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

aibility to backends to define a specific pages charset

Browse source
This commit is contained in:
Romain Bignon 2010-04-04 16:51:05 +02:00
commit 655bc10e3e
3 changed files with 11 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

11
weboob/tools/parser.py
View file

@ -26,15 +26,12 @@ except ImportError:
try:
from elementtidy import TidyHTMLTreeBuilder
TidyHTMLTreeBuilder.ElementTree = ElementTree # force cElementTree if using it.
class HTMLTreeBuilder(TidyHTMLTreeBuilder.TidyHTMLTreeBuilder):
def __init__(self):
TidyHTMLTreeBuilder.TidyHTMLTreeBuilder.__init__(self, 'utf-8')
HTMLTreeBuilder = TidyHTMLTreeBuilder.TidyHTMLTreeBuilder
except ImportError:
from HTMLParser import HTMLParser
class HTMLTreeBuilder(HTMLParser):
def __init__(self, html=0, target=None):
def __init__(self, encoding=None):
HTMLParser.__init__(self)
if target is None:
target = ElementTree.TreeBuilder()
@ -61,8 +58,8 @@ except ImportError:
self._target.end(tag)
class StandardParser(object):
def parse(self, data):
parser = HTMLTreeBuilder()
def parse(self, data, encoding=None):
parser = HTMLTreeBuilder(encoding)
tree = ElementTree.parse(data, parser)
for elem in tree.getiterator():