modules/codimd/browser.py

@@ -141,7 +141,7 @@ def push_content(self, content):
 
             # add the note to user history
             # t= is supposed to be unique? a constant works fine
-            self.socket.open(note=content.id, t='WEBOOB')
+            self.socket.open(note=content.id, t='WOOB')
             return content
 
     # deleting a note is done in /socket.io route

modules/codimd/module.py

@@ -32,7 +32,7 @@
 
 class CodimdModule(Module, CapContent):
     NAME = 'codimd'
-    DESCRIPTION = 'CodiMD'
+    DESCRIPTION = 'HedgeDoc'
     MAINTAINER = 'Vincent A'
     EMAIL = 'dev@indigo.re'
     LICENSE = 'LGPLv3+'
@@ -41,7 +41,7 @@ class CodimdModule(Module, CapContent):
     BROWSER = CodimdBrowser
 
     CONFIG = BackendConfig(
-        Value('baseurl', label='URL of the CodiMD instance', default='https://hackmd.io/'),
+        Value('baseurl', label='URL of the HedgeDoc instance', default='https://demo.hedgedoc.org/'),
         ValueBackendPassword('login', label='Email or LDAP username', default=''),
         ValueBackendPassword('password', label='Password', default=''),
     )

modules/codimd/pages.py

@@ -46,7 +46,7 @@ class NotePage(RawPage):
     def get_title(self):
         return unquote(
             re.search(
-                r'filename=(?P<q>"?)(?P<name>.*?)(?P=q)',
+                r'filename=(?P<q>"?)(?P<name>.*?)(?P=q)(;|$)',
                 self.response.headers['Content-Disposition']
             )['name']
         )

modules/codimd/test.py

@@ -26,6 +26,10 @@
 class CodimdTest(BackendTest):
     MODULE = 'codimd'
 
+    def login_cb(self, backend_name, value):
+        # accept empty credentials, that should be ok for features.md on the main domain
+        return ''
+
     def test_get_simple(self):
         content = self.backend.get_content('features')
         assert content
@@ -34,4 +38,8 @@ def test_get_simple(self):
         assert content.title == 'Features.md'
 
         assert content.content
-        assert content.content.startswith('# Features')
+        assert (
+            content.content.startswith('# Features')
+            # newer versions have yaml frontmatter
+            or '\n# Features' in content.content
+        )

modules/enercoop/pages.py

@@ -156,12 +156,8 @@ def _history_on_page(self):
         if not script_l:
             return
 
-        script = script_l[0].text
-
-        jvalues = re.search(r"window.x_axis_values=([^;]+)", script)[1]
-        xvalues = json.loads(jvalues)
-        jvalues = re.search(r"window.y_axis_values=([^;]+)", script)[1]
-        yvalues = json.loads(jvalues)
+        xvalues = json.loads(script_l[0].attrib["data-x-axis-values"])
+        yvalues = json.loads(script_l[0].attrib["data-y-axis-values"])
 
         xvalues, yvalues = self._tweak_values(xvalues, yvalues)
         if all(yv == 0 for yv in yvalues):

modules/free/browser.py

@@ -21,8 +21,9 @@
 
 from woob.browser import LoginBrowser, URL, need_login
 from woob.exceptions import BrowserIncorrectPassword, BrowserUnavailable
+from woob.tools.capabilities.bill.documents import sorted_documents, merge_iterators
 
-from .pages import LoginPage, HomePage, ConsolePage, SuiviPage, DocumentsPage, ProfilePage
+from .pages import LoginPage, HomePage, ConsolePage, SuiviPage, DocumentsPage, ProfilePage, ContractPage
 
 
 class FreeBrowser(LoginBrowser):
@@ -35,6 +36,7 @@ class FreeBrowser(LoginBrowser):
     documents = URL(r'/liste-factures.pl(?P<urlid>.*)', DocumentsPage)
     profile = URL(r'/modif_infoscontact.pl(?P<urlid>.*)', ProfilePage)
     address = URL(r'/show_adresse.pl(?P<urlid>.*)', ProfilePage)
+    contracts = URL(r"/afficher-cgv.pl(?P<urlid>.*)", ContractPage)
 
     def __init__(self, *args, **kwargs):
         LoginBrowser.__init__(self, *args, **kwargs)
@@ -79,7 +81,14 @@ def get_subscription_list(self):
 
     @need_login
     def iter_documents(self, subscription):
-        return self.documents.stay_or_go(urlid=self.urlid).get_documents(subid=subscription.id)
+        self.contracts.stay_or_go(urlid=self.urlid)
+        contracts_iterator = sorted_documents(self.page.iter_documents(subscription_id=subscription.id))
+
+        self.documents.stay_or_go(urlid=self.urlid)
+        bills_iterator = sorted_documents(self.page.get_documents(subid=subscription.id))
+
+        for doc in merge_iterators(contracts_iterator, bills_iterator):
+            yield doc
 
     @need_login
     def get_profile(self):

modules/free/pages.py

@@ -20,10 +20,10 @@
 from __future__ import unicode_literals
 
 from woob.browser.pages import HTMLPage, LoggedPage, RawPage
-from woob.browser.filters.standard import CleanDecimal, CleanText, Env, Format, Regexp
+from woob.browser.filters.standard import CleanDecimal, CleanText, Env, Format, Field, Eval, Regexp, QueryValue, Slugify, Date
 from woob.browser.elements import ListElement, ItemElement, method
-from woob.browser.filters.html import Attr
-from woob.capabilities.bill import DocumentTypes, Bill, Subscription
+from woob.browser.filters.html import Link
+from woob.capabilities.bill import DocumentTypes, Bill, Subscription, Document
 from woob.capabilities.profile import Profile
 from woob.capabilities.base import NotAvailable
 from woob.tools.date import parse_french_date
@@ -88,9 +88,8 @@ class get_documents(ListElement):
         class item(ItemElement):
             klass = Bill
 
-            obj_id = Format('%s_%s', Env('subid'), Regexp(Attr('./span[1]/a', 'href'),
-                                                          r'(?<=.facture=)([^*]+)'))
-            obj_url = Attr('./span[1]/a', 'href', default=NotAvailable)
+            obj_id = Format('%s_%s', Env('subid'), QueryValue(Field("url"), "no_facture"))
+            obj_url = Link("./span[1]/a", default=NotAvailable)
             obj_date = Env('date')
             obj_format = 'pdf'
             obj_label = Format("Facture %s", CleanText("./span[2]"))
@@ -114,3 +113,34 @@ def get_profile(self, subscriber):
     def set_address(self, profile):
         assert len(self.doc.xpath('//p/strong[contains(text(), " ")]')) == 1, 'There are several addresses.'
         profile.address = CleanText('//p/strong[contains(text(), " ")]')(self.doc) or NotAvailable
+
+
+class ContractPage(LoggedPage, HTMLPage):
+    @method
+    class iter_documents(ListElement):
+        item_xpath = (
+            '//div[has-class("monabo")]//ul[has-class("no_arrow")]/li[not(@class)]//a'
+        )
+
+        class item(ItemElement):
+            klass = Document
+            obj_url = Link(".")
+            obj_date = Date(
+                CleanText(
+                    'ancestor::div[contains(@class, "monabo")]//strong/span[@class="red"]'
+                ),
+                dayfirst=True,
+            )
+            obj_id = Format(
+                "%s_%s_%s",
+                Env("subscription_id"),
+                Eval(lambda t: t.strftime("%Y%m%d"), Field("date")),
+                Slugify(Regexp(Field("url"), r"([^/]+)\.pdf")),
+            )
+            obj_type = DocumentTypes.CONTRACT
+            obj_label = Format(
+                "%s (%s)",
+                CleanText("ancestor::li"),
+                Regexp(Field("url"), r"([^/]+)\.pdf"),
+            )
+            obj_format = "pdf"

modules/lutim/browser.py

@@ -17,6 +17,8 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this woob module. If not, see <http://www.gnu.org/licenses/>.
 
+# flake8: compatible
+
 from base64 import b64decode, b64encode
 import math
 from io import BytesIO
@@ -29,10 +31,9 @@
 
 class LutimBrowser(PagesBrowser):
     BASEURL = 'https://lut.im'
-    VERIFY = False # XXX SNI is not supported
 
-    image_page = URL('/(?P<id>.+)', ImagePage)
-    upload_page = URL('/', UploadPage)
+    image_page = URL('(?P<id>.+)', ImagePage)
+    upload_page = URL('', UploadPage)
 
     def __init__(self, base_url, *args, **kw):
         PagesBrowser.__init__(self, *args, **kw)
@@ -46,12 +47,12 @@ def fetch(self, paste):
 
     def post(self, paste, max_age=0):
         bin = b64decode(paste.contents)
-        name = paste.title or 'file' # filename is mandatory
+        name = paste.title or 'file'  # filename is mandatory
         filefield = {'file': (name, BytesIO(bin))}
         params = {'format': 'json'}
         if max_age:
             params['delete-day'] = int(math.ceil(max_age / 86400.))
-        self.location('/', data=params, files=filefield)
+        self.location(self.BASEURL, data=params, files=filefield)
         assert self.upload_page.is_here()
         info = self.page.fetch_info()
         paste.id = urljoin(self.base_url, info['short'])

modules/lutim/module.py

@@ -17,6 +17,7 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this woob module. If not, see <http://www.gnu.org/licenses/>.
 
+# flake8: compatible
 
 import re
 
@@ -34,7 +35,7 @@
 
 class LutimModule(Module, CapPaste):
     NAME = 'lutim'
-    DESCRIPTION = u'lutim website'
+    DESCRIPTION = u"Lutim (Let's Upload That IMage)"
     MAINTAINER = u'Vincent A'
     EMAIL = 'dev@indigo.re'
     LICENSE = 'AGPLv3+'
@@ -42,7 +43,7 @@ class LutimModule(Module, CapPaste):
 
     BROWSER = LutimBrowser
 
-    CONFIG = BackendConfig(Value('base_url', label='Hoster base URL', default='https://lut.im/'))
+    CONFIG = BackendConfig(Value('base_url', label='Hoster base URL'))
 
     @property
     def base_url(self):
@@ -58,9 +59,9 @@ def can_post(self, contents, title=None, public=None, max_age=None):
         if public:
             return 0
         elif max_age and max_age < 86400:
-            return 0 # it cannot be shorter than one day
+            return 0  # it cannot be shorter than one day
         elif re.search(r'[^a-zA-Z0-9=+/\s]', contents):
-            return 0 # not base64, thus not binary
+            return 0  # not base64, thus not binary
         else:
             mime = image_mime(contents, ('gif', 'jpeg', 'png'))
             return 20 * int(mime is not None)

modules/lutim/pages.py

@@ -17,8 +17,10 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this woob module. If not, see <http://www.gnu.org/licenses/>.
 
+# flake8: compatible
 
 import re
+
 from woob.browser.pages import JsonPage, RawPage
 from woob.capabilities.base import UserError
 

modules/sachsen/__init__.py → modules/payfit/__init__.py

 # -*- coding: utf-8 -*-
 
-# Copyright(C) 2010-2014 Florent Fourcot
+# Copyright(C) 2021      Florent Fourcot
 #
 # This file is part of a woob module.
 #
 # This woob module is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
+# it under the terms of the GNU Lesser General Public License as published by
 # the Free Software Foundation, either version 3 of the License, or
 # (at your option) any later version.
 #
 # This woob module 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.
+# GNU Lesser General Public License for more details.
 #
-# You should have received a copy of the GNU Affero General Public License
+# You should have received a copy of the GNU Lesser General Public License
 # along with this woob module. If not, see <http://www.gnu.org/licenses/>.
 
-from .module import SachsenLevelModule
+from .module import PayFitModule
 
-__all__ = ['SachsenLevelModule']
+
+__all__ = ['PayFitModule']

modules/payfit/browser.py

+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2021      Florent Fourcot
+#
+# This file is part of a woob module.
+#
+# This woob module is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This woob module 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 Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with this woob module. If not, see <http://www.gnu.org/licenses/>.
+
+from woob.browser import LoginBrowser, need_login, URL
+from woob.browser.exceptions import ClientError
+from woob.browser.profiles import Firefox
+from woob.exceptions import BrowserIncorrectPassword
+from woob.capabilities.base import find_object
+from woob.capabilities.bill import DocumentNotFound
+from .pages import LoginPage, AccountListPage, UserInfoPage, DocumentsPage, CategoryPage
+
+
+class PayFitBrowser(LoginBrowser):
+    BASEURL = 'https://api.payfit.com/'
+    PROFILE = Firefox()
+
+    login = URL('/auth/signin', LoginPage)
+    account_list = URL('/hr/individuals/accounts/list', AccountListPage)  # GET
+    user_info = URL('/hr/user/info', UserInfoPage)  # POST
+    set_account = URL('/auth/updateCurrentAccount')
+    document_list = URL('/files/files', DocumentsPage)
+    category_info = URL('/files/category', CategoryPage)
+    download = URL(r'/files/file/(?P<id>\w+)\?attachment=1')
+
+    def do_login(self):
+        data = {"email": self.username,
+                "password": self.password,
+                "remember": False}
+        try:
+            self.login.go(json=data)
+        except ClientError:
+            raise BrowserIncorrectPassword()
+
+    @need_login
+    def iter_documents(self, subscription):
+        employee_id, company_id = subscription.id.split("-")
+        self.set_account.go(params={"companyId": company_id, "employeeId": employee_id})
+        self.category_info.go(params={"name": "payslip", "country": subscription._country})
+        payslip_id = self.page.get_id()
+        self.document_list.go(json={"employeeIds": [employee_id],
+                                    "companyIds": [company_id],
+                                    "categoryIds": [payslip_id]})
+        yield from self.page.iter_documents()
+
+    @need_login
+    def iter_subscription(self):
+        self.account_list.go()
+        for company, employee in self.page.iter_accounts():
+            self.set_account.go(params={"companyId": company["id"], "employeeId": employee["id"]})
+            self.user_info.go(data={})
+            yield from self.page.get_subscription(company, employee)
+
+    @need_login
+    def get_document(self, id):
+        return find_object(self.iter_documents(None), id=id,
+                           error=DocumentNotFound)

modules/payfit/module.py

+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2021      Florent Fourcot
+#
+# This file is part of a woob module.
+#
+# This woob module is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This woob module 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 Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with this woob module. If not, see <http://www.gnu.org/licenses/>.
+
+import hashlib
+import hmac
+
+from woob.tools.backend import Module, BackendConfig
+from woob.capabilities.base import find_object
+from woob.capabilities.bill import CapDocument, SubscriptionNotFound,\
+                                     Document, DocumentNotFound
+from woob.tools.value import Value, ValueBackendPassword
+
+from .browser import PayFitBrowser
+
+
+__all__ = ['PayFitModule']
+
+
+class PayFitModule(Module, CapDocument):
+    NAME = 'payfit'
+    DESCRIPTION = 'payfit website'
+    MAINTAINER = 'Florent Fourcot'
+    EMAIL = 'woob@flo.fourcot.fr'
+    LICENSE = 'LGPLv3+'
+    VERSION = '3.1'
+
+    BROWSER = PayFitBrowser
+    CONFIG = BackendConfig(Value('login', label='Email address', required=True),
+                           ValueBackendPassword('password', label='Password'))
+
+    def create_default_browser(self):
+        mac = hmac.new(self.config['password'].get().encode(), msg=b'', digestmod=hashlib.sha256)
+        return self.create_browser(self.config['login'].get(), mac.hexdigest())
+
+    def get_document(self, _id):
+        _, sub_id = _id.split("-", maxsplit=1)
+        return find_object(self.iter_documents(sub_id), id=_id,
+                           error=DocumentNotFound)
+
+    def get_subscription(self, _id):
+        return find_object(self.browser.iter_subscription(), id=_id,
+                           error=SubscriptionNotFound)
+
+    def iter_documents(self, subscription):
+        if isinstance(subscription, str):
+            subscription = self.get_subscription(subscription)
+        return self.browser.iter_documents(subscription)
+
+    def iter_subscription(self):
+        return self.browser.iter_subscription()
+
+    def download_document(self, doc):
+        if not isinstance(doc, Document):
+            doc = self.get_document(doc)
+        return self.browser.open(doc.url).content

modules/payfit/pages.py

+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2021      Florent Fourcot
+#
+# This file is part of a woob module.
+#
+# This woob module is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Lesser General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This woob module 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 Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with this woob module. If not, see <http://www.gnu.org/licenses/>.
+
+
+from woob.browser.pages import LoggedPage, JsonPage
+from woob.browser.elements import ItemElement, DictElement, method
+from woob.browser.filters.json import Dict
+from woob.capabilities.bill import Subscription, Document
+from woob.browser.filters.standard import Date, BrowserURL, Format
+
+
+class LoginPage(JsonPage):
+    pass
+
+
+class UserInfoPage(LoggedPage, JsonPage):
+    def get_subscription(self, company, employee):
+        subscription = Subscription()
+        subscription.id = f"{employee['id']}-{company['id']}"
+        subscription.label = f"{self.get('jobName')} - {self.get('companyName')}"
+        subscription.subscriber = self.get('fullName')
+        subscription._country = self.get('companyCountry')
+        yield subscription
+
+
+class AccountListPage(LoggedPage, JsonPage):
+    def iter_accounts(self):
+        for account in self.doc:
+            employee = account["accountInfo"]
+            company = account["companyInfo"]
+            if "employeeId" not in account["account"]:
+                continue
+            employee["id"] = account["account"]["employeeId"]
+            company["id"] = account["account"]["companyId"]
+            yield company, employee
+
+
+class DocumentsPage(LoggedPage, JsonPage):
+    @method
+    class iter_documents(DictElement):
+
+        class item(ItemElement):
+            klass = Document
+            obj_date = Date(Dict('createdAt'))
+            obj_format = Dict('type')
+            obj_label = Dict('name')
+            obj_id = Format("%s-%s-%s", Dict('id'), Dict('employeeId'), Dict('companyId'))
+            obj_url = BrowserURL('download', id=Dict('id'))
+
+
+class CategoryPage(LoggedPage, JsonPage):
+    def get_id(self):
+        return self.get('id')

modules/presseurop/__init__.py

-"NewspaperPresseuropModule init"
-# -*- coding: utf-8 -*-
-
-# Copyright(C) 2012  Florent Fourcot
-#
-# This file is part of a woob module.
-#
-# This woob module 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.
-#
-# This woob module 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 this woob module. If not, see <http://www.gnu.org/licenses/>.
-
-from .module import NewspaperPresseuropModule
-
-
-__all__ = ['NewspaperPresseuropModule']

modules/presseurop/browser.py

-"browser for presseurop website"
-# -*- coding: utf-8 -*-
-
-# Copyright(C) 2012  Florent Fourcot
-#
-# This file is part of a woob module.
-#
-# This woob module 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.
-#
-# This woob module 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 this woob module. If not, see <http://www.gnu.org/licenses/>.
-
-from datetime import date, datetime, time
-from .pages import PresseuropPage
-from woob.browser.browsers import AbstractBrowser
-from woob.browser.url import URL
-
-
-class NewspaperPresseuropBrowser(AbstractBrowser):
-    "NewspaperPresseuropBrowser class"
-    PARENT = 'genericnewspaper'
-    BASEURL = 'http://www.voxeurop.eu'
-
-    presseurop_page = URL("/.*", PresseuropPage)
-
-    def __init__(self, *args, **kwargs):
-        self.weboob = kwargs['weboob']
-        super(NewspaperPresseuropBrowser, self).__init__(*args, **kwargs)
-
-    def get_daily_date(self, _id):
-        self.location(_id)
-        return self.page.get_daily_date()
-
-    def get_daily_infos(self, _id):
-        url = "http://www.voxeurop.eu/fr/today/" + _id
-        self.location(url)
-        title = self.page.get_title()
-        article_date = date(*[int(x)
-                              for x in _id.split('-')])
-        article_time = time(0, 0, 0)
-        article_datetime = datetime.combine(article_date, article_time)
-        return url, title, article_datetime

modules/presseurop/module.py

-# -*- coding: utf-8 -*-
-
-# Copyright(C) 2012 Florent Fourcot
-#
-# This file is part of a woob module.
-#
-# This woob module 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.
-#
-# This woob module 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 this woob module. If not, see <http://www.gnu.org/licenses/>.
-"backend for http://www.presseurop.eu"
-
-from woob.capabilities.messages import CapMessages, Thread
-from woob.tools.backend import AbstractModule
-
-from woob.tools.backend import BackendConfig
-from woob.tools.value import Value
-from .browser import NewspaperPresseuropBrowser
-from .tools import rssid, url2id
-from woob.tools.newsfeed import Newsfeed
-
-
-class NewspaperPresseuropModule(AbstractModule, CapMessages):
-    MAINTAINER = u'Florent Fourcot'
-    EMAIL = 'weboob@flo.fourcot.fr'
-    VERSION = '3.1'
-    LICENSE = 'AGPLv3+'
-    STORAGE = {'seen': {}}
-    NAME = 'presseurop'
-    DESCRIPTION = u'Presseurop website'
-    BROWSER = NewspaperPresseuropBrowser
-    RSSID = staticmethod(rssid)
-    URL2ID = staticmethod(url2id)
-    RSSSIZE = 300
-    PARENT = 'genericnewspaper'
-    CONFIG = BackendConfig(Value('lang', label='Lang of articles',
-                           choices={'fr': 'fr', 'de': 'de', 'en': 'en',
-                                    'cs': 'cs', 'es': 'es', 'it': 'it', 'nl': 'nl',
-                                    'pl': 'pl', 'pt': 'pt', 'ro': 'ro'},
-                           default='fr'))
-
-    def __init__(self, *args, **kwargs):
-        super(self.__class__, self).__init__(*args, **kwargs)
-        self.RSS_FEED = 'http://www.voxeurop.eu/%s/rss.xml' % self.config['lang'].get()
-
-    def iter_threads(self):
-        daily = []
-        for article in Newsfeed(self.RSS_FEED, self.RSSID).iter_entries():
-            if "/news-brief/" in article.link:
-                day = self.browser.get_daily_date(article.link)
-                if day and (day not in daily):
-                    localid = url2id(article.link)
-                    daily.append(day)
-                    id, title, date = self.browser.get_daily_infos(day)
-                    id = id + "#" + localid
-                    thread = Thread(id)
-                    thread.title = title
-                    thread.date = date
-                    yield(thread)
-                elif day is None:
-                    thread = Thread(article.link)
-                    thread.title = article.title
-                    thread.date = article.datetime
-                    yield(thread)
-            else:
-                thread = Thread(article.link)
-                thread.title = article.title
-                thread.date = article.datetime
-                yield(thread)

modules/presseurop/pages.py

-"ArticlePage object for presseurope"
-# -*- coding: utf-8 -*-
-
-# Copyright(C) 2012 Florent Fourcot
-#
-# This file is part of a woob module.
-#
-# This woob module 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.
-#
-# This woob module 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 this woob module. If not, see <http://www.gnu.org/licenses/>.
-
-from woob.browser.pages import AbstractPage
-from woob.browser.filters.html import CSS, CleanHTML
-
-
-class PresseuropPage(AbstractPage):
-    "PresseuropPage object for presseurop"
-    _selector = CSS
-    PARENT = 'genericnewspaper'
-    PARENT_URL = 'generic_news_page'
-
-    def on_loaded(self):
-        self.main_div = self.doc.getroot()
-        self.element_title_selector = "title"
-        self.element_author_selector = "a[rel=author], div.profilecartoontext>p>a"
-        self.element_body_selector = "div.block, div.panel, div.bodytext"
-
-    def get_body(self):
-        element_body = self.get_element_body()
-        self.try_drop_tree(element_body, "li.button-social")
-        self.try_drop_tree(element_body, "div.sharecount")
-        self.try_drop_tree(element_body, "p.ruledtop")
-        self.try_drop_tree(element_body, "p.ctafeedback")
-        self.try_drop_tree(element_body, "aside.articlerelated")
-        self.try_drop_tree(element_body, "div.sharecount")
-        self.try_drop_tree(element_body, "iframe")
-        self.clean_relativ_urls(element_body, "http://presseurop.eu")
-        return CleanHTML('.')(element_body)
-
-    def get_title(self):
-        title = super(self.__class__, self).get_title()
-        title = title.split('|')[0]
-        return title
-
-    def get_author(self):
-        author = super(self.__class__, self).get_author()
-        try:
-            source = self.doc.getroot().xpath(
-                    "//span[@class='sourceinfo']/a")[0]
-            source = source.text
-            author = author + " | " + source
-            return author
-        except:
-            return author
-
-    def get_daily_date(self):
-        plink = self.doc.getroot().xpath("//p[@class='w200']")
-        if len(plink) > 0:
-            link = plink[0].xpath('a')[0]
-            date = link.attrib['href'].split('/')[3]
-            return date
-        return None

modules/presseurop/test.py

-# -*- coding: utf-8 -*-
-
-# Copyright(C) 2012 Florent Fourcot
-#
-# This file is part of a woob module.
-#
-# This woob module 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.
-#
-# This woob module 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 this woob module. If not, see <http://www.gnu.org/licenses/>.
-
-
-from woob.tools.test import BackendTest
-from woob.tools.value import Value
-
-
-class PresseuropTest(BackendTest):
-    MODULE = 'presseurop'
-
-    def setUp(self):
-        if not self.is_backend_configured():
-            self.backend.config['lang'] = Value(value='fr')
-
-    def test_new_messages(self):
-        for message in self.backend.iter_unread_messages():
-            pass