def get_images(html, url):
# build js context
js = "var window = global;"
configjs_url = re.search(r'src="(http://[^"]+?/config_\w+?\.js)"',
html).group(1)
configjs = grabhtml(configjs_url, referer=url)
js += re.search(r'^(var CryptoJS|window\["\\x65\\x76\\x61\\x6c"\]).+',
configjs, re.MULTILINE).group()
js += re.search(
r'<script type="text/javascript">((eval|window\["\\x65\\x76\\x61\\x6c"\]).+?)</script',
html).group(1)
with VM(js) as vm:
files, path = vm.run("[cInfo.files, cInfo.path]")
# find server
# "http://c.3qfm.com/scripts/core_5C348B32A78647FF4208EACA42FC5F84.js"
# getpath()
corejs_url = re.search(r'src="(http://[^"]+?/core_\w+?\.js)"',
html).group(1)
corejs = grabhtml(corejs_url, referer=url)
# cache server list
servs = re.search(r"var servs=(.+?),pfuncs=", corejs).group(1)
servs = eval(servs)
servs = [host["h"] for category in servs for host in category["hosts"]]
global servers
servers = CycleList(servs)
host = servers.get()
utils = re.search(r"SMH\.(utils=.+?),SMH\.imgData=", corejs).group(1)
js = utils + """;
function getFiles(path, files, host) {
// lets try if it will be faster in javascript
return files.map(function(file){
return utils.getPath(host, path + file);
});
}
"""
with VM(js) as vm:
images = vm.call("getFiles", path, files, host)
if config.getboolean("nowebp"):
images = map(lambda i: i[:-5] if i.endswith(".webp") else i, images)
return images
def get_episodes(html, url):
html = html.replace("\n", "")
js = """
var output;
function getCookie() {}
function getcookie() {}
var window = {
open: function(result){
output = result;
}
};
var document = {
location: {
href: ""
}
};
""" + grabhtml(urljoin(url, "/js/comicview.js"))
s = []
matches = re.finditer(r'<a [^>]*?onclick="(cview[^"]+?);[^>]*>(.+?)</a>',
html, re.M)
with VM(js) as vm:
for match in matches:
cview, title = match.groups()
vm.run(cview)
ep_url = vm.run("output")
title = clean_tags(title)
e = Episode(title, urljoin(url, ep_url))
s.append(e)
return s
def get_episodes(html, url):
episodes = None
cid = re.search(r"comic/(\d+)", url).group(1)
# http://tw.ikanman.com/comic/10924/
episodes = get_list(html, cid)
# http://tw.ikanman.com/comic/4350/
if not episodes:
view_state = re.search(r'id="__VIEWSTATE" value="([^"]+)',
html).group(1)
js_main = re.search(r'src="([^"]+?/main_[^"]*?\.js)"', html).group(1)
js_main = grabhtml(js_main)
js_main = re.search(r'^window\[.+', js_main, re.M).group()
js = """
var window = global;
""" + js_main
with VM(js) as vm:
ep_html = vm.call("LZString.decompressFromBase64", view_state)
episodes = get_list(ep_html, cid)
episodes = [Episode(v[0].strip(), urljoin(url, v[1])) for v in episodes]
return episodes[::-1]
def get_images(html, url):
s_files = re.search('sFiles="([^"]+)"', html).group(1)
s_path = re.search('sPath="([^"]+)"', html).group(1)
viewhtm = grabhtml("http://www.iibq.com/script/viewhtm.js")
env = """
window = {
"eval": eval,
"parseInt": parseInt,
"String": String,
"RegExp": RegExp
};
location = {
"hostname": "www.iibq.com"
};
"""
js = env + re.search(r'(.+?)var cuImg', viewhtm, re.DOTALL).group(1)
with VM(js) as vm:
arr_files = vm.call("unsuan", s_files).split("|")
ds = grabhtml("http://www.iibq.com/script/ds.js")
sl_url = re.search('sDS = "([^"]+)"',
ds).group(1).split("^")[0].split("|")[1]
return [sl_url + s_path + f for f in arr_files]
def get_episodes(html, url):
html = html.replace("\n", "")
js = """
var output;
function getCookie() {}
var window = {
open: function(result){
output = result;
}
};
function get(url, catid) {
cview(url, catid);
return output;
}
var document = {
location: {
href: ""
}
};
""" + grabhtml(urljoin(url, "/js/comicview.js"))
s = []
matches = re.finditer(
"<a [^>]*?onclick=\"cview\('(.+?)',(\d+?)[^>]*?>(.+?)</a>", html, re.M)
with VM(js) as vm:
for match in matches:
ep_url, catid, title = match.groups()
ep_url = vm.call("get", ep_url, int(catid))
title = clean_tags(title)
e = Episode(title, urljoin(url, ep_url))
s.append(e)
return s
def get_images(html, url):
#print(html.encode('gbk','ignore').decode('gbk'))
js = re.search(r'<script type="text/javascript">(var cInfo =[^;]+;)',
html).group(1)
with VM(js) as vm:
files = vm.run("cInfo.fs")
#http://www.ccdm1.com/Public/manhuadao/js/configs.js?v=0731
server = 'http://ccimg1.61mh.com'
images = ["{server}{file}".format(server=server, file=i) for i in files]
return images
def get_images(html, url):
env = """
var photosr = new Array();
function base64decode(str){var base64EncodeChars="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";var base64DecodeChars=new Array(-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,62,-1,-1,-1,63,52,53,54,55,56,57,58,59,60,61,-1,-1,-1,-1,-1,-1,-1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,-1,-1,-1,-1,-1,-1,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,-1,-1,-1,-1,-1);var c1,c2,c3,c4;var i,len,out;len=str.length;i=0;out="";while(i<len){do{c1=base64DecodeChars[str.charCodeAt(i++)&255]}while(i<len&&c1==-1);if(c1==-1){break}do{c2=base64DecodeChars[str.charCodeAt(i++)&255]}while(i<len&&c2==-1);if(c2==-1){break}out+=String.fromCharCode((c1<<2)|((c2&48)>>4));do{c3=str.charCodeAt(i++)&255;if(c3==61){return out}c3=base64DecodeChars[c3]}while(i<len&&c3==-1);if(c3==-1){break}out+=String.fromCharCode(((c2&15)<<4)|((c3&60)>>2));do{c4=str.charCodeAt(i++)&255;if(c4==61){return out}c4=base64DecodeChars[c4]}while(i<len&&c4==-1);if(c4==-1){break}out+=String.fromCharCode(((c3&3)<<6)|c4)}return out};
eval(eval(base64decode(packed).slice(4)));
"""
js = re.search(r'(packed=[^;]+;)', html).group(1) + env
with VM(js) as vm:
arr_files = vm.run('photosr')[1:]
return ('http://img1.733mh.com/' + f for f in arr_files)
def get_images(html, url):
nview = re.search('src="([^"]*nview\.js[^"]*)"', html).group(1)
nview = urljoin(url, nview)
nview = grabhtml(nview)
try:
# http://www.comicbus.com/html/103.html
script = re.search('(var ch=.+?)spp\(\)', html, re.DOTALL).group(1)
except AttributeError:
# http://www.comicbus.com/html/7294.html
script = re.search('(var chs=.+?)</script>', html, re.DOTALL).group(1)
js = """
var url,
images = [],
document = {
location: {
toString() {return url;},
get href() {return url;},
set href(_url) {url = _url; scriptBody()}
},
getElementById() {
return {
set src(value) {
images.push(value);
},
style: {}
};
}
},
navigator = {
userAgent: "",
language: ""
},
window = {},
alert = () => {};
function scriptBody() {
initpage = () => {};
""" + nview + script + """
jn();
}
function getImages(url) {
images = [];
document.location.href = url;
return images;
}
"""
with VM(js) as vm:
images = vm.call("getImages", url)
return [urljoin(url, i) for i in images]
def test_VM(self):
with self.subTest("create VM"):
vm = VM().create()
r = vm.run("'foo' + 'bar'")
vm.destroy()
self.assertEqual(r, "foobar")
with self.subTest("with statement"):
with VM() as vm:
r = vm.run("'foo' + 'bar'")
self.assertEqual(r, "foobar")
def turn(self, mat, strength, x, y):
ref = {"mat": copy_2D(mat), "x": x, "y": y}
try:
with VM() as vm:
turn_call = "turn({}, {}, {}, {}, {})".format(
" '{}' ".format(self.color), json.dumps(mat), strength,
x, y)
call_str = "{} {} {}".format(preload_code,
turn_code[self.color],
turn_call)
action = vm.run(call_str)
if type(action) == list:
return tuple(action)
except:
print("Error: {}".format(self.color))
def build_ctx(url):
"""Reuse javascript context"""
global ctx
js_url = urljoin(url, "/script/view.js")
js = grabhtml(js_url)
js = """
var imgEl = {
style: {},
name: ""
},
domainEl = {};
location = {
href: "",
hostname: ""
};
document = {
location: location,
getElementById: function(id){
if (id == "hdDomain") {
return domainEl;
}
if (/^img/.test(id)) {
return imgEl;
}
return {};
}
};
window = {
document: document,
eval: eval,
parseInt: parseInt,
String: String,
RegExp: RegExp
};
function getImages(url, name, hdDomain) {
location.href = url;
location.hostname = url.match(/:\/\/([^\/]+)/)[1];
imgEl.name = name;
domainEl.value = hdDomain;
window_onload();
return imgEl.src;
}
""" + js
ctx = VM(js).create()
def get_episodes(html, url):
html = html.replace("\n", "")
js = """
var output;
function getCookie() {}
var window = {
open: function(result){
output = result;
}
};
function get(url, catid) {
cview(url, catid);
return output;
}
var document = {
location: {
href: ""
}
};
""" + grabhtml(urljoin(url, "/js/comicview.js"))
s = []
matches = re.finditer(
"<a href='#' onclick=\"cview\('(.+?)',(\d+?)\);return "
"false;\" id=\"\w+?\" class=\"\w+?\">(.+?)</a>", html, re.M)
with VM(js) as vm:
for match in matches:
ep_url, catid, title = match.groups()
ep_url = vm.call("get", ep_url, int(catid))
# tag cleanup
title = title.strip()
title = re.sub("<script.+?</script>", "", title)
title = re.sub("<.+?>", "", title)
e = Episode(title, urljoin(url, ep_url))
s.append(e)
return s
def get_images(html, url):
s_files = re.search('sFiles="([^"]+)', html).group(1)
s_path = re.search('sPath="([^"]+)', html).group(1)
viewhtm = re.search(r'src="([^"]*?viewhtm\d*\.js[^"]*)', html)
viewhtm = grabhtml(urljoin(url, viewhtm.group(1)))
env = """
window = {
"eval": eval,
"parseInt": parseInt,
"String": String,
"RegExp": RegExp
};
location = {
"hostname": null
};
function setHostname(hostname) {
location.hostname = hostname;
}
"""
js = env + re.search(r'function isMobile\(\){.+?}(.+?)var cMod', viewhtm,
re.DOTALL).group(1)
with VM(js) as vm:
vm.call("setHostname", urlparse(url).hostname)
arr_files = vm.call("unsuan", s_files).split("|")
ds = re.search(r"src='([^']*?ds\.js[^']*)", html)
ds = grabhtml(urljoin(url, ds.group(1)))
global servers
servers = re.search('sDS = "([^"]+)', ds).group(1).split("^")
servers = [s.split("|")[1] for s in servers]
servers = cycle(servers)
server = next(servers)
return (server + s_path + f for f in arr_files)
def get_images(html, url):
# build js context
js = """
var window = global;
var cInfo;
var SMH = {
imgData: function(data) {
cInfo = data;
return {
preInit: function(){}
};
}
};
"""
configjs_url = re.search(r'src="(https?://[^"]+?/config_\w+?\.js)"',
html).group(1)
configjs = grabhtml(configjs_url, referer=url)
js += re.search(r'^(var CryptoJS|window\["\\x65\\x76\\x61\\x6c"\]).+',
configjs, re.MULTILINE).group()
js += re.search(
r'<script type="text/javascript">((eval|window\["\\x65\\x76\\x61\\x6c"\]).+?)</script',
html).group(1)
with VM(js) as vm:
files, path, params = vm.run("[cInfo.files, cInfo.path, cInfo.sl]")
# find server
# "http://c.3qfm.com/scripts/core_5C348B32A78647FF4208EACA42FC5F84.js"
# getpath()
corejs_url = re.search(r'src="(https?://[^"]+?/core_\w+?\.js)"',
html).group(1)
corejs = grabhtml(corejs_url, referer=url)
# cache server list
servs = re.search(r"var servs=(.+?),pfuncs=", corejs).group(1)
servs = eval(servs)
servs = [host["h"] for category in servs for host in category["hosts"]]
global servers
servers = cycle(servs)
host = next(servers)
utils = re.search(r"SMH\.(utils=.+?),SMH\.imgData=", corejs).group(1)
js = """
var location = {
protocol: "http:"
};
""" + utils + """;
function getFiles(path, files, host) {
// lets try if it will be faster in javascript
return files.map(function(file){
return utils.getPath(host, path + file);
});
}
"""
with VM(js) as vm:
images = vm.call("getFiles", path, files, host)
if config.getboolean("nowebp"):
images = map(lambda i: i[:-5] if i.endswith(".webp") else i, images)
params = urlencode(params)
images = ["{file}?{params}".format(file=i, params=params) for i in images]
return images
