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

Allow forcing a Page content encoding

Browse source
This commit is contained in:
Laurent Bachelier 2014-05-16 15:37:24 +02:00
commit 82f47bff88
1 changed files with 14 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

16
weboob/tools/browser2/page.py
View file

@ -517,9 +517,15 @@ class JsonPage(BasePage):
class XMLPage(BasePage): class XMLPage(BasePage):
ENCODING = None
"""
Force a page encoding.
It is recommended to use None for autodetection.
"""
def __init__(self, browser, response, *args, **kwargs): def __init__(self, browser, response, *args, **kwargs):
super(XMLPage, self).__init__(browser, response, *args, **kwargs) super(XMLPage, self).__init__(browser, response, *args, **kwargs)
parser = etree.XMLParser(encoding=response.encoding) parser = etree.XMLParser(encoding=self.ENCODING or response.encoding)
self.doc = etree.parse(StringIO(response.content), parser) self.doc = etree.parse(StringIO(response.content), parser)
@ -535,9 +541,15 @@ class HTMLPage(BasePage):
""" """
FORM_CLASS = Form FORM_CLASS = Form
ENCODING = None
"""
Force a page encoding.
It is recommended to use None for autodetection.
"""
def __init__(self, browser, response, *args, **kwargs): def __init__(self, browser, response, *args, **kwargs):
super(HTMLPage, self).__init__(browser, response, *args, **kwargs) super(HTMLPage, self).__init__(browser, response, *args, **kwargs)
parser = html.HTMLParser(encoding=response.encoding) parser = html.HTMLParser(encoding=self.ENCODING or response.encoding)
self.doc = html.parse(StringIO(response.content), parser) self.doc = html.parse(StringIO(response.content), parser)
def get_form(self, xpath='//form', name=None, nr=None): def get_form(self, xpath='//form', name=None, nr=None):