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

Pep8 on ecrans module

Browse source
This commit is contained in:
Florent 2012-03-13 17:31:24 +01:00
commit b0e8c10499
4 changed files with 18 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

8
modules/ecrans/backend.py
View file

@ -23,6 +23,7 @@ from weboob.tools.capabilities.messages.GenericBackend import GenericNewspaperBa
from .browser import NewspaperEcransBrowser from .browser import NewspaperEcransBrowser
from .tools import rssid, url2id from .tools import rssid, url2id
class NewspaperEcransBackend(GenericNewspaperBackend, ICapMessages): class NewspaperEcransBackend(GenericNewspaperBackend, ICapMessages):
MAINTAINER = 'Julien Hebert' MAINTAINER = 'Julien Hebert'
EMAIL = 'juke@free.fr' EMAIL = 'juke@free.fr'
@ -34,7 +35,6 @@ class NewspaperEcransBackend(GenericNewspaperBackend, ICapMessages):
BROWSER = NewspaperEcransBrowser BROWSER = NewspaperEcransBrowser
RSS_FEED = 'http://www.ecrans.fr/spip.php?page=backend' RSS_FEED = 'http://www.ecrans.fr/spip.php?page=backend'
RSSID = staticmethod(rssid) RSSID = staticmethod(rssid)
URL2ID = staticmethod(url2id) URL2ID = staticmethod(url2id)
# RSS Size is actually 10, but some articles are not sorted by publication date # RSS Size is actually 10, but some articles are not sorted by publication date
RSSSIZE = 40 RSSSIZE = 40

1
modules/ecrans/browser.py
View file

@ -22,7 +22,6 @@ from .pages.article import ArticlePage
from weboob.tools.browser import BaseBrowser from weboob.tools.browser import BaseBrowser
class NewspaperEcransBrowser(BaseBrowser): class NewspaperEcransBrowser(BaseBrowser):
"NewspaperEcransBrowser class" "NewspaperEcransBrowser class"
PAGES = { PAGES = {

9
modules/ecrans/pages/article.py
View file

@ -19,19 +19,20 @@
# along with weboob. If not, see <http://www.gnu.org/licenses/>. # along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.tools.capabilities.messages.genericArticle import GenericNewsPage, remove_from_selector_list, try_remove_from_selector_list, try_drop_tree from weboob.tools.capabilities.messages.genericArticle import GenericNewsPage, remove_from_selector_list, try_remove_from_selector_list, try_drop_tree
class ArticlePage(GenericNewsPage): class ArticlePage(GenericNewsPage):
"ArticlePage object for inrocks" "ArticlePage object for inrocks"
def on_loaded(self): def on_loaded(self):
self.main_div = self.document.getroot() self.main_div = self.document.getroot()
self.element_title_selector = "title" self.element_title_selector = "title"
self.element_author_selector = "p.auteur>a" self.element_author_selector = "p.auteur>a"
self.element_body_selector = "div.bloc_article_01" self.element_body_selector = "div.bloc_article_01"
def get_body(self): def get_body(self):
element_body = self.get_element_body() element_body = self.get_element_body()
remove_from_selector_list(self.parser, element_body, ["p.auteur", "h4" ]) remove_from_selector_list(self.parser, element_body, ["p.auteur", "h4"])
try_remove_from_selector_list(self.parser, element_body, ["p.tag", "div.alire", self.element_title_selector, "h4"]) try_remove_from_selector_list(self.parser, element_body, ["p.tag", "div.alire", self.element_title_selector, "h4"])
try_drop_tree(self.parser, element_body, "script") try_drop_tree(self.parser, element_body, "script")
return self.parser.tostring(element_body) return self.parser.tostring(element_body)

14
modules/ecrans/tools.py
View file

@ -20,25 +20,29 @@
import re import re
def id2url(_id): def id2url(_id):
"return an url from an id" "return an url from an id"
regexp2 = re.compile("(\w+).([0-9]+).(.*$)") regexp2 = re.compile("(\w+).([0-9]+).(.*$)")
match = regexp2.match(_id) match = regexp2.match(_id)
if match: if match:
return 'http://www.20minutes.fr/%s/%s/%s' % ( match.group(1), return 'http://www.20minutes.fr/%s/%s/%s' % (match.group(1),
match.group(2), match.group(2),
match.group(3)) match.group(3))
else: else:
raise ValueError("id doesn't match") raise ValueError("id doesn't match")
def url2id(url): def url2id(url):
"return an id from an url" "return an id from an url"
regexp = re.compile("(^.*),([0-9]+)\.html$") regexp = re.compile("(^.*),([0-9]+)\.html$")
match = regexp.match(url) match = regexp.match(url)
if match: if match:
return match.group(2) return match.group(2)
else: else:
raise ValueError("Can't find an id for the url") raise ValueError("Can't find an id for the url")
def rssid(entry): def rssid(entry):
return url2id(entry.id) return url2id(entry.id)