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

fix factorization of comic readers

Browse source 
there is still a race condition during the selection of the comic reader
class; sometimes, the URL matches for mangatoshokan but for some reason
mangafox is choosen instead
This commit is contained in:
Noé Rubinstein 2011-08-30 10:18:26 +02:00 • committed by Romain Bignon
commit 076a12f4e5
7 changed files with 48 additions and 177 deletions
Download patch file Download diff file Expand all files Collapse all files

78
weboob/backends/simplyreadit/backend.py
View file

@ -17,74 +17,18 @@
# 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 __future__ import with_statement
import re
from weboob.capabilities.gallery import ICapGallery, BaseGallery, BaseImage
from weboob.tools.backend import BaseBackend
from weboob.tools.browser import BaseBrowser, BasePage
from ..genericcomicreader.backend import GenericComicReaderBackend, DisplayPage
__all__ = ['SimplyreaditBackend']
class DisplayPage(BasePage):
def get_page(self, gallery):
src = self.document.xpath("//img[@class='open']/@src")[0]
return BaseImage(src,
gallery=gallery,
url=src)
def page_list(self):
return self.document.xpath("(//div[contains(@class,'dropdown_right')]/ul[@class='dropdown'])[1]/li/a/@href")
class SimplyreaditBrowser(BaseBrowser):
PAGES = { r'http://.+\.simplyread.it/reader/read/.+': DisplayPage }
def iter_gallery_images(self, gallery):
self.location(gallery.url)
assert self.is_on_page(DisplayPage)
for p in self.page.page_list():
self.location(p)
assert self.is_on_page(DisplayPage)
yield self.page.get_page(gallery)
def fill_image(self, image, fields):
if 'data' in fields:
image.data = self.readurl(image.url)
class SimplyreaditBackend(BaseBackend, ICapGallery):
class SimplyreaditBackend(GenericComicReaderBackend):
NAME = 'simplyreadit'
MAINTAINER = 'Noé Rubinstein'
EMAIL = 'noe.rubinstein@gmail.com'
VERSION = '0.9'
DESCRIPTION = 'Simplyread.it'
LICENSE = 'AGPLv3+'
BROWSER = SimplyreaditBrowser
def iter_gallery_images(self, gallery):
with self.browser:
return self.browser.iter_gallery_images(gallery)
def get_gallery(self, _id):
match = re.match(r'(?:(?:.+symplyread.it/reader/read/)?/)?([^/]+(?:/[^/]+)*)', _id)
if match is None:
return None
_id = match.group(1)
gallery = BaseGallery(_id, url=('http://www.simplyread.it/reader/read/%s' % _id))
with self.browser:
return gallery
def fill_gallery(self, gallery, fields):
gallery.title = gallery.id
def fill_image(self, image, fields):
with self.browser:
self.browser.fill_image(image, fields)
OBJECTS = {
BaseGallery: fill_gallery,
BaseImage: fill_image }
DESCRIPTION = 'Simplyreadit manga reading site'
BROWSER_PARAMS = dict(
img_src_xpath="//img[@class='open']/@src",
page_list_xpath="(//div[contains(@class,'dropdown_right')]/ul[@class='dropdown'])[1]/li/a/@href",
page_to_location="%s")
ID_TO_URL = 'http://www.simplyread.it/reader/read/%s'
ID_REGEXP = r'[^/]+(?:/[^/]+)*'
URL_REGEXP = r'.+simplyread.it/reader/read/(%s)/page/.+' % ID_REGEXP
PAGES = { r'http://.+\.simplyread.it/reader/read/.+': DisplayPage }