implement ICapVideoProvider.iter_search_results()

weboob/backends/youtube/backend.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 """
-Copyright(C) 2010  Christophe Benz
+Copyright(C) 2010  Christophe Benz, Romain Bignon
 
 This program is free software; you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -32,26 +32,39 @@ class YoutubeBackend(BaseBackend, ICapVideoProvider):
     LICENSE = 'GPLv3'
 
     CONFIG = {}
-    browser = None
+    _browser = None
 
-    def need_browser(func):
+    def __getattr__(self, name):
+        if name == 'browser':
+            if not self._browser:
+                self._browser = YoutubeBrowser()
+            return self._browser
+        raise AttributeError, name
+
+    def need_url(func):
         def inner(self, *args, **kwargs):
-            if not self.browser:
-                self.browser = YoutubeBrowser()
             url = args[0]
-            if u'youtube.com' not in url:
+            if isinstance(url, (str,unicode)) and not url.isdigit() and u'youtube.com' not in url:
                 return None
             return func(self, *args, **kwargs)
         return inner
 
-    @need_browser
+    @need_url
+    def get_video(self, _id):
+        return self.browser.get_video(_id)
+
+    SORTBY = ['', 'video_avg_rating', 'video_view_count', 'video_date_uploaded']
+    def iter_search_results(self, pattern=None, sortby=ICapVideoProvider.SEARCH_RELEVANCE):
+        return self.browser.iter_search_results(pattern, self.SORTBY[sortby])
+
+    @need_url
     def iter_page_urls(self, mozaic_url):
         raise NotImplementedError()
 
-    @need_browser
+    @need_url
     def get_video_title(self, page_url):
         return self.browser.get_video_title(page_url)
 
-    @need_browser
+    @need_url
     def get_video_url(self, page_url):
         return self.browser.get_video_url(page_url)

weboob/backends/youtube/browser.py

@@ -18,23 +18,37 @@ Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 
 """
 
+import urllib
 import re
 
 from weboob.tools.browser import BaseBrowser
 from weboob.tools.parsers.lxmlparser import LxmlHtmlParser
 
-from .pages import VideoPage
+from .pages import VideoPage, ResultsPage
 
 __all__ = ['YoutubeBrowser']
 
 class YoutubeBrowser(BaseBrowser):
+    PAGES = {'.*youtube\.com/watch\?v=(.+)': VideoPage,
+             '.*youtube\.com/results\?.*': ResultsPage,
+            }
     video_signature_regex = re.compile(r'&t=([^ ,&]*)')
 
     def __init__(self, *args, **kwargs):
         kwargs['parser'] = LxmlHtmlParser()
-        self.PAGES = {r'.*youtube\.com/watch\?v=(.+)': VideoPage}
         BaseBrowser.__init__(self, *args, **kwargs)
 
+    def iter_search_results(self, pattern, sortby):
+        if not pattern:
+            self.home()
+        else:
+            if sortby:
+                sortby = '&search_sort=%s' % sortby
+            self.location('http://www.youtube.com/results?search_type=videos&search_query=%s%s' % (urllib.quote_plus(pattern), sortby))
+
+        assert self.is_on_page(ResultsPage)
+        return self.page.iter_videos()
+
     def get_video_title(self, page_url):
         self.location(page_url)
         return self.page.title

weboob/backends/youtube/pages/__init__.py

@@ -19,3 +19,4 @@ Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 """
 
 from .video import VideoPage
+from .results import ResultsPage

weboob/backends/youtube/pages/results.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+
+"""
+Copyright(C) 2010  Romain Bignon
+
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, version 3 of the License.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; if not, write to the Free Software
+Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+
+"""
+
+import re
+
+from weboob.tools.browser import BasePage
+from weboob.capabilities.video import Video
+
+class ResultsPage(BasePage):
+    WATCH_RE = re.compile('/watch?v=(\w+)')
+    def iter_videos(self):
+        for div in self.document.getroot().cssselect("div[class^=video-entry]"):
+            a = div.find('a')
+            if a is None:
+                print 'wtf'
+                continue
+
+            _id = ''
+            m = self.WATCH_RE.match(a.attrib['href'])
+            if m:
+                _id = m.group(1)
+
+            title = a.find('span').find('img').attrib['alt']
+            preview_url = a.find('span').find('img').attrib['src']
+            if preview_url.endswith('.gif'):
+                preview_url = a.find('span').find('img').attrib['thumb']
+
+            vtime = a.find('span').find('span')
+            duration = 0
+            if not vtime is None:
+                vtime = vtime.find('span').text.split(':')
+                if len(vtime) > 0:
+                    duration += int(vtime[-1])
+                if len(vtime) > 1:
+                    duration += 60 * int(vtime[-2])
+                if len(vtime) > 3:
+                    duration += 3600 * int(vtime[-3])
+                if len(vtime) > 4:
+                    print 'WTF'
+
+            author = ''
+            author_div = div.cssselect('span[class=video-username]')
+            if author_div:
+                author = author_div[0].find('a').text.strip()
+            yield Video(_id,
+                        title,
+                        author=author,
+                        duration=duration,
+                        preview_url=preview_url)