def http_download(download_url, outfile, proxy_url=None, proxy_port=None):
if proxy_url:
proxy = "{}:{}".format(proxy_url, proxy_port)
mainlog.info("Using a proxy : {}".format(proxy))
urlopener = build_opener(ProxyHandler({
'https': proxy,
'http': proxy
}), HTTPRedirectHandler())
else:
mainlog.info("Not using a proxy")
urlopener = build_opener(HTTPHandler(), HTTPSHandler(),
HTTPRedirectHandler())
urlopener.addheaders = [(
'User-agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:32.0) Gecko/20100101 Firefox/32.0'
)]
datasource = urlopener.open(download_url)
out = open(outfile, 'wb')
while True:
d = datasource.read(8192)
# self.logger.debug("Downloaded {} bytes".format(len(d)))
if not d:
break
else:
out.write(d)
out.flush()
out.close()
datasource.close()
def open(request):
request = request_vim_to_python(request)
rhandler = HTTPRedirectHandler()
rhandler.max_redirections = request['max_redirect']
opener = build_opener(rhandler)
if request['username']:
passmgr = HTTPPasswordMgrWithDefaultRealm()
passmgr.add_password(
None,
request['url'],
request['username'],
request['password'],
)
opener.add_handler(HTTPBasicAuthHandler(passmgr))
opener.add_handler(HTTPDigestAuthHandler(passmgr))
req = Request(
url=request['url'],
data=request['data'],
headers=request['headers'],
method=request['method'],
)
if request['gzip_decompress']:
req.add_header('Accept-encoding', 'gzip')
try:
res = retry(tries=request['retry'])(opener.open)(
req, timeout=request['timeout'])
except HTTPError as e:
res = e
if not hasattr(res, 'version'):
# urllib2 does not have 'version' field
import httplib
res.version = httplib.HTTPConnection._http_vsn
response_status = "HTTP/%s %d %s\n" % (
'1.1' if res.version == 11 else '1.0',
res.code,
res.msg,
)
response_headers = str(res.headers)
response_body = res.read()
if (request['gzip_decompress']
and res.headers.get('Content-Encoding') == 'gzip'):
response_body = gzip_decompress(response_body)
if hasattr(res.headers, 'get_content_charset'):
# Python 3
response_encoding = res.headers.get_content_charset()
else:
# Python 2
response_encoding = res.headers.getparam('charset')
response_body = response_body.decode(response_encoding)
return (
request['url'],
response_status + response_headers,
response_body,
)
def http_error_302(self, req, fp, code, msg, headers):
previous_url = req.url
result = HTTPRedirectHandler.http_error_302(
self, req, fp, code, msg, headers)
if not hasattr(result, "redirected_via"):
result.redirected_via = []
result.redirected_via.append(previous_url)
def http_error_302(self, req, fp, code, msg, headers):
previous_url = req.url
result = HTTPRedirectHandler.http_error_302(
self, req, fp, code, msg, headers)
if not hasattr(result, "redirected_via"):
result.redirected_via = []
result.redirected_via.append(previous_url)
def _handle_redirect(self, req, fp, code, msg, headers):
url_unescaped = headers.get('Location')
new_url = quote_url(url_unescaped)
headers.replace_header('Location', new_url)
result = HTTPRedirectHandler.http_error_302(self, req, fp, code, msg,
headers)
return result
def http_error_302(self, req, fp, code, msg, headers):
if self.throw:
self.location = headers.getheader('Location')
raise RedirectionException()
else:
return HTTPRedirectHandler.http_error_302(self, req, fp, code, msg,
headers)
def http_error_301(self, req, fp, code, msg, headers):
new_url = req.get_full_url()
result = HTTPRedirectHandler.http_error_301(
self, req, fp, code, msg, headers)
if not hasattr(result, "redirected_via"):
result.redirected_via = []
result.redirected_via.append(new_url)
def http_error_301(self, req, fp, code, msg, headers):
new_url = req.get_full_url()
result = HTTPRedirectHandler.http_error_301(
self, req, fp, code, msg, headers)
if not hasattr(result, "redirected_via"):
result.redirected_via = []
result.redirected_via.append(new_url)
def auth(*, email, password, client_id, scope):
def split_key_value(kv_pair):
kv = kv_pair.split("=")
return kv[0], kv[1]
# Authorization form
def auth_user(email, password, client_id, scope, opener):
response = opener.open(
"http://oauth.vk.com/oauth/authorize?" + \
"redirect_uri=http://oauth.vk.com/blank.html&response_type=token&" + \
"client_id=%s&scope=%s" % (client_id, ",".join(scope))
)
doc = response.read().decode('utf-8')
parser = AuthFormParser()
parser.feed(doc)
parser.close()
if not parser.form_parsed or parser.url is None or "pass" not in parser.params or \
"email" not in parser.params:
raise RuntimeError("Something wrong")
parser.params["email"] = email
parser.params["pass"] = password
if parser.method == "POST":
response = opener.open(parser.url,
urlencode(parser.params).encode('ascii'))
else:
raise NotImplementedError("Method '%s'" % parser.method)
return response.read(), response.geturl()
# Permission request form
def give_access(doc, opener):
parser = AuthFormParser()
parser.feed(doc)
parser.close()
if not parser.form_parsed or parser.url is None:
raise RuntimeError("Something wrong")
if parser.method == "POST":
response = opener.open(parser.url,
urlencode(parser.params).encode('ascii'))
else:
raise NotImplementedError("Method '%s'" % parser.method)
return response.geturl()
if not isinstance(scope, list):
scope = [scope]
opener = build_opener(HTTPCookieProcessor(http.cookiejar.CookieJar()),
HTTPRedirectHandler())
doc, url = auth_user(email, password, client_id, scope, opener)
if urlparse(url).path != "/blank.html":
# Need to give access to requested scope
url = give_access(doc.decode('utf-8'), opener)
if urlparse(url).path != "/blank.html":
raise RuntimeError("Expected success here")
answer = dict(
split_key_value(kv_pair)
for kv_pair in urlparse(url).fragment.split("&"))
if "access_token" not in answer or "user_id" not in answer:
raise RuntimeError("Missing some values in answer")
return answer["access_token"], answer["user_id"]
def setup_method(self, method):
self.cookies = CookieJar()
self.opener = build_opener(HTTPRedirectHandler(),
HTTPHandler(debuglevel=0),
HTTPSHandler(debuglevel=0),
HTTPCookieProcessor(self.cookies))
self.application_process = Process(target=main)
self.application_process.start()
def http_error_302(self, req, fp, code, msg, headers):
#self.log.info("http_error_302: code %s headers %s" % (code, headers))
if 'location' in headers:
newurl = headers['location']
if newurl.startswith('mms:'):
raise URLError("MMS REDIRECT:" + headers["Location"])
return HTTPRedirectHandler.http_error_302(self, req, fp, code, msg,
headers)
def redirect_request(self, req, fp, code, msg, headers, newurl):
if PY2:
# HTTPRedirectHandler is an old style class
request = HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, newurl)
else:
request = super(S3HTTPRedirectHandler, self).redirect_request(req, fp, code, msg, headers, newurl)
del request.headers['Authorization']
return request
def redirect_request(self, request, fp, code, msg, headers, new_url):
request_method = request.get_method()
if str(
code
) in self.redirect_codes and request_method in self.valid_methods:
new_url = new_url.replace(' ', '%20')
request = Request(new_url,
data=request.data,
headers=request.headers,
origin_req_host=request.get_origin_req_host(),
unverifiable=True)
if self.method in self.valid_methods:
if request.get_method() != self.method:
request.get_method = lambda: self.method
return request
else:
HTTPRedirectHandler.redirect_request(request, fp, code, msg,
headers, new_url)
def download(self, url, error_message, timeout, tries):
http_proxy = self.setting.http_proxy
https_proxy = self.setting.https_proxy
if http_proxy or https_proxy:
proxies = {}
if http_proxy:
proxies['http'] = http_proxy
if not https_proxy:
proxies['https'] = http_proxy
if https_proxy:
proxies['https'] = https_proxy
proxy_handler = ProxyHandler(proxies)
else:
proxy_handler = ProxyHandler()
handlers = [proxy_handler, HTTPRedirectHandler()]
# secure_url_match = re.match('^https://([^/]+)', url)
# if secure_url_match != None:
# secure_domain = secure_url_match.group(1)
# bundle_path = self.check_certs(secure_domain, timeout)
# if not bundle_path:
# return False
# handlers.append(VerifiedHTTPSHandler(ca_certs=bundle_path))
opener = build_opener(*handlers)
while tries > 0:
tries -= 1
try:
request = Request(
url, headers={"User-Agent": "OmniMarkup Downloader"})
http_file = opener.open(request, timeout=timeout)
return http_file.read()
except HTTPException as e:
log.warning('%s HTTP exception %s (%s) downloading %s.',
error_message, e.__class__.__name__, str(e), url)
except HTTPError as e:
# Bitbucket and Github ratelimit using 503 a decent amount
if str(e.code) == '503':
log.warning(
'Downloading %s was rate limited, trying again', url)
continue
log.warning('%s HTTP error %s downloading %s.', error_message,
str(e.code), url)
except URLError as e:
# Bitbucket and Github timeout a decent amount
if str(e.reason) == 'The read operation timed out' or \
str(e.reason) == 'timed out':
log.warning('Downloading %s timed out, trying again', url)
continue
log.warning('%s URL error %s downloading %s.', error_message,
str(e.reason), url)
break
return False
def http_error_302(self, req, res, code, msg, headers):
'''Filter non-GET request before calling parent implementation.'''
method = req.get_method()
# Bail unless method is get
if method != 'GET':
return res
# Let parent handle the rest
return HTTPRedirectHandler.http_error_302(self, req, res, code, msg,
headers)
def __init__(self, data_path, **kwargs):
if not validation.is_data_path(data_path):
raise Exception('invalid data_path: %s' % data_path)
self.cookie_jar = MozillaCookieJar(
os.path.join(data_path, default.COOKIES_FILENAME))
try:
self.cookie_jar.load()
except EnvironmentError:
pass
self.opener = build_opener(HTTPRedirectHandler(),
HTTPCookieProcessor(self.cookie_jar))
super(Session, self).__init__(**kwargs)
def redirect_request(self, req, res, code, msg, hdrs, newurl):
response = {
'url': req.get_full_url(),
'headers': res.headers,
'code': code,
'msg': msg,
'new_url': newurl
}
self.redirect_hdrs.append(response)
nreq = HTTPRedirectHandler.redirect_request(self, req, res, code, msg,
hdrs, newurl)
return nreq
def http_error_302(self, request, fp, code, message, headers):
cookie = SimpleCookie()
request_cookie = request.headers.get('Cookie')
if request_cookie:
cookie.load(request_cookie)
set_cookie = headers.get('set-cookie')
if set_cookie:
for value in set_cookie:
cookie.load(value)
headers['Cookie'] = cookie.output(header='', sep='; ')
redirect_handler = HTTPRedirectHandler.http_error_302(self, request, fp, code, message, headers)
return inesHTTPError(request, redirect_handler, code, message, headers)
def redirect_request(self, req, fp, code, msg, headers, newurl):
newreq = HTTPRedirectHandler.redirect_request(self, req, fp, code, msg,
headers, newurl)
if 'Authorization' not in req.headers:
return newreq
src = urlparse(req.get_full_url()).hostname
dest = urlparse(newreq.get_full_url()).hostname
if dest != src:
bot.debug('AuthRedirectHandler: stripping "Authorization" header '
"(%s != %s)" % (dest, src))
del newreq.headers['Authorization']
return newreq
def http_error_302(self, req, res, code, msg, headers):
'''Filter non-GET request before calling parent implementation.'''
method = req.get_method()
# Bail unless method is get
if method != 'GET':
return res
# Let parent handle the rest
return HTTPRedirectHandler.http_error_302(
self,
req,
res,
code,
msg,
headers)
def login(self):
if self.type == 'geonetwork':
url = "%sgeonetwork/srv/en/xml.user.login" % self.base
headers = {
"Content-Type": "application/x-www-form-urlencoded",
"Accept": "text/plain"
}
post = urlencode({
"username": self.user,
"password": self.password
})
request = Request(url, post, headers)
self.opener = build_opener(HTTPCookieProcessor(),
HTTPRedirectHandler())
response = self.opener.open(request)
doc = dlxml.fromstring(response.read())
assert doc.tag == 'ok', "GeoNetwork login failed!"
self.connected = True
def __init__(self, proxy=None):
global USER_AGENT
self.redirh = HTTPRedirectHandler()
self.cookie = HTTPCookieProcessor()
self.rawopen = build_opener(self.redirh, self.cookie)
if proxy is None or self.no_proxy:
self.opener = self.rawopen
elif proxy == 'auto':
# proxy.uku.im:8888
#self.proxyh = ProxyHandler({'http': "http://211.155.86.25:8888"})
#self.proxyh = ProxyHandler({'http': "proxy.uku.im:8888"})
self.proxyh = ProxyHandler({'http': "https://secure.uku.im:8443"})
#self.proxyh = ProxyHandler({'http': "https://proxy.uku.im:443"})
self.opener = build_opener(self.proxyh, self.redirh, self.cookie)
else:
self.proxyh = ProxyHandler(proxy)
self.opener = build_opener(self.proxyh, self.redirh, self.cookie)
self.extra_headers = {"User-Agent": USER_AGENT}
def http_error_301(self, req, res, code, msg, headers):
'''Update location and filter non-GET request before calling parent
implementation.
'''
method = req.get_method()
resource = req.resource
# Update resource location
if 'location' in headers:
resource.location = headers['location']
# Bail unless method is GET
if method != 'GET':
return res
# Let parent handle the rest
return HTTPRedirectHandler.http_error_301(self, req, res, code, msg,
headers)
def __init__(self, args):
""" Start up... """
self.args = args
self.cj = http.cookiejar.MozillaCookieJar(COOKIES_FILENAME)
if os.access(COOKIES_FILENAME, os.F_OK):
self.cj.load(os.getcwd() + "/" + COOKIES_FILENAME)
self.opener = build_opener(HTTPRedirectHandler(),
HTTPHandler(debuglevel=0),
HTTPSHandler(debuglevel=0),
HTTPCookieProcessor(self.cj))
self.opener.addheaders = [
('User-Agent',
('Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.124 Safari/537.36'
)),
('Accept',
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
]
if not os.path.exists(TMP_DIR):
os.makedirs(TMP_DIR)
def __init__(self):
self.user = bugtracker_user
self.password = bugtracker_pass
self.login_page = 'https://bugs.archlinux.org/index.php?do=authenticate'
#self.target_page = 'http://bugs.archlinux.org/index.php?events%5B%5D=1&events%5B%5D=13&events%5B%5D=2&events%5B%5D=4&event_number=50&do=reports'
#self.target_page = 'http://bugs.archlinux.org/index.php?events[]=1&events[]=13&events[]=2&events[]=4&fromdate=&todate=&event_number=50&project=0&do=reports&submit='
self.target_page = 'https://bugs.archlinux.org/index.php?events%5B%5D=1&events%5B%5D=13&events%5B%5D=2&events%5B%5D=4&event_number=50&do=reports&project=0'
self.cj = CookieJar()
self.opener = build_opener(HTTPRedirectHandler(),
HTTPHandler(debuglevel=0),
HTTPSHandler(debuglevel=0),
HTTPCookieProcessor(self.cj))
# self.opener.addheaders = [
# ('User-agent', ('Mozilla/4.0 (compatible; MSIE 6.0; '
# 'Windows NT 5.2; .NET CLR 1.1.4322)'))
# ]
self.opener.addheaders = [('User-agent', 'Mozilla/5.0')]
# need this twice - once to set cookies, once to log in...
self.login()
#self.login()
self.old_events = set([])
def http_error_301(self, req, res, code, msg, headers):
'''Update location and filter non-GET request before calling parent
implementation.
'''
method = req.get_method()
resource = req.resource
# Update resource location
if 'location' in headers:
resource.location = headers['location']
# Bail unless method is GET
if method != 'GET':
return res
# Let parent handle the rest
return HTTPRedirectHandler.http_error_301(
self,
req,
res,
code,
msg,
headers)
class Page(object):
verb_handler = HTTPHandler()
if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
verb_handler.set_http_debuglevel(2)
redir_handler = HTTPRedirectHandler()
opener = build_opener(verb_handler, redir_handler)
def __init__(self):
pass
@staticmethod
def unenscape_Google_bang_URL(old_URL):
"""
See https://developers.google.com/webmasters\
/ajax-crawling/docs/getting-started for more information
"""
if old_URL.find('#!') != -1:
return old_URL.replace('#!', '?_escaped_fragment_=')
elif old_URL.startswith('https://groups.google.com/d/topic/'):
# DEBUG:get_one_topic:URL collected =
# https://groups.google.com/d/topic/jbrout/dreCkob3KSs
# DEBUG:__init__:root_URL =
# https://groups.google.com/forum/\
# ?_escaped_fragment_=topic/jbrout/dreCkob3KSs
return old_URL.replace(
'https://groups.google.com/d/',
'https://groups.google.com/forum/?_escaped_fragment_=')
else:
return old_URL
def _get_page_BS(self, URL):
res = self.opener.open(self.unenscape_Google_bang_URL(URL))
in_str = res.read()
bs = BeautifulSoup(in_str)
res.close()
return bs
def http_error_303(self, req, res, code, msg, hdrs):
# Let parent handle the rest
return HTTPRedirectHandler.http_error_303(self, req, res, code, msg,
hdrs)
request.add_unredirected_header('Authorization',
'Bearer ' + auth_token)
return self.parent.open(request, timeout=request.timeout)
# Got some help from this example https://gist.github.com/FiloSottile/2077115
class HeadRequest(Request):
def get_method(self):
return "HEAD"
better_urllib_get = OpenerDirector()
better_urllib_get.addheaders = DEFAULT_HEADERS.copy()
better_urllib_get.add_handler(HTTPHandler())
better_urllib_get.add_handler(HTTPSHandler())
better_urllib_get.add_handler(HTTPRedirectHandler())
better_urllib_get.add_handler(SocketFileHandler())
better_urllib_get.add_handler(Oauth2TokenAuthHandler())
class RegistryError(Exception):
def __init__(self, response):
self.response_obj = response
# Util functions
#############################################################################################
def parse_thresholds(spec, include_units=True, units_required=True):
"""
Given a spec string break it up into ':' separated chunks. Convert strings to ints as it makes sense
def redirect_request(self, req, fp, code, msg, headers, newurl):
new_req = HTTPRedirectHandler.redirect_request(self, req, fp, code,
msg, headers, newurl)
req.redirect_code = code
return new_req
import pickle
import time
import requests
from celerycrawler import settings
from datetime import datetime
from urllib.parse import urlparse
from urllib.robotparser import RobotFileParser
from urllib.request import urlopen, Request, HTTPError
from urllib.request import install_opener, build_opener, HTTPRedirectHandler
from couchdb.mapping import Document, TextField, DateTimeField, ListField, FloatField
from django.core.cache import cache
install_opener(build_opener(HTTPRedirectHandler()))
class Page(Document):
type = TextField(default="page")
url = TextField()
raw = TextField()
content = TextField()
links = ListField(TextField())
rank = FloatField(default=0)
last_checked = DateTimeField(default=datetime.now)
def is_valid(self):
return (datetime.now() - self.last_checked).days < 7
def update(self):
print("updating page")
parse = urlparse(self.url)
def redirect_request(self, req, fp, code, msg, headers, newurl):
new_req = HTTPRedirectHandler.redirect_request(self, req, fp, code,
msg, headers, newurl)
req.redirect_code = code
return new_req
def _handle_redirect(self, req, fp, code, msg, headers):
url_unescaped = headers.get('Location')
new_url = quote_url(url_unescaped)
headers.replace_header('Location', new_url)
result = HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
return result
def http_error_307(self, req, res, code, msg, hdrs):
#return None
self.counter['307'] += 1
if self.counter['307'] <= 1:
return HTTPRedirectHandler.http_error_307(self, req, res, code,
msg, hdrs)
def redirect_request(self, req, fp, code, msg, hdrs, newurl):
self.last_url = newurl
r = HTTPRedirectHandler.redirect_request(
self, req, fp, code, msg, hdrs, newurl)
r.get_method = lambda: 'HEAD'
return r
def __init__(self):
HTTPRedirectHandler.__init__(self)
self.redirect_hdrs = []
self.counter = collections.Counter()
def http_error_302(self, req, fp, code, msg, headers):
result = HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
result.status = code
return result
def http_error_302(self, req, fp, code, msg, headers):
result = HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
result.status = code
return result
def redirect_request(self, req, *rest):
resource = req.resource
nreq = HTTPRedirectHandler.redirect_request(self, req, *rest)
nreq.resource = resource
return nreq
