implement ICapVideoProvider.iter_search_results()

weboob/backends/youporn/backend.py

@@ -53,6 +53,9 @@ class YoupornBackend(Backend, ICapVideoProvider):
     def get_video(self, _id):
         return self.browser.get_video(_id)
 
+    def iter_search_results(self, pattern=None):
+        return self.browser.iter_search_results(pattern)
+
     @need_url
     def iter_page_urls(self, mozaic_url):
         raise NotImplementedError()

weboob/backends/youporn/browser.py

@@ -19,6 +19,7 @@ Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 """
 
 import re
+import urllib
 
 from weboob.tools.browser import Browser
 
@@ -29,6 +30,7 @@ class YoupornBrowser(Browser):
     DOMAIN = 'youporn.com'
     PROTOCOL = 'http'
     PAGES = {'http://[w\.]*youporn\.com/?': IndexPage,
+             'http://[w\.]*youporn\.com/search.*': IndexPage,
              'http://[w\.]*youporn\.com/watch/.+': VideoPage,
             }
 
@@ -38,10 +40,19 @@ class YoupornBrowser(Browser):
 
     def id2url(self, _id):
         if isinstance(_id, int) or isinstance(_id, (str,unicode)) and _id.isdigit():
-            return 'http://www.youporn.com/watch/%d' % _id
+            return 'http://www.youporn.com/watch/%d' % int(_id)
         else:
             return str(_id)
 
+    def iter_search_results(self, pattern):
+        if not pattern:
+            self.home()
+        else:
+            self.location('/search?query=%s' % urllib.quote_plus(pattern))
+
+        assert self.is_on_page(IndexPage)
+        return self.page.iter_videos()
+
     def get_video(self, _id):
         self.location(self.id2url(_id))
         return self.page.video

weboob/backends/youporn/pages/index.py

@@ -19,8 +19,17 @@ Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 """
 
 from .base import PornPage
+from weboob.capabilities.video import Video
 
 class IndexPage(PornPage):
-    def loaded(self):
-        if not PornPage.loaded(self):
-            return
+    def iter_videos(self):
+        for h1 in self.document.getiterator('h1'):
+            a = h1.find('a')
+            if a is None:
+                continue
+
+            url = a.attrib['href']
+            _id = url[len('/watch/'):]
+            _id = _id[:_id.find('/')]
+            title = a.text
+            yield Video(int(_id), title)