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

try to resolve this fucking encoding bug

Browse source
This commit is contained in:
juke 2011-02-02 20:04:53 +01:00 • committed by Romain Bignon
commit 75859bd5f4
2 changed files with 11 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

1
weboob/applications/cleanboob/cleanboob.py
View file

@ -35,4 +35,5 @@ class CleanBoob(ReplApplication):
def main(self, argv): def main(self, argv):
for backend, content in self.do('get_thread', argv[1]): for backend, content in self.do('get_thread', argv[1]):
self.format(content) self.format(content)
#print content
return 0 return 0

19
weboob/backends/minutes20/pages/article.py
View file

@ -15,10 +15,10 @@
# along with this program; if not, write to the Free Software # along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
from weboob.tools.browser import BasePage from weboob.tools.browser import BasePage
from weboob.tools.parsers.lxmlparser import select from weboob.tools.parsers.lxmlparser import select, SelectElementException
import lxml
import sys
class Article(object): class Article(object):
def __init__(self): def __init__(self):
self.title = u'' self.title = u''
@ -33,20 +33,21 @@ class ArticlePage(BasePage):
def set_article(self): def set_article(self):
self.article = Article() self.article = Article()
#elp(self.get_title().encode('iso8859-1'))
self.article.title = self.get_title() self.article.title = self.get_title()
self.article.body = self.get_article() self.article.body = self.get_article()
def get_title(self): def get_title(self):
return self.browser.parser.tostring(select(self.document.getroot(), "h1", 1)) return self.browser.parser.tostring(select(self.document.getroot(), "h1", 1))
def get_article(self): def get_article(self):
main_div = self.document.getroot() main_div = self.document.getroot()
article_body = select(main_div, "div.mn-line>div.mna-body")[0] article_body = select(main_div, "div.mn-line>div.mna-body", 1)
txt_article = article_body.text_content() txt_article = self.browser.parser.tostring(article_body)
txt_to_remove = select(article_body, "div.mna-tools")[0].text_content() try:
txt_to_remove2 = select(main_div, "div.mn-line>div.mna-body>div.mna-comment-call")[0].text_content() txt_to_remove = self.browser.parser.tostring(select(article_body, "div.mna-tools", 1))
except SelectElementException:
txt_to_remove = ''
txt_to_remove2 = self.browser.parser.tostring(select(main_div, "div.mn-line>div.mna-body>div.mna-comment-call", 1))
return txt_article.replace(txt_to_remove, '', 1).replace( txt_to_remove2, '', 1) return txt_article.replace(txt_to_remove, '', 1).replace( txt_to_remove2, '', 1)
def get_content(self): def get_content(self):