def __init__(self, orig_url):
import re
import six
from six.moves.urllib.parse import urlsplit, urlunsplit
from six.moves.urllib.parse import quote_plus, quote, unquote_plus
from pywb.utils.loaders import to_native_str
from pywb.rewrite.wburl import WbUrl
pywb.rewrite.wburl.BaseWbUrl.__init__(self)
if six.PY2 and isinstance(orig_url, six.text_type):
orig_url = orig_url.encode('utf-8')
orig_url = quote(orig_url)
self._original_url = orig_url
if not self._init_query(orig_url):
if not self._init_replay(orig_url):
raise Exception('Invalid WbUrl: ', orig_url)
new_uri = WbUrl.to_uri(self.url)
self._do_percent_encode = True
self.url = new_uri
# begin brozzler changes
if (self.url.startswith('urn:') or self.url.startswith('screenshot:')
or self.url.startswith('thumbnail:')):
return
# end brozzler changes
# protocol agnostic url -> http://
# no protocol -> http://
#inx = self.url.find('://')
inx = -1
m = self.SCHEME_RX.match(self.url)
if m:
inx = m.span(1)[0]
#if inx < 0:
# check for other partially encoded variants
# m = self.PARTIAL_ENC_RX.match(self.url)
# if m:
# len_ = len(m.group(0))
# self.url = (urllib.unquote_plus(self.url[:len_]) +
# self.url[len_:])
# inx = self.url.find(':/')
if inx < 0:
self.url = self.DEFAULT_SCHEME + self.url
else:
inx += 2
if inx < len(self.url) and self.url[inx] != '/':
self.url = self.url[:inx] + '/' + self.url[inx:]
def __init__(self, orig_url):
import re
import six
from six.moves.urllib.parse import urlsplit, urlunsplit
from six.moves.urllib.parse import quote_plus, quote, unquote_plus
from pywb.utils.loaders import to_native_str
from pywb.rewrite.wburl import WbUrl
pywb.rewrite.wburl.BaseWbUrl.__init__(self)
if six.PY2 and isinstance(orig_url, six.text_type):
orig_url = orig_url.encode('utf-8')
orig_url = quote(orig_url)
self._original_url = orig_url
if not self._init_query(orig_url):
if not self._init_replay(orig_url):
raise Exception('Invalid WbUrl: ', orig_url)
new_uri = WbUrl.to_uri(self.url)
self._do_percent_encode = True
self.url = new_uri
# begin brozzler changes
if (self.url.startswith('urn:') or self.url.startswith('screenshot:')
or self.url.startswith('thumbnail:')):
return
# end brozzler changes
# protocol agnostic url -> http://
# no protocol -> http://
#inx = self.url.find('://')
inx = -1
m = self.SCHEME_RX.match(self.url)
if m:
inx = m.span(1)[0]
#if inx < 0:
# check for other partially encoded variants
# m = self.PARTIAL_ENC_RX.match(self.url)
# if m:
# len_ = len(m.group(0))
# self.url = (urllib.unquote_plus(self.url[:len_]) +
# self.url[len_:])
# inx = self.url.find(':/')
if inx < 0:
self.url = self.DEFAULT_SCHEME + self.url
else:
inx += 2
if inx < len(self.url) and self.url[inx] != '/':
self.url = self.url[:inx] + '/' + self.url[inx:]
