def get_images(html, url):
key = search(r'id="dm5_key".+?<script[^>]+?>\s*eval(.+?)</script>', html,
DOTALL)
if key:
key = eval(key.group(1)).split(";")[1]
key = search(r"=(.+)$", key).group(1)
key = eval(key)
else:
key = ""
count = search("DM5_IMAGE_COUNT=(\d+);", html).group(1)
cid = search("DM5_CID=(\d+);", html).group(1)
s = []
for p in range(1, int(count) + 1):
fun_url = urljoin(
url,
"chapterfun.ashx?cid={}&page={}&language=1&key={}>k=6".format(
cid, p, key))
s.append(create_grabber(fun_url, url))
global first_grabber
first_grabber = s[0]
return s
def test_VMError(self):
with self.assertRaisesRegex(VMError, "foo"):
eval("throw new Error('foo')")
# doesn't inherit Error
with self.assertRaisesRegex(VMError, "foo"):
eval("throw 'foo'")
def test_eval(self):
with self.subTest("one line eval"):
r = eval("'foo' + 'bar'")
self.assertEqual(r, "foobar")
with self.subTest("multiline"):
r = eval("""
var foo = x => x + 'bar';
foo('foo');
""")
self.assertEqual(r, "foobar")
def get_images_eval(html, url):
# Set base url
base = "http://images.dmzj.com/"
# Get urls
html = html.replace("\n", "")
s = re.search(r"page = '';\s*(.+?);\s*var g_comic_name", html).group(1)
pages = eval(s + "; pages")
pages = eval(pages)
# thumbs.db?!
# http://manhua.dmzj.com/zhuoyandexiana/3488-20.shtml
return [base + page for page in pages if page and not page.lower().endswith("thumbs.db")]
def get_images(html, url):
hash = re.search("/artwork/([^/]+)", url).group(1)
pattern = "cache\.put\('/projects/{hash}\.json', ('.+?')\);$".format(
hash=hash)
data_json = eval(re.search(pattern, html, re.M).group(1))
data = json.loads(data_json)
return [a["image_url"] for a in data["assets"]]
def get_images(html, url):
if html[0] == '"':
# wtf
html = json.loads(html)
# breakpoint()
key = re.search(r'var KEY = "([^"]+)', html).group(1)
cartoon_id = re.search(r'var CARTOON_ID = "([^"]+)', html).group(1)
chapter_id = re.search(r'var CHAPTER_ID = "([^"]+)', html).group(1)
page = re.search(r'var PAGE = "([^"]+)', html).group(1)
total_page = re.search(r'var TOTAL_PAGE = "([^"]+)', html).group(1)
if int(page) < int(total_page):
next_page_cache[url] = urljoin(
url,
re.search('href="([^"]+)">下一頁', html).group(1))
code = grabhtml(urljoin(url, "/comicseries/getpictrue.html"),
method="POST",
data={
"key": key,
"cartoon_id": cartoon_id,
"chapter_id": chapter_id,
"page": page
},
header={"X-Requested-With": "XMLHttpRequest"})
# breakpoint()
data = eval(code)
return data["current"]
def get_images(html, url):
data = re.search("var DATA\s*=\s*'[^']+'", html).group()
nonce = re.search("window\.nonce = (.+)", html).group(1)
nonce2 = re.search("window\[.+?=(.+)", html)
nonce2 = nonce2.group(1) if nonce2 else None
view_js = re.search('src="([^"]+?page\.chapter\.view[^"]+?\.js[^"]*)',
html).group(1)
view_js = grabhtml(urljoin(url, view_js))
view_js = re.search("(eval\(.+?)\}\(\)", view_js, re.DOTALL).group(1)
code = "\n".join([
data, """
function createDummy() {
return new Proxy(() => true, {
get: () => createDummy()
});
}
const window = document = createDummy();
""", "const nonce = {};".format(nonce2 or nonce), "const W = {DATA, nonce};",
view_js
])
data = node_vm2.eval(code)
return [p["url"] for p in data["picture"]]
def get_init_data(html):
js = re.search("(var globalInitData =.+?)</script>", html, re.DOTALL).group(1)
return eval("""
Object.freeze = n => n;
""" + js + """
globalInitData;
""")
def get_images_eval(html, url):
# Set base url
base = "http://images.dmzj.com/"
# Get urls
html = html.replace("\n", "")
s = re.search(r"page = '';\s*(.+?);\s*var g_comic_name", html).group(1)
pages = eval(s + "; pages")
pages = eval(pages)
# thumbs.db?!
# http://manhua.dmzj.com/zhuoyandexiana/3488-20.shtml
return [
base + page for page in pages
if page and not page.lower().endswith("thumbs.db")
]
def get_images(html, url):
pages_js = re.search(r'page_url":(\[[^\]]+\])', html).group(1)
pages = eval(pages_js)
# thumbs.db?!
# http://manhua.dmzj.com/zhuoyandexiana/3488-20.shtml
return [page for page in pages if page and not page.lower().endswith("thumbs.db")]
def grabber():
text = grabhtml(fun, referer=url)
d = eval(text + """;
((typeof (hd_c) != 'undefined' && hd_c.length > 0 &&
typeof (isrevtt) != 'undefined') ? hd_c : d)
""")
return d[0]
def get_images(html, url):
key = search(r'id="dm5_key".+?<script[^>]+?>\s*eval(.+?)</script>', html,
DOTALL)
if key:
key = eval(key.group(1)).split(";")[1]
key = search(r"=(.+)$", key).group(1)
key = eval(key)
else:
key = ""
count = int(search("DM5_IMAGE_COUNT=(\d+);", html).group(1))
cid = search("DM5_CID=(\d+);", html).group(1)
mid = search("DM5_MID=(\d+);", html).group(1)
dt = search('DM5_VIEWSIGN_DT="([^"]+)', html).group(1)
sign = search('DM5_VIEWSIGN="([^"]+)', html).group(1)
pages = {}
def grab_page(page):
params = {
"cid": cid,
"page": page + 1,
"language": 1,
"key": key,
"gtk": 6,
"_cid": cid,
"_mid": mid,
"_dt": dt,
"_sign": sign
}
fun_url = urljoin(url, "chapterfun.ashx")
text = grabhtml(fun_url, referer=url, params=params)
d = eval(text)
for i, image in enumerate(d):
pages[i + page] = image
def create_page_getter(page):
def getter():
if page not in pages:
grab_page(page)
return pages[page]
return getter
return [create_page_getter(p) for p in range(count)]
def get_init_data(html):
js = re.search("(var globalInitData =.+?)</script>", html,
re.DOTALL).group(1)
return eval("""
Object.freeze = n => n;
""" + js + """
globalInitData;
""")
def get_images(html, url):
key = re.search('root\.YUI_config\.flickr\.api\.site_key = "([^"]+)',
html).group(1)
model = re.search(r"Y\.ClientApp\.init\(([\s\S]+?)\)\s*\.then",
html).group(1)
data = eval(("auth = null, reqId = null, model = {model}, "
"model.modelExport['photo-models'][0]").format(model=model))
return query_video(data["id"], data["secret"], key)
def get_images(html, url):
key = re.search('root\.YUI_config\.flickr\.api\.site_key = "([^"]+)', html).group(1)
model = re.search(r"Y\.ClientApp\.init\(([\s\S]+?)\)\s*\.then", html).group(1)
data = eval((
"auth = null, reqId = null, model = {model}, "
"model.modelExport['photo-models'][0]"
).format(model=model))
return query_video(data["id"], data["secret"], key)
def get_images(html, url):
js = re.search(r"(window\.DATA = [\s\S]+?)</script>", html).group(1)
imgs = eval("""
const window = {};
""" + js + """
window.PG_CONFIG.images.map(i => i.url.slice(0, i.url.length - window.DATA.seedLength));
""")
return imgs
def get_state(html):
js = re.search(r"(window\.__INITIAL_STATE__[\s\S]+?)</script>",
html).group(1)
return eval("""
const window = {};
""" + js + """
; window.__INITIAL_STATE__
""")
def get_images(html, url):
key = re.search(r'id="dm5_key".+?<script[^>]+?>\s*eval(.+?)</script>', html, re.DOTALL)
if key:
key = eval(key.group(1)).split(";")[1]
key = re.search(r"=(.+)$", key).group(1)
key = eval(key)
else:
key = ""
count = int(re.search("DM5_IMAGE_COUNT=(\d+);", html).group(1))
cid = re.search("DM5_CID=(\d+);", html).group(1)
mid = re.search("DM5_MID=(\d+);", html).group(1)
dt = re.search('DM5_VIEWSIGN_DT="([^"]+)', html).group(1)
sign = re.search('DM5_VIEWSIGN="([^"]+)', html).group(1)
pages = {}
def grab_page(page):
params = {
"cid": cid,
"page": page + 1,
"language": 1,
"key": key,
"gtk": 6,
"_cid": cid,
"_mid": mid,
"_dt": dt,
"_sign": sign
}
fun_url = urljoin(url, "chapterfun.ashx")
text = grabhtml(fun_url, referer=url, params=params)
d = eval(text)
for i, image in enumerate(d):
pages[i + page] = image
def create_page_getter(page):
def getter():
if page not in pages:
grab_page(page)
return pages[page]
return getter
return [create_page_getter(p) for p in range(count)]
def get_images(html, url):
pages_js = re.search(r'page_url":(\[[^\]]+\])', html).group(1)
pages = eval(pages_js)
# thumbs.db?!
# http://manhua.dmzj.com/zhuoyandexiana/3488-20.shtml
return [
page for page in pages
if page and not page.lower().endswith("thumbs.db")
]
def get_images(html, url):
scripts.fetch(
html, url,
["crypto-js\.js", "decrypt\d+\.js", "config\.js", "common\.js"])
pre_js = re.search("(var chapterImages.+?)</script>", html,
re.DOTALL).group(1)
main_js = re.search("decrypt\d+\(.+", html).group()
images = eval("""
(function () {
function atob(data) {
return Buffer.from(data, "base64").toString("binary");
}
function createLocalStorage() {
const storage = {};
return {setItem, getItem, removeItem};
function setItem(key, value) {
storage[key] = value;
}
function getItem(key) {
return storage[key];
}
function removeItem(key) {
delete storage[key];
}
}
const exports = undefined;
const toastr = {options: {}};
const top = {
location: {pathname: ""},
localStorage: createLocalStorage()
};
const jQuery = Object.assign(() => {}, {
cookie: () => false,
event: {trigger() {}}
});
const $ = jQuery;
const window = top;
const SinTheme = {
initChapter() {},
getPage() {}
};
""" + pre_js + str(scripts) + main_js + """
const s = [];
for (let i = 0; i < chapterImages.length; i++) {
s.push(SinMH.getChapterImage(i + 1));
}
return s;
}).call(global)
""")
return images
def get_images(html, url):
match = re.search("/artwork/([^/]+)", url)
if match:
hash = match.group(1)
pattern = "cache\.put\('/projects/{hash}\.json', ('.+?')\);$".format(hash=hash)
data_json = eval(re.search(pattern, html, re.M).group(1))
elif re.search("/projects/(\w+)\.json", url):
data_json = html
else:
raise Exception("Unknown page {}".format(url))
data = json.loads(data_json)
return [a["image_url"] for a in data["assets"]]
def get_images(html, url):
# Set base url
base = "http://images.dmzj.com/"
# Get urls
s = re.search(r"page = '';\s+([^\n]+)", html).group(1)
pages = eval(s + "; pages")
pages = re.search('"page_url":"([^"]+)', pages).group(1)
pages = re.split("\r?\n", pages)
# thumbs.db?!
# http://manhua.dmzj.com/zhuoyandexiana/3488-20.shtml
return [base + page for page in pages if page and not page.lower().endswith("thumbs.db")]
def get_images(html, url):
match = re.search("/artwork/([^/]+)", url)
if match:
hash = match.group(1)
pattern = "cache\.put\('/projects/{hash}\.json', ('.+?')\);$".format(
hash=hash)
data_json = eval(re.search(pattern, html, re.M).group(1))
elif re.search("/projects/(\w+)\.json", url):
data_json = html
else:
raise Exception("Unknown page {}".format(url))
data = json.loads(data_json)
return [a["image_url"] for a in data["assets"]]
def get_images(html, url):
js = re.search('(var siteName.+?)</script>', html, re.DOTALL).group(1)
# http://www.gufengmh.com/js/config.js
config = grabhtml(urljoin(url, "/js/config.js"))
return eval("""
const toastr = {
options: {}
};
""" + config + js + """
const domain = SinConf.resHost[0].domain[0];
chapterImages.map(i => `${domain}/${chapterPath}${i}`);
""")
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_images(html, url):
data = re.search("var DATA\s*=\s*'[^']+'", html).group()
nonce = re.search("window\.nonce = (.+)", html).group(1)
nonce2 = re.search("window\[.+?=(.+)", html)
nonce2 = nonce2.group(1) if nonce2 else None
view_js = re.search('src="([^"]+?page\.chapter\.view[^"]+?\.js[^"]+)', html).group(1)
view_js = grabhtml(urljoin(url, view_js))
view_js = re.search("(eval\(.+?)\}\(\)", view_js, re.DOTALL).group(1)
code = data + ";var nonce = " + (nonce2 or nonce) + ";var W = {DATA, nonce};" + view_js + ";_v"
data = node_vm2.eval(code)
return [p["url"] for p in data["picture"]]
def get_images(html, url):
key = re.search('root\.YUI_config\.flickr\.api\.site_key = "([^"]+)',
html).group(1)
model = re.search(r"Y\.ClientApp\.init\(([\s\S]+?)\)\s*\.then",
html).group(1)
js = """
const auth = null, reqId = null;
const model = """ + model + """;
model.modelExport.main["photo-models"][0]
"""
data = eval(js)
if data.get("mediaType") == "video":
return query_video(data["id"], data["secret"], key)
max_size = max(data["sizes"].values(), key=lambda s: s.get("width", 0))
return urljoin(url, max_size["url"])
def get_images(html, url):
js_url = re.search(r'src="([^"]+base64\.js)"', html).group(1)
js_content = grabhtml(urljoin(url, js_url))
data = re.search('(var chapterTree=.+?)</script>', html, re.DOTALL).group(1)
match = re.search(r'window\["\\x65\\x76\\x61\\x6c"\](.+?)</script>', html, re.DOTALL)
data2 = match.group(1) if match else ""
imgs = eval("""
const document = {{}};
{};
{};
eval({});
getUrlpics().map(getrealurl);
""".format(js_content, data, data2))
return imgs
def get_images(html, url):
# Set base url
base = "http://images.dmzj.com/"
# Get urls
s = re.search(r"page = '';\s+([^\n]+)", html).group(1)
pages = eval(s + "; pages")
pages = re.search('"page_url":"([^"]+)', pages).group(1)
pages = re.split("\r?\n", pages)
# thumbs.db?!
# http://manhua.dmzj.com/zhuoyandexiana/3488-20.shtml
return [
base + page for page in pages
if page and not page.lower().endswith("thumbs.db")
]
def eval_script(scripts, name):
name = name.replace('http://', '').replace('.', '_').replace('/', '_')
new = ''
for script in scripts:
for line in script.replace('//-->', '').split('\n'):
if line != '\n':
new += line
if 'document.write(' in new:
js_target = new.replace('document.write(', '').replace('));', ');')
a = eval(js_target)
pa = './Export/%s/%s.dmp' % (datetime.date.today(), name)
with open(pa, 'a+') as f:
f.write('\n#Auto generated\n#' + str(datetime.date.today()) + '\n\n' + a)
print('[+] Saved under ./Export/%s/%s' % (datetime.date.today(), name))
else:
print('[-] Unable to process this script. Update me.')
return 'None'
def get_images(html, url):
global global_js
js = re.search("(var ret_classurl.+?)</script>", html, re.DOTALL).group(1)
if not global_js:
global_js_url = re.search('src="([^"]+global\.js)"', html).group(1)
global_js = grabhtml(urljoin(url, global_js_url))
global_js = re.search("(var WebimgServer.+?)window\.onerror",
global_js, re.DOTALL).group(1)
imgs, server = eval("""
function request() {
return "";
}
""" + js + global_js + """;
[photosr.slice(1), WebimgServerURL[0]]
""")
return [urljoin(server, img) for img in imgs]
def get_episodes(html, url):
data_js = re.search("initIntroData(.+?);", html, re.DOTALL).group(1)
data = eval(data_js)
ep_data = []
for category in data:
ep_data += category["data"]
ep_data = sorted(ep_data, key=lambda data: data["chapter_order"])
episodes = []
for data in ep_data:
ep_url = "/view/{}/{}.html".format(data["comic_id"], data["id"])
title = data["title"] + data["chapter_name"]
episodes.append(Episode(title, urljoin(url, ep_url)))
return episodes
def grab_page(page):
params = {
"cid": cid,
"page": page + 1,
"language": 1,
"key": key,
"gtk": 6,
"_cid": cid,
"_mid": mid,
"_dt": dt,
"_sign": sign
}
fun_url = urljoin(url, "chapterfun.ashx")
text = grabhtml(fun_url, referer=url, params=params)
d = eval(text)
for i, image in enumerate(d):
pages[i + page] = image
def get_episodes(html, url):
data_js = re.search("initIntroData(.+?);", html, re.DOTALL).group(1)
data = eval(data_js)
ep_data = []
for category in data:
ep_data += category["data"]
ep_data = sorted(ep_data, key=lambda data: data["chapter_order"])
episodes = []
for data in ep_data:
ep_url = "/view/{}/{}.html".format(data["comic_id"], data["id"])
title = data["title"] + data["chapter_name"]
episodes.append(Episode(title, urljoin(url, ep_url)))
return episodes
def grab_page(page):
params = {
"cid": cid,
"page": page + 1,
"language": 1,
"key": key,
"gtk": 6,
"_cid": cid,
"_mid": mid,
"_dt": dt,
"_sign": sign
}
fun_url = urljoin(url, "chapterfun.ashx")
text = grabhtml(fun_url, referer=url, params=params)
d = eval(text)
for i, image in enumerate(d):
pages[i + page] = image
def get_images(html, url):
script = re.search(r'<script>\s*(var qTcms_Cur[\s\S]+?)</script>',
html).group(1)
show_js_src = re.search(r'src="([^"]+?show\.\d+\.js[^"]*)', html).group(1)
show_js = grabhtml(urljoin(url, show_js_src))
real_pic_fn = re.search(
r'(function f_qTcms_Pic_curUrl_realpic[\s\S]+?)function',
show_js).group(1)
code = """
{script}
{real_pic_fn}
Buffer.from(qTcms_S_m_murl_e, "base64")
.toString()
.split("$qingtiandy$")
.map(f_qTcms_Pic_curUrl_realpic);
""".format(script=script, real_pic_fn=real_pic_fn)
return [urljoin(url, i) for i in eval(code)]
def get_images(html, url):
js_url = re.search(r'src="([^"]+base64\.js)"', html).group(1)
js_content = grabhtml(urljoin(url, js_url))
data = re.search('(var chapterTree=.+?)</script>', html,
re.DOTALL).group(1)
match = re.search(r'window\["\\x65\\x76\\x61\\x6c"\](.+?)</script>', html,
re.DOTALL)
data2 = match.group(1) if match else ""
imgs = eval("""
const document = {{}};
{};
{};
eval({});
getUrlpics().map(getrealurl);
""".format(js_content, data, data2))
return imgs
def get_images(html, url):
script = re.search(r'<script>\s*(var qTcms_Cur[\s\S]+?)</script>', html).group(1)
show_js_src = re.search(r'src="([^"]+?show\.\d+\.js[^"]*)', html).group(1)
show_js = grabhtml(urljoin(url, show_js_src))
real_pic_fn = re.search(r'(function f_qTcms_Pic_curUrl_realpic[\s\S]+?)function', show_js).group(1)
code = """
{script}
{real_pic_fn}
function base64_decode(data) {{
return Buffer.from(data, "base64").toString();
}}
// m.wuyouhui.net/template/wap1/css/d7s/js/show.20170501.js?20190506201115
Buffer.from(qTcms_S_m_murl_e, "base64")
.toString()
.split("$qingtiandy$")
.filter(u => !/^(--|\+)/.test(u))
.map(f_qTcms_Pic_curUrl_realpic);
""".format(script=script, real_pic_fn=real_pic_fn)
return [urljoin(url, i) for i in eval(code)]
def get_images(html, url):
if "pixiv.user.loggedIn = true" not in html:
raise PauseDownloadError("you didn't login!")
# ugoku
rs = re.search(r"pixiv\.context\.ugokuIllustFullscreenData\s+= ([^;]+)",
html)
if rs:
json = rs.group(1)
o = eval("(" + json + ")")
cache["frames"] = o["frames"]
return [o["src"]]
# new image layout (2014/12/14)
rs = re.search(r'class="big" data-src="([^"]+)"', html)
if rs:
return [rs.group(1)]
rs = re.search(r'data-src="([^"]+)" class="original-image"', html)
if rs:
return [rs.group(1)]
# old image layout
imgs = get_images_old(html, url)
if imgs:
return imgs
# restricted
rs = re.search('<section class="restricted-content">', html)
if rs:
raise SkipEpisodeError
# error page
rs = re.search('class="error"', html)
if rs:
raise SkipEpisodeError
# id doesn't exist
rs = re.search("pixiv.context.illustId", html)
if not rs:
raise SkipEpisodeError
def get_images_old(html, url):
match = re.search(r'"works_display"><a (?:class="[^"]*" )?href="([^"]+)"',
html)
if not match:
return
inner_url = match.group(1)
html = grabhtml(urljoin(url, inner_url), referer=url)
if "mode=big" in inner_url:
# single image
img = re.search(r'src="([^"]+)"', html).group(1)
return [img]
if "mode=manga" in inner_url:
# multiple image
imgs = []
def create_grabber(url):
def grabber():
html = grabhtml(url)
return re.search(r'img src="([^"]+)"', html).group(1)
return grabber
for match in re.finditer(
r'a href="(/member_illust\.php\?mode=manga_big[^"]+)"', html):
imgs.append(create_grabber(urljoin(url, match.group(1))))
# New manga reader (2015/3/18)
# http://www.pixiv.net/member_illust.php?mode=manga&illust_id=19254298
if not imgs:
for match in re.finditer(r'originalImages\[\d+\] = ("[^"]+")',
html):
img = eval(match.group(1))
imgs.append(img)
return imgs
def get_images(html, url):
check_login(html)
init_data = re.search(r"(var globalInitData[\s\S]+?)</script>",
html).group(1)
init_data = eval("""
Object.freeze = null;
""" + init_data + """
globalInitData;
""")
illust_id = re.search("illust_id=(\d+)", url).group(1)
illust = init_data["preload"]["illust"][illust_id]
if illust["illustType"] != 2: # normal images
first_img = illust["urls"]["original"]
return [get_nth_img(first_img, i) for i in range(illust["pageCount"])]
# https://www.pixiv.net/member_illust.php?mode=medium&illust_id=44298524
ugoira_meta = "https://www.pixiv.net/ajax/illust/{}/ugoira_meta".format(
illust_id)
ugoira_meta = json.loads(grabhtml(ugoira_meta))
cache["frames"] = ugoira_meta["body"]["frames"]
return ugoira_meta["body"]["originalSrc"]
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, md5, cid = vm.run("[cInfo.files, cInfo.path, cInfo.sl.md5, cInfo.cid]")
# 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({
"cid": cid,
"md5": md5
})
images = ["{file}?{params}".format(file=i, params=params) for i in images]
return images
def get_images(html, url): js = re.search(r"(eval\([\s\S]+?)</script", html).group(1) return eval(js + ";newImgs")
