mirror of
https://github.com/webrecorder/pywb.git
synced 2025-03-26 07:49:24 +01:00
94784d6e5d
wombat:
- I: function overrides applied by wombat now better appear to be the original new function name same as originals when possible
- I: WombatLocation now looks and behaves more like the original Location interface
- I: The custom storage class now looks and behaves more like the original Storage
- I: SVG image rewriting has been improved: both the href and xlink:href deprecated since SVG2 now rewritten always
- I: document.open now handles the case of creation of a new window
- I: Request object rewriting of the readonly href property is now correctly handled
- I: EventTarget.addEventListener, removeEventListener overrides now preserve the original this argument of the wrapped listener
- A: document.close override to ensure wombat is initialized after write or writeln usage
- A: reconstruction of <doctype...> in rewriteHTMLComplete IFF it was included in the original string of HTML
- A: document.body setter override to ensure rewriting of the new body or frameset
- A: Attr.[value, nodeValue, textContent] added setter override to perform URL rewrites
- A: SVGElements rewriting of the filter, style, xlink:href, href, and src attributes
- A: HTMLTrackElement rewriting of the src attribute of the
- A: HTMLQuoteElement and HTMLModElement rewriting of the cite attribute
- A: Worklet.addModule: Loads JS module specified by a URL.
- A: HTMLHyperlinkElementUtils overrides to the areaelement
- A: ShadowRootoverrides to: innerHTML even though inherites from DocumentFragement and Node it still has innerHTML getter setter.
- A: ShadowRoot, Element, DocumentFragment append, prepend: adds strings of HTML or a new Node inherited from ParentNode
- A: StylePropertyMap override: New way to access and set CSS properties.
- A: Response.redirecthttps rewriting of the URL argument.
- A: UIEvent, MouseEvent, TouchEvent, KeyboardEvent, WheelEvent, InputEvent, and CompositionEven constructor and init{even-name} overrides in order to ensure that wombats JS Proxy usage does not affect their defined behaviors
- A: XSLTProcessor override to ensure its usage is not affected by wombats JS Proxy usage.
- A: navigator.unregisterProtocolHandler: Same override as existing navigator.registerProtocolHandler but from the inverse operation
- A: PresentationRequest: Constructor takes a URL or an array of URLs.
- A: EventSource and WebSocket override in order to ensure that they do not cause live leaks
- A: overrides for the child node interface
- Fix: autofetch worker creatation of the backing worker when it is operating within an execution context with a null origin
tests:
- A: 559 tests specific to wombat and client side rewritting
pywb:
- Fix: a few broken tests due to iana.org requiring a user agent in its requests
rewrite:
- introduced a new JSWorkerRewriter class in order to support rewriting via wombat workers in the context of all supported worker variants via
- ensured rewriter app correctly sets the static prefix
ci:
- Modified travis.yml to specifically enumerate jobs
documentation:
- Documented new wombat, wombat proxy moded, wombat workers
auto-fetch:
- switched to mutation observer when in proxy mode so that the behaviors can operate in tandem with the autofetcher
147 lines
4.0 KiB
Python
147 lines
4.0 KiB
Python
from pywb.rewrite.content_rewriter import BaseContentRewriter
|
|
|
|
from pywb.rewrite.html_rewriter import HTMLRewriter
|
|
from pywb.rewrite.html_insert_rewriter import HTMLInsertOnlyRewriter
|
|
|
|
from pywb.rewrite.regex_rewriters import RegexRewriter, CSSRewriter, XMLRewriter
|
|
from pywb.rewrite.regex_rewriters import JSLocationOnlyRewriter, JSNoneRewriter, JSWombatProxyRewriter
|
|
|
|
from pywb.rewrite.header_rewriter import DefaultHeaderRewriter
|
|
from pywb.rewrite.cookie_rewriter import HostScopeCookieRewriter
|
|
|
|
from pywb.rewrite.jsonp_rewriter import JSONPRewriter
|
|
|
|
from pywb.rewrite.rewrite_dash import RewriteDASH
|
|
from pywb.rewrite.rewrite_hls import RewriteHLS
|
|
from pywb.rewrite.rewrite_amf import RewriteAMF
|
|
|
|
from pywb.rewrite.rewrite_js_workers import JSWorkerRewriter
|
|
|
|
from pywb import DEFAULT_RULES_FILE
|
|
|
|
import copy
|
|
from werkzeug.useragents import UserAgent
|
|
|
|
|
|
# ============================================================================
|
|
class DefaultRewriter(BaseContentRewriter):
|
|
DEFAULT_REWRITERS = {
|
|
'header': DefaultHeaderRewriter,
|
|
'cookie': HostScopeCookieRewriter,
|
|
|
|
'html': HTMLRewriter,
|
|
'html-banner-only': HTMLInsertOnlyRewriter,
|
|
|
|
'css': CSSRewriter,
|
|
|
|
'js': JSLocationOnlyRewriter,
|
|
'js-proxy': JSNoneRewriter,
|
|
'js-worker': JSWorkerRewriter,
|
|
|
|
'json': JSONPRewriter,
|
|
|
|
'xml': XMLRewriter,
|
|
|
|
'dash': RewriteDASH,
|
|
|
|
'hls': RewriteHLS,
|
|
|
|
'amf': RewriteAMF,
|
|
}
|
|
|
|
rewrite_types = {
|
|
# HTML
|
|
'text/html': 'guess-html',
|
|
'application/xhtml': 'html',
|
|
'application/xhtml+xml': 'html',
|
|
|
|
# CSS
|
|
'text/css': 'css',
|
|
|
|
# JS
|
|
'text/javascript': 'js',
|
|
'application/javascript': 'js',
|
|
'application/x-javascript': 'js',
|
|
|
|
# JSON
|
|
'application/json': 'json',
|
|
|
|
# HLS
|
|
'application/x-mpegURL': 'hls',
|
|
'application/vnd.apple.mpegurl': 'hls',
|
|
|
|
# DASH
|
|
'application/dash+xml': 'dash',
|
|
|
|
# AMF
|
|
'application/x-amf': 'amf',
|
|
|
|
# XML -- don't rewrite xml
|
|
#'text/xml': 'xml',
|
|
#'application/xml': 'xml',
|
|
#'application/rss+xml': 'xml',
|
|
|
|
# PLAIN
|
|
'text/plain': 'guess-text',
|
|
|
|
# DEFAULT or octet-stream
|
|
'': 'guess-text',
|
|
'application/octet-stream': 'guess-bin'
|
|
}
|
|
|
|
default_content_types = {
|
|
'html': 'text/html',
|
|
'css': 'text/css',
|
|
'js': 'text/javascript'
|
|
}
|
|
|
|
def __init__(self, replay_mod='', config=None):
|
|
config = config or {}
|
|
rules_file = config.get('rules_file', DEFAULT_RULES_FILE)
|
|
super(DefaultRewriter, self).__init__(rules_file, replay_mod)
|
|
self.all_rewriters = copy.copy(self.DEFAULT_REWRITERS)
|
|
|
|
def init_js_regex(self, regexs):
|
|
return RegexRewriter.parse_rules_from_config(regexs)
|
|
|
|
def get_rewrite_types(self):
|
|
return self.rewrite_types
|
|
|
|
|
|
# ============================================================================
|
|
class RewriterWithJSProxy(DefaultRewriter):
|
|
def __init__(self, *args, **kwargs):
|
|
super(RewriterWithJSProxy, self).__init__(*args, **kwargs)
|
|
|
|
def get_rewriter(self, rw_type, rwinfo=None):
|
|
if rw_type == 'js' and rwinfo:
|
|
# check if UA allows this
|
|
if self.ua_allows_obj_proxy(rwinfo.url_rewriter.rewrite_opts):
|
|
return JSWombatProxyRewriter
|
|
|
|
# otherwise, return default rewriter
|
|
return super(RewriterWithJSProxy, self).get_rewriter(rw_type, rwinfo)
|
|
|
|
def ua_allows_obj_proxy(self, opts):
|
|
ua = opts.get('ua')
|
|
if not ua:
|
|
ua_string = opts.get('ua_string')
|
|
if ua_string:
|
|
ua = UserAgent(ua_string)
|
|
|
|
if ua is None:
|
|
return True
|
|
|
|
supported = {
|
|
'chrome': '49.0',
|
|
'firefox': '44.0',
|
|
'safari': '10.0',
|
|
'opera': '36.0',
|
|
'edge': '12.0',
|
|
'msie': None,
|
|
}
|
|
|
|
min_vers = supported.get(ua.browser)
|
|
|
|
return (min_vers and ua.version >= min_vers)
|