules/youjizz/pages/index.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright(C) 2010-2012 Roger Philibert
+# Copyright(C) 2010-2014 Roger Philibert
 #
 # This file is part of weboob.
 #
@@ -21,9 +21,10 @@
 import datetime
 import re
 
-from weboob.tools.browser import BasePage, BrokenPageError
+from weboob.tools.browser2 import HTMLPage
+from weboob.tools.browser2.page import ListElement, method, ItemElement
+from weboob.tools.browser2.filters import Filter, Link, CleanText
 from weboob.capabilities.image import BaseImage
-from weboob.tools.misc import to_unicode
 
 from ..video import YoujizzVideo
 
@@ -31,35 +32,42 @@ from ..video import YoujizzVideo
 __all__ = ['IndexPage']
 
 
-class IndexPage(BasePage):
-    def iter_videos(self):
-        span_list = self.parser.select(self.document.getroot(), 'span#miniatura')
-        for span in span_list:
-            a = self.parser.select(span, 'a', 1)
-            url = a.attrib['href']
-            _id = re.sub(r'/videos/(.+)\.html', r'\1', url)
+class IndexPage(HTMLPage):
+    @method
+    class iter_videos(ListElement):
+        item_xpath = '//span[@id="miniatura"]'
 
-            video = YoujizzVideo(_id)
+        next_page = Link(u'//a[text()="Next »"]')
 
-            video.thumbnail = BaseImage(span.find('.//img').attrib['data-original'])
-            video.thumbnail.url = video.thumbnail.id
+        class item(ItemElement):
+            klass = YoujizzVideo
 
-            title_el = self.parser.select(span, 'span#title1', 1)
-            video.title = to_unicode(title_el.text.strip())
+            class Id(Filter):
+                def filter(self, link):
+                    return re.sub(r'/videos/(.+)\.html', r'\1', link)
 
-            time_span = self.parser.select(span, 'span.thumbtime span', 1)
-            time_txt = time_span.text.strip().replace(';', ':')
-            hours, minutes, seconds = 0, 0, 0
-            if ':' in time_txt:
-                t = time_txt.split(':')
-                t.reverse()
-                seconds = int(t[0])
-                minutes = int(t[1])
-                if len(t) == 3:
-                    hours = int(t[2])
-            elif time_txt != 'N/A':
-                raise BrokenPageError('Unable to parse the video duration: %s' % time_txt)
+            class Duration(Filter):
+                def filter(self, txt):
+                    time_txt = txt.replace(';', ':')
+                    hours, minutes, seconds = 0, 0, 0
+                    if ':' in time_txt:
+                        t = time_txt.split(':')
+                        t.reverse()
+                        seconds = int(t[0])
+                        minutes = int(t[1])
+                        if len(t) == 3:
+                            hours = int(t[2])
+                    elif time_txt != 'N/A':
+                        raise ValueError('Unable to parse the video duration: %s' % time_txt)
 
-            video.duration = datetime.timedelta(hours=hours, minutes=minutes, seconds=seconds)
+                    return datetime.timedelta(hours=hours, minutes=minutes, seconds=seconds)
 
-            yield video
+
+            obj_id = Id(Link('.//a'))
+            obj_title = CleanText('.//span[@id="title1"]')
+            obj_duration = Duration(CleanText('.//span[@class="thumbtime"]//span'))
+
+            def obj_thumbnail(self):
+                thumbnail = BaseImage(self.xpath('.//img')[0].attrib['data-original'])
+                thumbnail.url = thumbnail.id
+                return thumbnail