Add pastealacon backend for CapPaste

Sadly, not posting for now, for two reasons:
* we get a captcha very often
* the form page seems invalid and mechanize is not able to select the form

weboob/backends/pastealacon/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011 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 .backend import PastealaconBackend
+
+__all__ = ['PastealaconBackend']

weboob/backends/pastealacon/backend.py

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011 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.capabilities.paste import ICapPaste
+from weboob.tools.backend import BaseBackend
+from weboob.capabilities.base import NotLoaded
+
+from .browser import PastealaconBrowser
+from .paste import PastealaconPaste
+
+
+__all__ = ['PastealaconBackend']
+
+
+class PastealaconBackend(BaseBackend, ICapPaste):
+    NAME = 'pastealacon'
+    MAINTAINER = 'Laurent Bachelier'
+    EMAIL = 'laurent@bachelier.name'
+    VERSION = '0.8'
+    DESCRIPTION = 'Paste a la con paste tool'
+    LICENSE = 'AGPLv3+'
+    BROWSER = PastealaconBrowser
+
+    def get_paste(self, _id):
+        return PastealaconPaste(_id)
+
+    def fill_paste(self, paste, fields):
+        # if we only want the contents
+        if fields == ['contents']:
+            if paste.contents is NotLoaded:
+                contents = self.browser.get_contents(paste.id)
+                paste.contents = contents
+        elif fields:
+            self.browser.fill_paste(paste)
+        return paste
+
+    OBJECTS = {PastealaconPaste: fill_paste}

weboob/backends/pastealacon/browser.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011 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.browser import BaseBrowser
+
+from .pages import PastePage
+
+__all__ = ['PastealaconBrowser']
+
+class PastealaconBrowser(BaseBrowser):
+    DOMAIN = 'pastealacon.com'
+    ENCODING = 'ISO-8859-1'
+    PAGES = {'http://%s/(?P<id>\d+)' % DOMAIN: PastePage}
+
+    def fill_paste(self, paste):
+        """
+        Get as much as information possible from the paste page
+        """
+        self.location(paste.page_url)
+        return self.page.fill_paste(paste)
+
+    def get_contents(self, _id):
+        """
+        Get the contents from the raw URL
+        This is the fastest and safest method if you only want the content.
+        Returns unicode.
+        """
+        return self.readurl('http://%s/pastebin.php?dl=%s' % (self.DOMAIN, _id)).decode(self.ENCODING)

weboob/backends/pastealacon/pages.py

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011 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.browser import BasePage
+
+from urlparse import urlparse
+import re
+
+__all__ = ['PastePage']
+
+class PastePage(BasePage):
+    def fill_paste(self, paste):
+        root = self.document.getroot()
+        header = self.parser.select(root, 'id("content")//h3', 1, 'xpath')
+        matches = re.match(r'Posted by (?P<author>.+) on (?P<date>.+) \(', header.text)
+        paste.title = matches.groupdict().get('author')
+        paste.contents = self.parser.select(root, '//textarea[@id="code"]', 1, 'xpath').text
+        return paste
+
+    def get_id(self):
+        """
+        Find out the ID from the URL
+        """
+        path = urlparse(self.url).path
+        return path[1:]

weboob/backends/pastealacon/paste.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011 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.capabilities.paste import BasePaste
+
+
+__all__ = ['PastealaconPaste']
+
+
+class PastealaconPaste(BasePaste):
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://pastealacon.com/%s' % _id

weboob/backends/pastealacon/test.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011 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
+
+class PastealaconTest(BackendTest):
+    BACKEND = 'pastealacon'
+
+    def test_get_paste(self):
+        # html method
+        p = self.backend.get_paste('27184')
+        self.backend.fillobj(p, ['title'])
+        assert p.title == 'ouiboube'
+        assert p.page_url == 'http://pastealacon.com/27184'
+        assert u'coucou\r\ncoucou\r\nhéhéhé' == p.contents
+
+        # raw method
+        p = self.backend.get_paste('27184')
+        self.backend.fillobj(p, ['contents'])
+        assert p.title is NotLoaded
+        assert p.page_url == 'http://pastealacon.com/27184'
+        assert u'coucou\r\ncoucou\r\nhéhéhé' == p.contents