def handle_web_links(self):
self.log_debug("Search for Web links ")
pack_links = []
pattern = r'<form action="http://linkcrypt.ws/out.html"[^>]*?>.*?<input[^>]*?value="(.+?)"[^>]*?name="file"'
ids = re.findall(pattern, self.data, re.I | re.S)
self.log_debug(f"Decrypting {len(ids)} Web links")
for idx, weblink_id in enumerate(ids):
try:
res = self.load(
"http://linkcrypt.ws/out.html", post={"file": weblink_id}
)
indexs = res.find("href=doNotTrack('") + 17
indexe = res.find("'", indexs)
link2 = res[indexs:indexe]
link2 = html_unescape(link2)
pack_links.append(link2)
except Exception as detail:
self.log_debug(
"Error decrypting Web link {}, {}".format(weblink_id, detail)
)
return pack_links
def handle_captcha(self, inputs):
m = search_pattern(self.CAPTCHA_PATTERN, self.data)
if m is not None:
captcha_url = urljoin(self.pyfile.url, m.group(1))
inputs["code"] = self.captcha.decrypt(captcha_url)
return
m = search_pattern(self.CAPTCHA_BLOCK_PATTERN, self.data, flags=re.S)
if m is not None:
captcha_div = m.group(1)
numerals = re.findall(
r"<span.*?padding-left\s*:\s*(\d+).*?>(\d)</span>",
html_unescape(captcha_div),
)
self.log_debug(captcha_div)
code = inputs["code"] = "".join(
a[1] for a in sorted(numerals, key=operator.itemgetter(0)))
self.log_debug(f"Captcha code: {code}", numerals)
return
recaptcha = ReCaptcha(self.pyfile)
try:
captcha_key = search_pattern(self.RECAPTCHA_PATTERN,
self.data).group(1)
except (AttributeError, IndexError):
captcha_key = recaptcha.detect_key()
else:
self.log_debug(f"ReCaptcha key: {captcha_key}")
if captcha_key:
self.captcha = recaptcha
inputs["g-recaptcha-response"], _ = recaptcha.challenge(
captcha_key)
return
solvemedia = SolveMedia(self.pyfile)
try:
captcha_key = search_pattern(self.SOLVEMEDIA_PATTERN,
self.data).group(1)
except (AttributeError, IndexError):
captcha_key = solvemedia.detect_key()
else:
self.log_debug(f"SolveMedia key: {captcha_key}")
if captcha_key:
self.captcha = solvemedia
(
inputs["adcopy_response"],
inputs["adcopy_challenge"],
) = solvemedia.challenge(captcha_key)
def get_file_name(self):
file_name_pattern = r"<h1 class=\'globalHd\'>(.*)</h1>"
return html_unescape(
re.search(file_name_pattern, self.data).group(1).replace("/", "") + ".flv"
)
def upload(
self,
path,
url,
get={},
ref=True,
cookies=True,
just_header=False,
decode=True,
redirect=True,
req=None,
):
# TODO: This should really go to HTTPRequest.py
"""
Uploads a file at url and returns response content.
:param url:
:param get:
:param ref:
:param cookies:
:param just_header: If True only the header will be retrieved and returned as dict
:param decode: Wether to decode the output according to http header, should be True in most cases
:return: Response content
"""
if self.pyload.debug:
self.log_debug(
"UPLOAD URL " + url,
*[
"{}={}".format(key, value)
for key, value in locals().items()
if key not in ("self", "url", "_[1]")
],
)
with open(path, mode="rb") as fp:
url = fixurl(url, unquote=True) #: Recheck in 0.6.x
if req is False:
req = get_request()
req.set_option("timeout", 60) # TODO: Remove in 0.6.x
elif not req:
req = self.req
if isinstance(cookies, list):
set_cookies(req.cj, cookies)
http_req = self.req.http if hasattr(self.req, "http") else self.req
if not redirect:
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.FOLLOWLOCATION, 0)
elif isinstance(redirect, int):
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.MAXREDIRS, redirect)
if isinstance(ref, str):
http_req.last_url = ref
http_req.set_request_context(url, get, {}, bool(ref),
bool(cookies), False)
http_req.header = ""
http_req.c.setopt(pycurl.HTTPHEADER, http_req.headers)
http_req.c.setopt(pycurl.UPLOAD, 1)
http_req.c.setopt(pycurl.READFUNCTION, fp.read)
http_req.c.setopt(pycurl.INFILESIZE, os.path.getsize(path))
if just_header:
http_req.c.setopt(pycurl.FOLLOWLOCATION, 0)
http_req.c.setopt(pycurl.NOBODY, 1)
http_req.c.perform()
html = http_req.header
http_req.c.setopt(pycurl.FOLLOWLOCATION, 1)
http_req.c.setopt(pycurl.NOBODY, 0)
else:
http_req.c.perform()
html = http_req.get_response()
http_req.c.setopt(pycurl.UPLOAD, 0)
http_req.c.setopt(pycurl.INFILESIZE, 0)
http_req.c.setopt(pycurl.POSTFIELDS, "")
http_req.last_effective_url = http_req.c.getinfo(
pycurl.EFFECTIVE_URL)
http_req.add_cookies()
try:
http_req.code = http_req.verify_header()
finally:
http_req.rep.close()
http_req.rep = None
if decode is True:
html = http_req.decode_response(html)
if not redirect:
http_req.c.setopt(pycurl.FOLLOWLOCATION, 1)
elif isinstance(redirect, int):
maxredirs = (int(
self.pyload.api.get_config_value("UserAgentSwitcher",
"maxredirs", "plugin"))
or 5) # TODO: Remove `int` in 0.6.x
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.MAXREDIRS, maxredirs)
if decode:
html = html_unescape(html)
# TODO: Move to network in 0.6.x
html = _decode(html, decode)
self.last_html = html
if self.pyload.debug:
self.dump_html()
# TODO: Move to network in 0.6.x
header = {"code": req.code, "url": req.last_effective_url}
# NOTE: req can be a HTTPRequest or a Browser object
header.update(parse_html_header(http_req.header))
self.last_header = header
if just_header:
return header
else:
return html
def load(
self,
url,
get={},
post={},
ref=True,
cookies=True,
just_header=False,
decode=True,
multipart=False,
redirect=True,
req=None,
):
"""
Load content at url and returns it.
:param url:
:param get:
:param post:
:param ref:
:param cookies:
:param just_header: If True only the header will be retrieved and returned as dict
:param decode: Wether to decode the output according to http header, should be True in most cases
:return: Loaded content
"""
if self.pyload.debug:
self.log_debug(
"LOAD URL " + url,
*[
"{}={}".format(key, value)
for key, value in locals().items()
if key not in ("self", "url", "_[1]")
],
)
url = fixurl(url, unquote=True) #: Recheck in 0.6.x
if req is False:
req = get_request()
req.set_option("timeout", 60) # TODO: Remove in 0.6.x
elif not req:
req = self.req
# TODO: Move to network in 0.6.x
if isinstance(cookies, list):
set_cookies(req.cj, cookies)
http_req = self.req.http if hasattr(self.req, "http") else self.req
# TODO: Move to network in 0.6.x
if not redirect:
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.FOLLOWLOCATION, 0)
elif isinstance(redirect, int):
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.MAXREDIRS, redirect)
# TODO: Move to network in 0.6.x
if isinstance(ref, str):
req.last_url = ref
html = req.load(
url,
get,
post,
bool(ref),
bool(cookies),
just_header,
multipart,
decode is True,
) # TODO: Fix network multipart in 0.6.x
# TODO: Move to network in 0.6.x
if not redirect:
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.FOLLOWLOCATION, 1)
elif isinstance(redirect, int):
maxredirs = (int(
self.pyload.api.get_config_value("UserAgentSwitcher",
"maxredirs", "plugin"))
or 5) # TODO: Remove `int` in 0.6.x
# NOTE: req can be a HTTPRequest or a Browser object
http_req.c.setopt(pycurl.MAXREDIRS, maxredirs)
# TODO: Move to network in 0.6.x
if decode:
html = html_unescape(html)
# TODO: Move to network in 0.6.x
html = _decode(html, decode)
self.last_html = html
if self.pyload.debug:
self.dump_html()
# TODO: Move to network in 0.6.x
header = {"code": req.code, "url": req.last_effective_url}
# NOTE: req can be a HTTPRequest or a Browser object
header.update(parse_html_header(http_req.header))
self.last_header = header
if just_header:
return header
else:
return html