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

don't use tostring(), maybe add method='text'

Browse source
This commit is contained in:
juke 2011-02-02 20:37:57 +01:00 • committed by Romain Bignon
commit b3e830665b
3 changed files with 8 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

4
weboob/applications/cleanboob/cleanboob.py
View file

@ -34,6 +34,6 @@ 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 self.format(content.root)
return 0 return 0

2
weboob/backends/minutes20/backend.py
View file

@ -84,6 +84,6 @@ class Newspaper20minutesBackend(BaseBackend, ICapMessages):
#thread.root = Message(thread=thread, id=0, title=content.title, sender=content.author, receivers=None, date=thread.date, parent=None, content=content.body, signature=None, children = [], flags=flags) #thread.root = Message(thread=thread, id=0, title=content.title, sender=content.author, receivers=None, date=thread.date, parent=None, content=content.body, signature=None, children = [], flags=flags)
thread.root = Message(thread=thread, id=0, title=content.title) thread.root = Message(thread=thread, id=0, title=content.title, sender=content.author, receivers=None, date=thread.date, parent=None, content=content.body)
return thread return thread

11
weboob/backends/minutes20/pages/article.py
View file

@ -17,8 +17,7 @@
from weboob.tools.browser import BasePage from weboob.tools.browser import BasePage
from weboob.tools.parsers.lxmlparser import select, SelectElementException 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''
@ -37,17 +36,17 @@ class ArticlePage(BasePage):
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 select(self.document.getroot(), "h1", 1).text_content()
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", 1) article_body = select(main_div, "div.mn-line>div.mna-body", 1)
txt_article = self.browser.parser.tostring(article_body) txt_article = article_body.text_content()
try: try:
txt_to_remove = self.browser.parser.tostring(select(article_body, "div.mna-tools", 1)) txt_to_remove = select(article_body, "div.mna-tools", 1).text_content()
except SelectElementException: except SelectElementException:
txt_to_remove = '' txt_to_remove = ''
txt_to_remove2 = self.browser.parser.tostring(select(main_div, "div.mn-line>div.mna-body>div.mna-comment-call", 1)) txt_to_remove2 = select(main_div, "div.mn-line>div.mna-body>div.mna-comment-call", 1).text_content()
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):