def get_challenge(self, code):
data = {}
for find in re.findall(
r'<input type=hidden name="([^"]+)" value="([^"]+)">'):
data[find[0]] = find[1]
data['adcopy_response'] = code
url = self.path
url = url[:url.find('media?c=')] + 'verify.noscript'
data = util.post(url, data, random_ua=True)
if not data:
logging.error('Failed to submit challenge!')
return None
info = re.search(r'URL=(http[^"]+)', data)
if not info:
return None
url = info.group(1)
if self.secure:
url = url.replace('http://', 'https://')
data = util.get(url, random_ua=True)
if data:
return re.search(r'id=gibberish>([^<]+)', data).group(1)
else:
return None
def ask_for_code(self, link):
data = util.get('http://api.recaptcha.net/challenge?k=' + self.id_, random_ua=True)
challenge = re.search(r'challenge.*?:.*?\'(.*)?\',', data)
server = re.search(r'server.*?:.*?\'(.*?)\',', data)
if not challenge or not server:
raise Exception('Failed to get ReCaptcha API response')
self.challenge = challenge.group(1)
self.server = server.group(1)
self.captcha_address = self.server + 'image?c=' + self.challenge
while self.tries < self.MAX_TRIES:
if self.tries > 0:
self.reload()
code = self.get_code()
if not self.challenge or not code:
raise Exception('Invalid challenge or code!')
data = {
'recaptcha_challenge_field': self.challenge,
'recaptcha_response_field': code
}
self.tries += 1
self.data = util.post(link, data, random_ua=True)
info = re.search(r'challenge\?k=(.+?)"', self.data)
if not info:
# No ID found \o/
break
self.id_ = info.group(1).replace('&error=1', '')
def get_challenge(self, code):
data = {}
for find in re.findall(r'<input type=hidden name="([^"]+)" value="([^"]+)">'):
data[find[0]] = find[1]
data['adcopy_response'] = code
url = self.path
url = url[:url.find('media?c=')] + 'verify.noscript'
data = util.post(url, data, random_ua=True)
if not data:
logging.error('Failed to submit challenge!')
return None
info = re.search(r'URL=(http[^"]+)', data)
if not info:
return None
url = info.group(1)
if self.secure:
url = url.replace('http://', 'https://')
data = util.get(url, random_ua=True)
if data:
return re.search(r'id=gibberish>([^<]+)', data).group(1)
else:
return None
def ask_for_code(self, link):
data = util.get('http://api.recaptcha.net/challenge?k=' + self.id_,
random_ua=True)
challenge = re.search(r'challenge.*?:.*?\'(.*)?\',', data)
server = re.search(r'server.*?:.*?\'(.*?)\',', data)
if not challenge or not server:
raise Exception('Failed to get ReCaptcha API response')
self.challenge = challenge.group(1)
self.server = server.group(1)
self.captcha_address = self.server + 'image?c=' + self.challenge
while self.tries < self.MAX_TRIES:
if self.tries > 0:
self.reload()
code = self.get_code()
if not self.challenge or not code:
raise Exception('Invalid challenge or code!')
data = {
'recaptcha_challenge_field': self.challenge,
'recaptcha_response_field': code
}
self.tries += 1
self.data = util.post(link, data, random_ua=True)
info = re.search(r'challenge\?k=(.+?)"', self.data)
if not info:
# No ID found \o/
break
self.id_ = info.group(1).replace('&error=1', '')
def process(link, dest):
tries = 3
while tries > 0:
if tries < 3:
time.sleep(0.3)
tries -= 1
with open(dest, 'wb') as stream:
res = util.download(link, stream, random_ua=True)
if not res:
return False
with open(dest, 'r') as stream:
if '<html' not in stream.read(1024):
# Let's assume we downloaded the file.
return True
stream.seek(0)
data = stream.read()
break
tries += 1
while tries > 0:
if tries < 3:
time.sleep(0.3)
tries -= 1
if 'solvemedia.com/papi/' in data:
logging.info('Detected SolveMedia captcha in "%s".', link)
try:
sv = SolveMedia(data)
code = sv.get_code()
challenge = sv.get_challenge(code)
except:
logging.exception('Captcha solving failed!')
else:
data = {
'adcopy_challenge': challenge,
'adcopy_response': code.replace(' ', '+')
}
data = util.post(link, data, random_ua=True)
if not data:
logging.error('Failed to submit captcha response!')
elif re.search(r'(api\.recaptcha\.net|google\.com/recaptcha/api/)',
data):
logging.info('Detected ReCaptcha in "%s".', link)
try:
rc = ReCaptcha(data)
info = re.search(r'challenge\?k=(.+?)"', data)
if info:
rc.id_ = info.group(1)
rc.ask_for_code(link)
data = rc.data
else:
logging.error('Can\'t find the ReCaptcha challenge!')
except:
logging.exception('Captcha solving failed!')
else:
info = MEDIAFIRE_EXTRACT.search(data)
if not info:
logging.error(
'Failed to parse MediaFire\'s response! Probably a CAPTCHA...'
)
continue
else:
with open(dest, 'wb') as stream:
return util.download(info.group(1),
stream,
random_ua=True)
def process(link, dest):
tries = 3
while tries > 0:
if tries < 3:
time.sleep(0.3)
tries -= 1
with open(dest, 'wb') as stream:
res = util.download(link, stream, random_ua=True)
if not res:
return False
with open(dest, 'r') as stream:
if '<html' not in stream.read(1024):
# Let's assume we downloaded the file.
return True
stream.seek(0)
data = stream.read()
break
tries += 1
while tries > 0:
if tries < 3:
time.sleep(0.3)
tries -= 1
if 'solvemedia.com/papi/' in data:
logging.info('Detected SolveMedia captcha in "%s".', link)
try:
sv = SolveMedia(data)
code = sv.get_code()
challenge = sv.get_challenge(code)
except:
logging.exception('Captcha solving failed!')
else:
data = {
'adcopy_challenge': challenge,
'adcopy_response': code.replace(' ', '+')
}
data = util.post(link, data, random_ua=True)
if not data:
logging.error('Failed to submit captcha response!')
elif re.search(r'(api\.recaptcha\.net|google\.com/recaptcha/api/)', data):
logging.info('Detected ReCaptcha in "%s".', link)
try:
rc = ReCaptcha(data)
info = re.search(r'challenge\?k=(.+?)"', data)
if info:
rc.id_ = info.group(1)
rc.ask_for_code(link)
data = rc.data
else:
logging.error('Can\'t find the ReCaptcha challenge!')
except:
logging.exception('Captcha solving failed!')
else:
info = MEDIAFIRE_EXTRACT.search(data)
if not info:
logging.error('Failed to parse MediaFire\'s response! Probably a CAPTCHA...')
continue
else:
with open(dest, 'wb') as stream:
return util.download(info.group(1), stream, random_ua=True)