Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2016-01-25 09:48:44 +05:30
parent 772d285326
commit 27bf2b8b63
1 changed files with 5 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
recipes/mediapart.recipe
View File

@ -120,8 +120,7 @@ class Mediapart(BasicNewsRecipe):
date_arr = date_str.lower().split() date_arr = date_str.lower().split()
return date(day=int(date_arr[0]), return date(day=int(date_arr[0]),
year=int(date_arr[2]), year=int(date_arr[2]),
month= month=[None, 'janvier', 'février', 'mars', 'avril', 'mai', 'juin', 'juillet',
[None, 'janvier', 'février', 'mars', 'avril', 'mai', 'juin', 'juillet',
'août', 'septembre', 'octobre', 'novembre', 'décembre'].index(date_arr[1])) 'août', 'septembre', 'octobre', 'novembre', 'décembre'].index(date_arr[1]))
def print_version(self, url): def print_version(self, url):
@ -145,10 +144,10 @@ class Mediapart(BasicNewsRecipe):
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.open('https://www.mediapart.fr/user') br.open('https://www.mediapart.fr/login')
br.select_form(nr=1) br.select_form(nr=1)
br['name'] = self.username br['name'] = self.username
br['pass'] = self.password br['password'] = self.password
br.submit() br.submit()
return br return br
@ -157,16 +156,6 @@ class Mediapart(BasicNewsRecipe):
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'(<body.*?>)(.*)</body>', re.IGNORECASE|re.DOTALL), (re.compile(r'(<body.*?>)(.*)</body>', re.IGNORECASE|re.DOTALL),
lambda match: lambda match:
match.group(1) match.group(1) + re.sub(
+ re.sub(re.compile(r'</?body>', re.IGNORECASE|re.DOTALL),'', re.compile(r'</?body>', re.IGNORECASE|re.DOTALL),'', match.group(2)) + '</body>')
match.group(2))
+ '</body>')
] ]
# def preprocess_html(self, soup):
# for title in soup.findAll('p', {'class':'titre_page'}):
# title.name = 'h3'
# for legend in soup.findAll('span', {'class':'legend'}):
# legend.insert(0, Tag(soup, 'br', []))
# legend.name = 'em'
# return soup