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

[minutes20] fix parsing insolite pages parsing

Browse source
This commit is contained in:
Bezleputh 2014-09-16 20:39:31 +02:00 • committed by Romain Bignon
commit 9d36e7a0e6
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
modules/minutes20/pages/article.py
View file

@ -28,7 +28,7 @@ class ArticlePage(SimplePage):
self.main_div = self.document.getroot()
self.element_title_selector = "h1"
self.element_author_selector = "div.mna-signature"
self.element_body_selector = "div.mna-body"
self.element_body_selector = "div[role=main], div.mna-body"
def get_body(self):
try:
@ -38,6 +38,9 @@ class ArticlePage(SimplePage):
else:
try_remove(self.parser, element_body, "div.mna-tools")
try_remove(self.parser, element_body, "div.mna-comment-call")
try_remove(self.parser, element_body, "ul[class^=content-related]")
try_remove(self.parser, element_body, "ul[class^=content-related]")
try_remove(self.parser, element_body, "p.author-sign")
try:
element_body.remove(self.get_element_author())
except NoAuthorElement: