Downparadise backend first commit

This commit is contained in:
Nicolas Duhamel 2011-04-12 16:14:46 +02:00 committed by Romain Bignon
commit cc52b8eb3c
9 changed files with 473 additions and 2 deletions

View file

@ -0,0 +1,23 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Nicolas Duhamel
#
# 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 .index import IndexPage
from .ucp import UcpPage
from .viewforum import ViewforumPage
__all__ = ['IndexPage', 'UcpPage', 'ViewforumPage']

View file

@ -0,0 +1,33 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Nicolas Duhamel
#
# 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/>.
import re
from weboob.tools.browser import BasePage
__all__ = ['DownparadisePage']
class DownparadisePage(BasePage):
def is_logged(self):
for form in self.document.getiterator('form'):
act = form.attrib.get('action', None)
if './ucp.php?mode=login' in act:
return False
return True

View file

@ -0,0 +1,59 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Nicolas Duhamel
#
# 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 .base import DownparadisePage
from weboob.capabilities.collection import Collection
__all__ = ['IndexPage']
class IndexPage(DownparadisePage):
def on_loaded(self):
self.collections = []
self.parse_forums()
def parse_forums(self):
""" Parse all forums """
def do(id):
self.browser.location(id)
return self.browser.page.iter_threads()
maintable = self.document.xpath("//div[@id='wrapheader']/table")[3]
for line in maintable.xpath("./tr"):
forums = line.xpath(".//a[@class='forumlink']")
for fo in forums:
coll = Collection()
coll.title = fo.text.strip().encode('latin-1')
coll.id = fo.get("href")
for link in line.getiterator('a'):
if "subforum" in link.attrib.get('class', ""):
sub = Collection(title=link.text.strip().encode('latin-1'))
sub.id = link.get("href")
sub.children = do
coll.appendchild(sub)
if not coll.children:
coll.children = do
self.collections.append(coll)
def get_collections(self):
return self.collections

View file

@ -0,0 +1,27 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Nicolas Duhamel
#
# 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 .base import DownparadisePage
__all__ = ['UcpPage']
class UcpPage(DownparadisePage):
def on_loaded(self):
pass

View file

@ -0,0 +1,45 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Nicolas Duhamel
#
# 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/>.
import re
from weboob.tools.browser import BasePage
from .base import DownparadisePage
from weboob.capabilities.collection import Collection
from weboob.capabilities.messages import Thread
__all__ = ['ViewforumPage']
def remove_html_tags(data):
p = re.compile(r'<.*?>')
return p.sub('', data)
class ViewforumPage(DownparadisePage):
def on_loaded(self):
pass
def iter_threads(self):
maintable = self.document.xpath("//div[@id='pagecontent']/table")[1]
iter_lignes = maintable.xpath(".//a[@class='topictitle']")
for i in iter_lignes:
thread = Thread(i.get("href"))
thread.title = remove_html_tags(self.parser.tostring(i)).strip().encode('raw_unicode_escape').decode('utf-8')
yield thread