def request(url,
close=True,
redirect=True,
error=False,
proxy=None,
post=None,
headers=None,
mobile=False,
XHR=False,
limit=None,
referer=None,
cookie=None,
compression=True,
output='',
timeout='30',
verifySsl=True,
flare=True,
ignoreErrors=None,
as_bytes=False):
try:
if not url: return None
if url.startswith('//'): url = 'http:' + url
try:
url = py_tools.ensure_text(url, errors='ignore')
except:
pass
if isinstance(post, dict):
post = bytes(urlencode(post), encoding='utf-8')
elif isinstance(post, str) and py_tools.isPY3:
post = bytes(post, encoding='utf-8')
handlers = []
if proxy is not None:
handlers += [
urllib2.ProxyHandler({'http': '%s' % (proxy)}),
urllib2.HTTPHandler
]
opener = urllib2.build_opener(*handlers)
urllib2.install_opener(opener)
if output == 'cookie' or output == 'extended' or close is not True:
cookies = cookielib.LWPCookieJar()
handlers += [
urllib2.HTTPHandler(),
urllib2.HTTPSHandler(),
urllib2.HTTPCookieProcessor(cookies)
]
opener = urllib2.build_opener(*handlers)
urllib2.install_opener(opener)
if not verifySsl and version_info >= (2, 7, 12):
try:
import ssl
ssl_context = ssl._create_unverified_context()
handlers += [urllib2.HTTPSHandler(context=ssl_context)]
opener = urllib2.build_opener(*handlers)
urllib2.install_opener(opener)
except:
from fenomscrapers.modules import log_utils
log_utils.error()
if verifySsl and ((2, 7, 8) < version_info < (2, 7, 12)):
# try:
# import ssl
# ssl_context = ssl.create_default_context()
# ssl_context.check_hostname = False
# ssl_context.verify_mode = ssl.CERT_NONE
# handlers += [urllib2.HTTPSHandler(context=ssl_context)]
# opener = urllib2.build_opener(*handlers)
# urllib2.install_opener(opener)
# except:
# from fenomscrapers.modules import log_utils
# log_utils.error()
try:
import ssl
try:
import _ssl
CERT_NONE = _ssl.CERT_NONE
except Exception:
CERT_NONE = ssl.CERT_NONE
ssl_context = ssl.create_default_context()
ssl_context.check_hostname = False
ssl_context.verify_mode = CERT_NONE
handlers += [urllib2.HTTPSHandler(context=ssl_context)]
opener = urllib2.build_opener(*handlers)
urllib2.install_opener(opener)
except:
from fenomscrapers.modules import log_utils
log_utils.error()
try:
headers.update(headers)
except:
headers = {}
if 'User-Agent' in headers: pass
elif mobile is not True:
headers['User-Agent'] = cache.get(randomagent, 12)
else:
headers['User-Agent'] = 'Apple-iPhone/701.341'
if 'Referer' in headers: pass
elif referer is not None: headers['Referer'] = referer
if 'Accept-Language' not in headers:
headers['Accept-Language'] = 'en-US'
if 'X-Requested-With' in headers: pass
elif XHR: headers['X-Requested-With'] = 'XMLHttpRequest'
if 'Cookie' in headers: pass
elif cookie: headers['Cookie'] = cookie
if 'Accept-Encoding' in headers: pass
elif compression and limit is None: headers['Accept-Encoding'] = 'gzip'
# if redirect is False:
# class NoRedirection(urllib2.HTTPErrorProcessor):
# def http_response(self, request, response):
# return response
# opener = urllib2.build_opener(NoRedirection)
# urllib2.install_opener(opener)
# try: del headers['Referer']
# except: pass
if redirect is False:
class NoRedirectHandler(urllib2.HTTPRedirectHandler):
def http_error_302(self, reqst, fp, code, msg, head):
infourl = addinfourl(fp, head, reqst.get_full_url())
infourl.status = code
infourl.code = code
return infourl
http_error_300 = http_error_302
http_error_301 = http_error_302
http_error_303 = http_error_302
http_error_307 = http_error_302
opener = urllib2.build_opener(NoRedirectHandler())
urllib2.install_opener(opener)
try:
del headers['Referer']
except:
pass
req = urllib2.Request(url, data=post)
_add_request_header(req, headers)
try:
response = urllib2.urlopen(req, timeout=int(timeout))
except HTTPError as error_response: # if HTTPError, using "as response" will be reset after entire Exception code runs and throws error around line 247 as "local variable 'response' referenced before assignment", re-assign it
response = error_response
try:
ignore = ignoreErrors and (int(response.code) == ignoreErrors
or int(
response.code) in ignoreErrors)
except:
ignore = False
if not ignore:
if response.code in [
301, 307, 308, 503, 403
]: # 403:Forbidden added 3/3/21 for cloudflare, fails on bad User-Agent
cf_result = response.read(5242880)
try:
encoding = response.headers["Content-Encoding"]
except:
encoding = None
if encoding == 'gzip':
cf_result = gzip.GzipFile(
fileobj=StringIO(cf_result)).read()
if flare and 'cloudflare' in str(response.info()).lower():
from fenomscrapers.modules import log_utils
log_utils.log(
'client module calling cfscrape: url=%s' % url,
level=log_utils.LOGDEBUG)
try:
from fenomscrapers.modules import cfscrape
if isinstance(post, dict): data = post
else:
try:
data = parse_qs(post)
except:
data = None
scraper = cfscrape.CloudScraper()
if response.code == 403: # possible bad User-Agent in headers, let cfscrape assign
response = scraper.request(
method='GET' if post is None else 'POST',
url=url,
data=data,
timeout=int(timeout))
else:
response = scraper.request(
method='GET' if post is None else 'POST',
url=url,
headers=headers,
data=data,
timeout=int(timeout))
result = response.content
flare = 'cloudflare' # Used below
try:
cookies = response.request._cookies
except:
log_utils.error()
if response.status_code == 403: # if cfscrape server still responds with 403
log_utils.log(
'cfscrape-Error url=(%s): %s' %
(url, 'HTTP Error 403: Forbidden'),
__name__,
level=log_utils.LOGDEBUG)
return None
except:
log_utils.error()
elif 'cf-browser-verification' in cf_result:
netloc = '%s://%s' % (urlparse(url).scheme,
urlparse(url).netloc)
ua = headers['User-Agent']
cf = cache.get(cfcookie().get, 168, netloc, ua,
timeout)
headers['Cookie'] = cf
req = urllib2.Request(url, data=post)
_add_request_header(req, headers)
response = urllib2.urlopen(req, timeout=int(timeout))
else:
if error is False:
from fenomscrapers.modules import log_utils
log_utils.error('Request-Error url=(%s)' % url)
return None
else:
if error is False:
from fenomscrapers.modules import log_utils
log_utils.error('Request-Error url=(%s)' % url)
return None
elif error is True and response.code in [
401, 404, 405
]: # no point in continuing after this exception runs with these response.code's
try:
response_headers = dict(
[(item[0].title(), item[1])
for item in list(response.info().items())]
) # behaves differently 18 to 19. 18 I had 3 "Set-Cookie:" it combined all 3 values into 1 key. In 19 only the last keys value was present.
except:
from fenomscrapers.modules import log_utils
log_utils.error()
response_headers = response.headers
return (str(response), str(response.code),
response_headers)
if output == 'cookie':
try:
result = '; '.join(
['%s=%s' % (i.name, i.value) for i in cookies])
except:
pass
try:
result = cf
except:
pass
if close is True: response.close()
return result
elif output == 'geturl':
result = response.geturl()
if close is True: response.close()
return result
elif output == 'headers':
result = response.headers
if close is True: response.close()
return result
elif output == 'chunk':
try:
content = int(response.headers['Content-Length'])
except:
content = (2049 * 1024)
if content < (2048 * 1024): return
try:
result = response.read(16 * 1024)
except:
result = response # testing
if close is True: response.close()
return result
elif output == 'file_size':
try:
content = int(response.headers['Content-Length'])
except:
content = '0'
if close is True: response.close()
return content
if flare != 'cloudflare':
if limit == '0': result = response.read(224 * 1024)
elif limit is not None: result = response.read(int(limit) * 1024)
else: result = response.read(5242880)
try:
encoding = response.headers["Content-Encoding"]
except:
encoding = None
if encoding == 'gzip':
result = gzip.GzipFile(fileobj=StringIO(result)).read()
if not as_bytes:
result = py_tools.ensure_text(result, errors='ignore')
if 'sucuri_cloudproxy_js' in result:
su = sucuri().get(result)
headers['Cookie'] = su
req = urllib2.Request(url, data=post)
_add_request_header(req, headers)
response = urllib2.urlopen(req, timeout=int(timeout))
if limit == '0': result = response.read(224 * 1024)
elif limit is not None: result = response.read(int(limit) * 1024)
else: result = response.read(5242880)
try:
encoding = response.headers["Content-Encoding"]
except:
encoding = None
if encoding == 'gzip':
result = gzip.GzipFile(fileobj=StringIO(result)).read()
if 'Blazingfast.io' in result and 'xhr.open' in result:
netloc = '%s://%s' % (urlparse(url).scheme, urlparse(url).netloc)
ua = headers['User-Agent']
headers['Cookie'] = cache.get(bfcookie().get, 168, netloc, ua,
timeout)
result = _basic_request(url,
headers=headers,
post=post,
timeout=timeout,
limit=limit)
if output == 'extended':
try:
response_headers = dict(
[(item[0].title(), item[1])
for item in list(response.info().items())]
) # behaves differently 18 to 19. 18 I had 3 "Set-Cookie:" it combined all 3 values into 1 key. In 19 only the last keys value was present.
except:
from fenomscrapers.modules import log_utils
log_utils.error()
response_headers = response.headers
try:
response_code = str(response.code)
except:
response_code = str(response.status_code
) # object from CFScrape Requests object.
try:
cookie = '; '.join(
['%s=%s' % (i.name, i.value) for i in cookies])
except:
pass
try:
cookie = cf
except:
pass
if close is True: response.close()
return (result, response_code, response_headers, headers, cookie)
else:
if close is True: response.close()
return result
except:
from fenomscrapers.modules import log_utils
log_utils.error('Request-Error url=(%s)' % url)
return None
def request(url,
close=True,
redirect=True,
error=False,
proxy=None,
post=None,
headers=None,
mobile=False,
XHR=False,
limit=None,
referer=None,
cookie=None,
compression=True,
output='',
timeout='30',
ignoreSsl=False,
flare=True,
ignoreErrors=None):
try:
if not url: return None
handlers = []
if proxy is not None:
handlers += [
urllib2.ProxyHandler({'http': '%s' % (proxy)}),
urllib2.HTTPHandler
]
opener = urllib2.build_opener(*handlers)
opener = urllib2.install_opener(opener)
if output == 'cookie' or output == 'extended' or not close is True:
cookies = cookielib.LWPCookieJar()
handlers += [
urllib2.HTTPHandler(),
urllib2.HTTPSHandler(),
urllib2.HTTPCookieProcessor(cookies)
]
opener = urllib2.build_opener(*handlers)
opener = urllib2.install_opener(opener)
if ignoreSsl or ((2, 7, 8) < sys.version_info < (2, 7, 12)):
try:
import ssl
ssl_context = ssl.create_default_context()
ssl_context.check_hostname = False
ssl_context.verify_mode = ssl.CERT_NONE
handlers += [urllib2.HTTPSHandler(context=ssl_context)]
opener = urllib2.build_opener(*handlers)
opener = urllib2.install_opener(opener)
except:
pass
if url.startswith('//'):
url = 'http:' + url
try:
headers.update(headers)
except:
headers = {}
if 'User-Agent' in headers: pass
elif mobile is not True:
headers['User-Agent'] = cache.get(randomagent, 12)
else:
headers['User-Agent'] = 'Apple-iPhone/701.341'
if 'Referer' in headers: pass
elif referer: headers['Referer'] = referer
if 'Accept-Language' not in headers:
headers['Accept-Language'] = 'en-US'
if 'X-Requested-With' in headers: pass
elif XHR: headers['X-Requested-With'] = 'XMLHttpRequest'
if 'Cookie' in headers: pass
elif cookie: headers['Cookie'] = cookie
if 'Accept-Encoding' in headers: pass
elif compression and limit is None: headers['Accept-Encoding'] = 'gzip'
if redirect is False:
class NoRedirection(urllib2.HTTPErrorProcessor):
def http_response(self, request, response):
return response
opener = urllib2.build_opener(NoRedirection)
opener = urllib2.install_opener(opener)
try:
del headers['Referer']
except:
pass
if isinstance(post, dict):
# Gets rid of the error: 'ascii' codec can't decode byte 0xd0 in position 0: ordinal not in range(128)
try:
iter_items = post.iteritems()
except:
iter_items = post.items()
for key, value in iter_items:
try:
post[key] = value.encode('utf-8')
except:
pass
post = urlencode(post)
request = urllib2.Request(url, data=post)
_add_request_header(request, headers)
try:
response = urllib2.urlopen(request, timeout=int(timeout))
except HTTPError as response:
try:
ignore = ignoreErrors and (int(response.code) == ignoreErrors
or int(
response.code) in ignoreErrors)
except:
ignore = False
if not ignore:
if response.code in [301, 307, 308, 503]:
cf_result = response.read(5242880)
try:
encoding = response.info().getheader(
'Content-Encoding')
except:
encoding = None
if encoding == 'gzip':
cf_result = gzip.GzipFile(
fileobj=StringIO(cf_result)).read()
if flare and 'cloudflare' in str(response.info()).lower():
log_utils.log(
'client module calling cfscrape: url=%s' % url,
level=log_utils.LOGNOTICE)
try:
from fenomscrapers.modules import cfscrape
if isinstance(post, dict): data = post
else:
try:
data = parse_qs(post)
except:
data = None
scraper = cfscrape.CloudScraper()
response = scraper.request(
method='GET' if post is None else 'POST',
url=url,
headers=headers,
data=data,
timeout=int(timeout))
result = response.content
flare = 'cloudflare' # Used below
try:
cookies = response.request._cookies
except:
log_utils.error()
except:
log_utils.error()
elif 'cf-browser-verification' in cf_result:
netloc = '%s://%s' % (urlparse(url).scheme,
urlparse(url).netloc)
ua = headers['User-Agent']
cf = cache.get(cfcookie().get, 168, netloc, ua,
timeout)
headers['Cookie'] = cf
request = urllib2.Request(url, data=post)
_add_request_header(request, headers)
response = urllib2.urlopen(request,
timeout=int(timeout))
else:
log_utils.log('Request-Error (%s): %s' %
(str(response.code), url),
level=log_utils.LOGERROR)
if error is False: return None
else:
log_utils.log('Request-Error (%s): %s' %
(str(response.code), url),
level=log_utils.LOGERROR)
if error is False: return None
if output == 'cookie':
try:
result = '; '.join(
['%s=%s' % (i.name, i.value) for i in cookies])
except:
pass
try:
result = cf
except:
pass
if close is True: response.close()
return result
elif output == 'geturl':
result = response.geturl()
if close is True: response.close()
return result
elif output == 'headers':
result = response.headers
if close is True: response.close()
return result
elif output == 'chunk':
try:
content = int(response.headers['Content-Length'])
except:
content = (2049 * 1024)
if content < (2048 * 1024): return
result = response.read(16 * 1024)
if close is True: response.close()
return result
if flare != 'cloudflare':
if limit == '0': result = response.read(224 * 1024)
elif limit is not None: result = response.read(int(limit) * 1024)
else: result = response.read(5242880)
try:
encoding = response.info().getheader('Content-Encoding')
except:
encoding = None
if encoding == 'gzip':
result = gzip.GzipFile(fileobj=StringIO(result)).read()
if 'sucuri_cloudproxy_js' in result:
su = sucuri().get(result)
headers['Cookie'] = su
request = urllib2.Request(url, data=post)
_add_request_header(request, headers)
response = urllib2.urlopen(request, timeout=int(timeout))
if limit == '0': result = response.read(224 * 1024)
elif limit is not None: result = response.read(int(limit) * 1024)
else: result = response.read(5242880)
try:
encoding = response.info().getheader('Content-Encoding')
except:
encoding = None
if encoding == 'gzip':
result = gzip.GzipFile(fileobj=StringIO(result)).read()
if 'Blazingfast.io' in result and 'xhr.open' in result:
netloc = '%s://%s' % (urlparse(url).scheme, urlparse(url).netloc)
ua = headers['User-Agent']
headers['Cookie'] = cache.get(bfcookie().get, 168, netloc, ua,
timeout)
result = _basic_request(url,
headers=headers,
post=post,
timeout=timeout,
limit=limit)
if output == 'extended':
try:
response_headers = dict([(item[0].title(), item[1])
for item in response.info().items()])
except:
response_headers = response.headers
try:
response_code = str(response.code)
except:
response_code = str(response.status_code
) # object from CFScrape Requests object.
try:
cookie = '; '.join(
['%s=%s' % (i.name, i.value) for i in cookies])
except:
pass
try:
cookie = cf
except:
pass
if close is True: response.close()
return (result, response_code, response_headers, headers, cookie)
else:
if close is True: response.close()
return result
except Exception as e:
log_utils.log('Request-Error: (%s) => %s' % (str(e), url),
level=log_utils.LOGERROR)
return None