nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

uniform minutes20 and inrocks

Browse source
This commit is contained in:
Juke 2011-02-17 04:06:01 +01:00 • committed by Romain Bignon
commit 2ebe8012bd
10 changed files with 76 additions and 97 deletions
Download patch file Download diff file Expand all files Collapse all files

34
weboob/backends/minutes20/pages/article.py
View file

@ -1,5 +1,6 @@
"ArticlePage object for minutes20"
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Julien Hebert
#
# This program is free software; you can redistribute it and/or modify
@ -15,30 +16,19 @@
# 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 .minutes20 import Minutes20Page, NoAuthorElement
def try_remove(base_element, selector):
try :
base_element.remove(select(base_element, selector, 1 ))
except (SelectElementException, ValueError):
pass
class ArticlePage(Minutes20Page):
"ArticlePage object for minutes20"
def set_body(self):
self.element_body = select(self.main_div, "div.mna-body", 1)
element_tools = select(self.element_body, "div.mna-tools", 1)
try :
self.element_body.remove(element_tools)
except ValueError:
pass
try:
self.element_body.remove(
select(self.element_body, "div.mna-comment-call", 1))
except (SelectElementException, ValueError):
pass
try:
self.element_body.remove(self.get_element_author())
except (NoAuthorElement, ValueError):
pass
self.article.body = self.browser.parser.tostring(self.element_body)
def get_body(self):
try_remove(self.element_body, "div.mna-tools")
try_remove(self.element_body, "div.mna-comment-call")
try_remove(self.element_body, self.element_author_selector)
return self.browser.parser.tostring(self.element_body)

42
weboob/backends/minutes20/pages/minutes20.py
View file

@ -29,38 +29,38 @@ class Article(object):
self.title = u''
self.body = u''
self.url = u''
self.author = u''
self.author = u''
self.date = None
class Minutes20Page(BasePage):
main_div = NotImplementedError
element_body = NotImplementedError
article = Article
def set_author(self):
self.article.author = self.get_element_author().text_content().strip()
element_author_selector = ValueError
element_title_selector = ValueError
element_body_selector = ValueError
def get_element_author(self):
try :
return select(self.main_div, "div.mna-signature", 1)
except SelectElementException:
raise NoAuthorElement()
def get_body(self):
return self.browser.parser.tostring(self.element_body)
def set_body(self):
self.article.body = self.browser.parser.tostring(select(self.main_div,
"div.mna-body",
1))
def get_author(self):
return select(self.main_div, self.element_author_selector, 1).text_content().strip()
def get_title(self):
return select(self.main_div, self.element_title_selector, 1).text_content().strip()
def on_loaded(self):
self.article = Article(self.browser, url2id(self.url) )
self.main_div = self.document.getroot()
self.article.title = select(self.main_div, "h1", 1).text_content()
self.article.url = self.url
try :
self.set_author()
except NoAuthorElement:
pass
self.set_body()
self.element_author_selector = "div.mna-signature"
self.element_title_selector = "h1"
self.element_body_selector = "div.mna-body"
self.element_body = select(self.main_div, self.element_body_selector, 1)
self.article.author = self.get_author()
self.article.title = self.get_title()
self.article.url = self.url
self.article.body = self.get_body()