Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixed cf new challenge solution #373

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fixed cf new challenge solution #373

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7ee8825
Fixed kissanime-cf new challenge
Sraq-Zit Jun 20, 2020
3b924a7
Version change
Sraq-Zit Jun 24, 2020
9546707
Changed regexp for js to match that of cloudflare
Sraq-Zit Jul 5, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
25 changes: 14 additions & 11 deletions cfscrape/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@

from .user_agents import USER_AGENTS

__version__ = "2.1.1"
__version__ = "2.1.1-alpha"

DEFAULT_USER_AGENT = random.choice(USER_AGENTS)

Expand Down Expand Up @@ -173,7 +173,7 @@ def solve_cf_challenge(self, resp, **original_kwargs):
for param in re.search(r'action=\"(.*?)\"', challenge_form, flags=re.S).group(1).split('?')[1].split('&'):
cloudflare_kwargs["params"].update({param.split('=')[0]:param.split('=')[1]})

for input_ in re.findall(r'\<input.*?(?:\/>|\<\/input\>)', challenge_form, flags=re.S):
for input_ in re.findall(r'[^-] \<input.*?(?:\/>|\<\/input\>)', challenge_form, flags=re.S):
if re.search(r'name=\"(.*?)\"',input_, flags=re.S).group(1) != 'jschl_answer':
if method == 'POST':
cloudflare_kwargs["data"].update({re.search(r'name=\"(.*?)\"',input_, flags=re.S).group(1):
Expand Down Expand Up @@ -246,22 +246,23 @@ def solve_cf_challenge(self, resp, **original_kwargs):

def solve_challenge(self, body, domain):
try:
all_scripts = re.findall(r'\<script type\=\"text\/javascript\"\>\n(.*?)\<\/script\>',body, flags=re.S)
javascript = next(filter(lambda w: "jschl-answer" in w,all_scripts)) #find the script tag which would have obfuscated js
javascript = re.search(r'\<script type\=\"text\/javascript\"\>\n(.*?)\<\/script\>',body, flags=re.S).group(1) # find javascript

challenge, ms = re.search(
r"setTimeout\(function\(\){\s*(var "
r"s,t,o,p,b,r,e,a,k,i,n,g,f.+?\r?\n[\s\S]+?a\.value\s*=.+?)\r?\n"
r"(?:[^{<>]*},\s*(\d{4,}))?",
r"s,t,o,p, b,r,e,a,k,i,n,g,f.+?\r?\n[\s\S]+?a\.value\s*=.+?)\r?\n"
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR only works for me if I add ,cpo into this line, like:
r"s,t,o,p, b,r,e,a,k,i,n,g,cpo,f.+?\r?\n[\s\S]+?a\.value\s*=.+?)\r?\n"

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR only works for me if I add ,cpo into this line, like:
r"s,t,o,p, b,r,e,a,k,i,n,g,cpo,f.+?\r?\n[\s\S]+?a\.value\s*=.+?)\r?\n"

It still don't work with me . Can you test this site ?
https://tubortaxdeal.com
https://www.aichoai.com

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

weird, the JS on those 2 sites looks really different, like it's not even minified or something. I wonder if they're using a different version of the cloudflare protection stuff?

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR only works for me if I add ,cpo into this line, like:
r"s,t,o,p, b,r,e,a,k,i,n,g,cpo,f.+?\r?\n[\s\S]+?a\.value\s*=.+?)\r?\n"

It was added just recently for the websites I tested.
Thanks !

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR only works for me if I add ,cpo into this line, like:
r"s,t,o,p, b,r,e,a,k,i,n,g,cpo,f.+?\r?\n[\s\S]+?a\.value\s*=.+?)\r?\n"

It was added just recently for the websites I tested.
Thanks !

don't work for https://localbitcoins.net

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also doesn't work for http://www.mangago.me/read-manga/hataraku_maousama/

r"(?:[^{<>]*},\s*(\d{4,}))",
javascript, flags=re.S
).groups()

# The challenge requires `document.getElementById` to get this content.
# Future proofing would require escaping newlines and double quotes
innerHTML = ''
innerHTML = {}
for i in javascript.split(';'):
if i.strip().split('=')[0].strip() == 'k': # from what i found out from pld example K var in
k = i.strip().split('=')[1].strip(' \'') # javafunction is for innerHTML this code to find it
innerHTML = re.search(r'\<div.*?id\=\"'+k+r'\".*?\>(.*?)\<\/div\>',body).group(1) #find innerHTML
k = re.finditer(r'\<div.*?id\=\"('+k+r'\d+)\".*?\>(.*?)\<\/div\>',body) #find innerHTML
innerHTML = {x.group(1): x.group(2) for x in k}

# Prefix the challenge with a fake document object.
# Interpolate the domain, div contents, and JS challenge.
Expand All @@ -271,8 +272,9 @@ def solve_challenge(self, body, domain):
createElement: function () {
return { firstChild: { href: "http://%s/" } }
},
getElementById: function () {
return {"innerHTML": "%s"};
getElementById: function (id) {
var data = %s;
return {"innerHTML": data[id]};
}
};

Expand All @@ -282,6 +284,7 @@ def solve_challenge(self, body, domain):
innerHTML,
challenge,
)
challenge = re.sub(r'setInterval\(.+?\d\),', '', challenge)
# Encode the challenge for security while preserving quotes and spacing.
challenge = b64encode(challenge.encode("utf-8")).decode("ascii")
# Use the provided delay, parsed delay, or default to 8 secs
Expand Down Expand Up @@ -336,7 +339,7 @@ def solve_challenge(self, body, domain):
except Exception:
logging.error("Error executing Cloudflare IUAM Javascript. %s" % BUG_REPORT)
raise

try:
float(result)
except Exception:
Expand Down