move genericArticle to tools
This commit is contained in:
parent
90cd02642b
commit
5a7ae0a5bd
10 changed files with 24 additions and 206 deletions
|
|
@ -17,13 +17,11 @@
|
|||
|
||||
from .pages.article import ArticlePage
|
||||
from weboob.tools.browser import BaseBrowser
|
||||
from .tools import id2url
|
||||
|
||||
|
||||
|
||||
class NewspaperInrocksBrowser(BaseBrowser):
|
||||
PAGES = {
|
||||
'http://www.lesinrocks.com/actualite/actu-article/t/60121/date/2011-02-15/article/accuse-davoir-participe-a-une-mutinerie-un-detenu-porte-plainte/': ArticlePage,
|
||||
'.*': ArticlePage,
|
||||
|
||||
}
|
||||
|
|
|
|||
|
|
@ -16,22 +16,16 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
from .genericArticle import GenericNewsPage
|
||||
|
||||
def try_remove(base_element, selector):
|
||||
try :
|
||||
base_element.remove(select(base_element, selector, 1 ))
|
||||
except (SelectElementException, ValueError):
|
||||
pass
|
||||
from weboob.tools.parsers.lxmlparser import select
|
||||
from weboob.tools.genericArticle import GenericNewsPage, try_remove
|
||||
|
||||
class ArticlePage(GenericNewsPage):
|
||||
"ArticlePage object for inrocks"
|
||||
def on_loaded(self):
|
||||
self.main_div = self.document.getroot()
|
||||
self.element_author_selector = "div.name>span"
|
||||
self.element_body_selector = "div.maincol"
|
||||
self.element_title_selector = "h1"
|
||||
self.element_body_selector = "div.maincol"
|
||||
|
||||
def get_body(self):
|
||||
element_body = self.get_element_body()
|
||||
|
|
|
|||
|
|
@ -16,31 +16,25 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
from .genericArticle import GenericNewsPage
|
||||
|
||||
def try_remove(base_element, selector):
|
||||
try :
|
||||
base_element.remove(select(base_element, selector, 1 ))
|
||||
except (SelectElementException, ValueError):
|
||||
pass
|
||||
from weboob.tools.parsers.lxmlparser import select
|
||||
from weboob.tools.genericArticle import GenericNewsPage, try_remove
|
||||
|
||||
class ArticlePage(GenericNewsPage):
|
||||
"ArticlePage object for inrocks"
|
||||
def on_loaded(self):
|
||||
self.main_div = self.document.getroot()
|
||||
self.element_author_selector = "div.name>span"
|
||||
self.element_body_selector = "#article"
|
||||
self.element_title_selector = "h1"
|
||||
self.element_body_selector = "#article"
|
||||
|
||||
def get_body(self):
|
||||
element_body = self.get_element_body()
|
||||
h1 = select(element_body, self.element_title_selector, 1)
|
||||
div_infos = select(element_body, "div.infos", 1)
|
||||
toolsbar = select(element_body, "#toolsbar", 1)
|
||||
el_script = select(element_body, "script", 1)
|
||||
element_body = self.get_element_body()
|
||||
h1_title = select(element_body, self.element_title_selector, 1)
|
||||
div_infos = select(element_body, "div.infos", 1)
|
||||
toolsbar = select(element_body, "#toolsbar", 1)
|
||||
el_script = select(element_body, "script", 1)
|
||||
|
||||
element_body.remove(h1)
|
||||
element_body.remove(h1_title)
|
||||
element_body.remove(div_infos)
|
||||
element_body.remove(toolsbar)
|
||||
|
||||
|
|
|
|||
|
|
@ -16,14 +16,7 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
from .genericArticle import GenericNewsPage
|
||||
|
||||
def try_remove(base_element, selector):
|
||||
try :
|
||||
base_element.remove(select(base_element, selector, 1 ))
|
||||
except (SelectElementException, ValueError):
|
||||
pass
|
||||
from weboob.tools.genericArticle import GenericNewsPage
|
||||
|
||||
class FlashActuPage(GenericNewsPage):
|
||||
"ArticlePage object for inrocks"
|
||||
|
|
|
|||
|
|
@ -1,81 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2011 Julien Hebert
|
||||
#
|
||||
# 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.
|
||||
from weboob.tools.browser import BasePage
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
|
||||
class NoAuthorElement(SelectElementException):
|
||||
pass
|
||||
|
||||
class NoneMainDiv(AttributeError):
|
||||
pass
|
||||
|
||||
class Article(object):
|
||||
author = u''
|
||||
|
||||
def __init__(self, browser, _id):
|
||||
self.browser = browser
|
||||
self.id = _id
|
||||
self.title = u''
|
||||
self.body = u''
|
||||
self.url = u''
|
||||
self.date = None
|
||||
|
||||
class GenericNewsPage(BasePage):
|
||||
__element_body = NotImplementedError
|
||||
__article = Article
|
||||
element_title_selector = NotImplementedError
|
||||
main_div = NotImplementedError
|
||||
element_body_selector = NotImplementedError
|
||||
element_author_selector = NotImplementedError
|
||||
|
||||
def get_body(self):
|
||||
return self.browser.parser.tostring(self.get_element_body())
|
||||
|
||||
def get_author(self):
|
||||
try:
|
||||
return self.get_element_author().text_content().strip()
|
||||
except NoAuthorElement:
|
||||
return self.__article.author
|
||||
|
||||
def get_title(self):
|
||||
return select(
|
||||
self.main_div,
|
||||
self.element_title_selector,
|
||||
1).text_content().strip()
|
||||
|
||||
def get_element_body(self):
|
||||
return select(self.main_div, self.element_body_selector, 1)
|
||||
|
||||
def get_element_author(self):
|
||||
try:
|
||||
return select(self.main_div, self.element_author_selector, 1)
|
||||
except SelectElementException:
|
||||
raise NoAuthorElement()
|
||||
except AttributeError:
|
||||
if self.main_div == None:
|
||||
raise NoneMainDiv("main_div is none on %s" % (self.browser))
|
||||
else:
|
||||
raise
|
||||
|
||||
def get_article(self, _id):
|
||||
__article = Article(self.browser, _id)
|
||||
__article.author = self.get_author()
|
||||
__article.title = self.get_title()
|
||||
__article.url = self.url
|
||||
__article.body = self.get_body()
|
||||
|
||||
return __article
|
||||
|
|
@ -16,7 +16,7 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
from .genericArticle import GenericNewsPage
|
||||
from weboob.tools.genericArticle import GenericNewsPage
|
||||
|
||||
class SimplePage(GenericNewsPage):
|
||||
"ArticlePage object for minutes20"
|
||||
|
|
|
|||
|
|
@ -16,16 +16,9 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
from .genericArticle import NoAuthorElement
|
||||
from weboob.tools.genericArticle import NoAuthorElement, try_remove
|
||||
from .simple import SimplePage
|
||||
|
||||
def try_remove(base_element, selector):
|
||||
try :
|
||||
base_element.remove(select(base_element, selector, 1 ))
|
||||
except (SelectElementException, ValueError):
|
||||
pass
|
||||
|
||||
class ArticlePage(SimplePage):
|
||||
"ArticlePage object for minutes20"
|
||||
|
||||
|
|
|
|||
|
|
@ -1,81 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2011 Julien Hebert
|
||||
#
|
||||
# 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.
|
||||
from weboob.tools.browser import BasePage
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
|
||||
class NoAuthorElement(SelectElementException):
|
||||
pass
|
||||
|
||||
class NoneMainDiv(AttributeError):
|
||||
pass
|
||||
|
||||
class Article(object):
|
||||
author = u''
|
||||
|
||||
def __init__(self, browser, _id):
|
||||
self.browser = browser
|
||||
self.id = _id
|
||||
self.title = u''
|
||||
self.body = u''
|
||||
self.url = u''
|
||||
self.date = None
|
||||
|
||||
class GenericNewsPage(BasePage):
|
||||
__element_body = NotImplementedError
|
||||
__article = Article
|
||||
element_title_selector = NotImplementedError
|
||||
main_div = NotImplementedError
|
||||
element_body_selector = NotImplementedError
|
||||
element_author_selector = NotImplementedError
|
||||
|
||||
def get_body(self):
|
||||
return self.browser.parser.tostring(self.get_element_body())
|
||||
|
||||
def get_author(self):
|
||||
try:
|
||||
return self.get_element_author().text_content().strip()
|
||||
except NoAuthorElement:
|
||||
return self.__article.author
|
||||
|
||||
def get_title(self):
|
||||
return select(
|
||||
self.main_div,
|
||||
self.element_title_selector,
|
||||
1).text_content().strip()
|
||||
|
||||
def get_element_body(self):
|
||||
return select(self.main_div, self.element_body_selector, 1)
|
||||
|
||||
def get_element_author(self):
|
||||
try:
|
||||
return select(self.main_div, self.element_author_selector, 1)
|
||||
except SelectElementException:
|
||||
raise NoAuthorElement()
|
||||
except AttributeError:
|
||||
if self.main_div == None:
|
||||
raise NoneMainDiv("main_div is none on %s" % (self.browser))
|
||||
else:
|
||||
raise
|
||||
|
||||
def get_article(self, _id):
|
||||
__article = Article(self.browser, _id)
|
||||
__article.author = self.get_author()
|
||||
__article.title = self.get_title()
|
||||
__article.url = self.url
|
||||
__article.body = self.get_body()
|
||||
|
||||
return __article
|
||||
|
|
@ -16,7 +16,8 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
from .genericArticle import GenericNewsPage
|
||||
from weboob.tools.genericArticle import GenericNewsPage
|
||||
|
||||
|
||||
class SimplePage(GenericNewsPage):
|
||||
"ArticlePage object for minutes20"
|
||||
|
|
|
|||
|
|
@ -17,6 +17,13 @@
|
|||
from weboob.tools.browser import BasePage
|
||||
from weboob.tools.parsers.lxmlparser import select, SelectElementException
|
||||
|
||||
def try_remove(base_element, selector):
|
||||
try :
|
||||
base_element.remove(select(base_element, selector, 1 ))
|
||||
except (SelectElementException, ValueError):
|
||||
pass
|
||||
|
||||
|
||||
class NoAuthorElement(SelectElementException):
|
||||
pass
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue