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

move select() in parser

Browse source
This commit is contained in:
Romain Bignon 2011-04-08 19:39:57 +02:00
commit 9afb301ebe
30 changed files with 197 additions and 197 deletions
Download patch file Download diff file Expand all files Collapse all files

32
weboob/backends/inrocks/pages/article.py
View file

@ -18,7 +18,7 @@
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.tools.parsers.lxmlparser import select, SelectElementException
from weboob.tools.browser import BrokenPageError
from weboob.tools.genericArticle import GenericNewsPage, try_remove, \
try_remove_from_selector_list, \
drop_comments, NoneMainDiv
@ -35,26 +35,28 @@ class ArticlePage(GenericNewsPage):
try :
element_body = self.get_element_body()
except NoneMainDiv:
return None
return None
else:
div_header_element = select(element_body, "div.header", 1)
element_detail = select(element_body, "div.details", 1)
div_content_element = select(element_body, "div.content", 1)
div_header_element = self.parser.select(element_body, "div.header", 1)
element_detail = self.parser.select(element_body, "div.details", 1)
div_content_element = self.parser.select(element_body, "div.content", 1)
drop_comments(element_body)
try_remove(element_body, "div.sidebar")
try_remove(element_detail, "div.footer")
try_remove_from_selector_list(div_header_element,
["h1", "div.picture", "div.date",
"div.news-single-img",
try_remove(self.parser, element_body, "div.sidebar")
try_remove(self.parser, element_detail, "div.footer")
try_remove_from_selector_list(self.parser,
div_header_element,
["h1", "div.picture", "div.date",
"div.news-single-img",
"div.metas_img", "strong"])
try_remove_from_selector_list(div_content_element,
try_remove_from_selector_list(self.parser,
div_content_element,
["div.tw_button", "div.wpfblike"])
try :
description_element = select(div_header_element,
description_element = self.parser.select(div_header_element,
"div.description", 1)
except SelectElementException:
except BrokenPageError:
pass
else:
text_content = description_element.text_content()
@ -75,6 +77,4 @@ class ArticlePage(GenericNewsPage):
div_content_element.drop_tag()
return self.browser.parser.tostring(element_body)
return self.parser.tostring(element_body)