attilasub backend created, search works

modules/attilasub/__init__.py

@@ -0,0 +1,3 @@
+from .backend import AttilasubBackend
+
+__all__ = ['AttilasubBackend']

modules/attilasub/backend.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Julien Veyssier
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+from weboob.capabilities.subtitle import ICapSubtitle
+from weboob.tools.backend import BaseBackend
+
+from .browser import AttilasubBrowser
+
+from urllib import quote_plus
+
+__all__ = ['AttilasubBackend']
+
+
+class AttilasubBackend(BaseBackend, ICapSubtitle):
+    NAME = 'attilasub'
+    MAINTAINER = u'Julien Veyssier'
+    EMAIL = 'julien.veyssier@aiur.fr'
+    VERSION = '0.f'
+    DESCRIPTION = '"Attila'' s Website 2.0" french subtitles'
+    LICENSE = 'AGPLv3+'
+    BROWSER = AttilasubBrowser
+
+    def create_default_browser(self):
+        return self.create_browser()
+
+    #def get_subtitle(self, id):
+    #    return self.browser.get_subtitle(id)
+
+    def get_subtitle_file(self, id):
+        subtitle = self.browser.get_subtitle(id)
+        if not subtitle:
+            return None
+
+        return self.browser.openurl(subtitle.url.encode('utf-8')).read()
+
+    def iter_subtitles(self, pattern):
+        return self.browser.iter_subtitles(quote_plus(pattern.encode('utf-8')))

modules/attilasub/browser.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Julien Veyssier
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+
+from weboob.tools.browser import BaseBrowser
+
+from .pages import SubtitlesPage, SearchPage
+
+
+__all__ = ['AttilasubBrowser']
+
+
+class AttilasubBrowser(BaseBrowser):
+    DOMAIN = 'davidbillemont3.free.fr'
+    PROTOCOL = 'http'
+    ENCODING = 'utf-8'
+    USER_AGENT = BaseBrowser.USER_AGENTS['wget']
+    PAGES = {
+        'http://search.freefind.com/find.html.*': SearchPage,
+        'http://davidbillemont3.free.fr/.*.htm': SubtitlesPage,
+        }
+
+    def iter_subtitles(self, pattern):
+        self.location('http://search.freefind.com/find.html?id=81131980&_charset_=&bcd=%%F7&scs=1&pageid=r&query=%s&mode=Find%%20pages%%20matching%%20ALL%%20words' % pattern.encode('utf-8'))
+        assert self.is_on_page(SearchPage)
+        return self.page.iter_subtitles(pattern)
+
+    #def get_torrent(self, id):
+    #    self.location('http://kat.ph/%s.html' % id)
+    #    assert self.is_on_page(TorrentPage)
+    #    return self.page.get_torrent(id)

modules/attilasub/pages.py

@@ -0,0 +1,83 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2012 Julien Veyssier
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+
+try:
+    from urlparse import parse_qs
+except ImportError:
+    from cgi import parse_qs  # NOQA
+
+from urlparse import urlsplit
+
+from weboob.capabilities.subtitle import Subtitle
+from weboob.capabilities.base import NotAvailable
+from weboob.tools.browser import BasePage
+from weboob.tools.misc import get_bytes_size
+
+
+__all__ = ['SubtitlesPage','SearchPage']
+
+
+class SearchPage(BasePage):
+    def iter_subtitles(self,pattern):
+        fontresult = self.parser.select(self.document.getroot(),'div.search-results font.search-results')
+        # for each result in freefind, explore the page to iter subtitles
+        for res in fontresult:
+            a = self.parser.select(res,'a',1)
+            url = a.attrib.get('href','')
+            self.browser.location(url)
+            assert self.browser.is_on_page(SubtitlesPage)
+            # subtitles page does the job
+            for subtitle in self.browser.page.iter_subtitles(pattern):
+                yield subtitle
+
+
+class SubtitlesPage(BasePage):
+    def iter_subtitles(self,pattern):
+        pattern = pattern.strip().replace('+',' ')
+        pattern_words = pattern.split()
+        tab = self.parser.select(self.document.getroot(),'table[bordercolor="#B8C0B2"]')
+        if len(tab) == 0:
+            tab = self.parser.select(self.document.getroot(),'table[bordercolordark="#B8C0B2"]')
+            if len(tab) == 0:
+                return
+        for line in tab[0].getiterator('tr'):
+            cols = self.parser.select(line,'td')
+            traduced_title = self.parser.select(cols[0],'font',1).text.lower()
+            original_title = self.parser.select(cols[1],'font',1).text.lower()
+
+            traduced_title_words = traduced_title.split()
+            original_title_words = original_title.split()
+
+            # if the pattern is one word and in the title OR if the 
+            # intersection between pattern and the title is at least 2 words
+            if (len(pattern_words) == 1 and pattern in traduced_title_words) or\
+               (len(pattern_words) == 1 and pattern in original_title_words) or\
+               (len(list(set(pattern_words) & set(traduced_title_words))) > 1) or\
+               (len(list(set(pattern_words) & set(original_title_words))) > 1):
+
+                # this is to trash special spacing chars
+                traduced_title = " ".join(traduced_title_words)
+                original_title = " ".join(original_title_words)
+
+                title = "%s (%s)"%(original_title,traduced_title)
+                subtitle = Subtitle(title,title)
+                subtitle.url = self.parser.select(cols[3],'a',1).attrib.get('href','')
+                subtitle.fps = 0
+                yield subtitle

modules/attilasub/test.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Julien Veyssier, Laurent Bachelier
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+from weboob.tools.test import BackendTest
+from weboob.capabilities.base import NotLoaded
+
+import urllib
+from random import choice
+
+class AttilasubTest(BackendTest):
+    BACKEND = 'attilasub'
+
+    def test_subtitle(self):
+        subtitles = list(self.backend.iter_subtitles('spiderman'))
+        for subtitle in subtitles:
+            path, qs = urllib.splitquery(subtitle.url)
+            #assert path.endswith('.torrent')
+
+        # get the file of a random sub
+        if len(subtitles):
+            subtitle = choice(subtitles)
+            self.backend.get_subtitle_file(subtitle.id)