def parse(self, url, data=None, encoding=POM.DEFAULT_ENCODING,
useragent=None, accept=None):
from pycopia.WWW import urllibplus
fo = urllibplus.urlopen(url, data, encoding, useragent=useragent, accept=accept)
if logfile:
from pycopia import UserFile
fo = UserFile.FileWrapper(fo, logfile=logfile)
return self.parse_orig(fo)
def parse(filename_url_or_file, parser=None, encoding=None, useragent=None, accept=None):
"""Parse a filename, URL, or file-like object into an HTML document
tree. Note: this returns a tree, not an element. Use
``parse(...).getroot()`` to get the document root.
"""
if parser is None:
parser = get_parser()
if isinstance(filename_url_or_file, basestring):
from pycopia.WWW import urllibplus
fp = urllibplus.urlopen(filename_url_or_file, encoding=encoding, useragent=useragent, accept=accept)
else:
fp = filename_url_or_file
return parser.parse(fp, useChardet=True)
def parse(self,
url,
data=None,
encoding=POM.DEFAULT_ENCODING,
useragent=None,
accept=None):
from pycopia.WWW import urllibplus
fo = urllibplus.urlopen(url,
data,
encoding,
useragent=useragent,
accept=accept)
self.parseFile(fo)
self.close()
def parse(self,
url,
data=None,
encoding=POM.DEFAULT_ENCODING,
useragent=None,
accept=None):
from pycopia.WWW import urllibplus
fo = urllibplus.urlopen(url,
data,
encoding,
useragent=useragent,
accept=accept)
if logfile:
from pycopia import UserFile
fo = UserFile.FileWrapper(fo, logfile=logfile)
return self.parse_orig(fo)
def parse(filename_url_or_file,
parser=None,
encoding=None,
useragent=None,
accept=None):
"""Parse a filename, URL, or file-like object into an HTML document
tree. Note: this returns a tree, not an element. Use
``parse(...).getroot()`` to get the document root.
"""
if parser is None:
parser = get_parser()
if isinstance(filename_url_or_file, basestring):
from pycopia.WWW import urllibplus
fp = urllibplus.urlopen(filename_url_or_file,
encoding=encoding,
useragent=useragent,
accept=accept)
else:
fp = filename_url_or_file
return parser.parse(fp, useChardet=True)
def parse(self, url, data=None, encoding=POM.DEFAULT_ENCODING,
useragent=None, accept=None):
from pycopia.WWW import urllibplus
fo = urllibplus.urlopen(url, data, encoding, useragent=useragent, accept=accept)
self.parseFile(fo)
self.close()