no title selector for flashactu page closes #526

This commit is contained in:
juke 2011-02-23 12:35:36 +01:00
commit 21e1dac437
2 changed files with 3 additions and 0 deletions

View file

@ -40,6 +40,7 @@ class NewspaperFigaroBrowser(BaseBrowser):
"http://www.lefigaro.fr/matieres-premieres/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/programmes-tele/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/le-talk/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/sortir-paris/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/environnement/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/rugby/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/societes/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
@ -47,6 +48,7 @@ class NewspaperFigaroBrowser(BaseBrowser):
"http://www.lefigaro.fr/conso/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/football-coupes-d-europe/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/sante/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/creation-gestion-entreprise/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
"http://www.lefigaro.fr/flash-eco/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": FlashActuPage,
}

View file

@ -24,6 +24,7 @@ class FlashActuPage(GenericNewsPage):
self.main_div = self.document.getroot()
self.element_author_selector = "div.name>span"
self.element_body_selector = "h2"
self.element_title_selector = "h1"
def get_body(self):
element_body = self.get_element_body()