本文整理汇总了Python中urllib2.splittype函数的典型用法代码示例。如果您正苦于以下问题:Python splittype函数的具体用法?Python splittype怎么用?Python splittype使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了splittype函数的20个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: csqueryConents
return
#客户端方法
def csqueryConents(self,csdompagination):
return csdompagination
def csqueryPagination(self,csdom,pagesPath):
pages=[]
for index,item in enumerate(pagesPath):
csquery=item
cspage=csdom.Select(csquery)
if cspage:
#找到所有的a标签
children=cspage.Find("a")
if children.Length>0:
for i in range(0,children.Length):
cshyper=CsQuery.CQ.Create(children[i])
href=cshyper.Attr("href")
text=cshyper.Text()
pagelamda=self.config.cfgContent.Options.PageLamda
if pagelamda:
str=pagelamda(cshyper,href,text)
print "this is type for url : %s" % (type(str))
if str:
href=str
print " this is true"
else:
print "this is false"
continue
if href and href[0:1]=="/":
proto, rest = urllib2.splittype(self.config.cfgUrl)
host, rest = urllib2.splithost(rest)
href=proto+"://"+host+href
elif href and href[0:1]=="?":
proto, rest = urllib2.splittype(self.config.cfgUrl)
host, rest = urllib2.splithost(rest)
p=rest.split("?")
p[1]=href[1:]
href=proto+"://"+host+"?".join(p)
elif href.find("http")==-1:
proto, rest = urllib2.splittype(self.config.cfgUrl)
host, rest = urllib2.splithost(rest)
p_rest=rest.split("/")
p_rest[len(p_rest)-1]=href
href=proto+"://"+host+"/".join(p_rest)
scale=self.config.cfgContent.Options.PageSimilarity
rate=0.0
simlilar=StringHelper.LevenshteinDistance(self.__url,href,rate)
print "this is simliar :%f " % simlilar[1]
if href and simlilar[1]>scale and simlilar[1]<1:
pages.append(href)
开发者ID:hn5092,项目名称:learn_python,代码行数:54,代码来源:build_result.py
示例2: get_host_from_url
def get_host_from_url(url):
"""
功能:把url转换为域名
"""
root_proto, root_rest = urllib2.splittype(url)
root_host, root_rest = urllib2.splithost(root_rest)
return root_host
开发者ID:leniy,项目名称:Blog-Social-Relations-Spider,代码行数:7,代码来源:main.py
示例3: _expand_recipe
def _expand_recipe(content, url=''):
urls = []
for line in content.splitlines():
line = line.lstrip().rstrip()
try:
target_type, target = line.split(':', 1)
except ValueError:
continue # blank line in recipe
if target_type in ACCEPTED_RECIPE_TYPES:
if isinstance(target, unicode):
target = target.encode('utf-8')
target = target.lstrip().rstrip()
# translate well-known variables
for name in COOK_VARIABLES:
target = target.replace("$"+name, COOK_VARIABLES[name])
# Check to see if the target is a URL (has a scheme)
# if not we want to join it to the current url before
# carrying on.
scheme, _ = urllib2.splittype(target)
if not scheme:
if not '%' in target:
target = urllib.quote(target)
target = urlparse.urljoin(url, target)
if target_type == 'recipe':
urls.extend(recipe_to_urls(target))
else:
urls.append(target)
return urls
开发者ID:bengillies,项目名称:tiddlywebplugins.twimport,代码行数:28,代码来源:twimport.py
示例4: doQuery
def doQuery(self,query,name):
# urllib doesn't honor user Content-type, use urllib2
garbage, path = urllib2.splittype(FieldVal(self.site,"url"))
host, selector = urllib2.splithost(path)
response=False
try:
errmsg= "** An ERROR occurred attempting HTTPS connection to"
h = httplib.HTTPSConnection(host, timeout=5)
errmsg= "** An ERROR occurred sending POST request to"
p = h.request('POST', selector, query,
{"Content-type": "application/x-ofx",
"Accept": "*/*, application/x-ofx"}
)
errmsg= "** An ERROR occurred retrieving POST response from"
#allow up to 30 secs for the server response (it has to assemble the statement)
h.sock.settimeout(30)
response = h.getresponse().read()
f = file(name,"w")
f.write(response)
f.close()
except Exception as inst:
self.status = False
print errmsg, host
print " Exception type:", type(inst)
print " Exception Val :", inst
if response:
print " HTTPS ResponseCode :", response.status
print " HTTPS ResponseReason:", response.reason
if h: h.close()
开发者ID:NolanT,项目名称:ynab-qfx,代码行数:32,代码来源:ofx.py
示例5: _add_proxies
def _add_proxies():
if sickrage.app.config.proxy_setting:
sickrage.app.log.debug("Using global proxy: " + sickrage.app.config.proxy_setting)
scheme, address = urllib2.splittype(sickrage.app.config.proxy_setting)
address = ('http://{}'.format(sickrage.app.config.proxy_setting),
sickrage.app.config.proxy_setting)[scheme]
return {"http": address, "https": address}
开发者ID:SiCKRAGETV,项目名称:SiCKRAGE,代码行数:7,代码来源:__init__.py
示例6: download_file
def download_file(self, url):
injectd_url = self.extract_url(urllib2.unquote(url))
try:
req = urllib2.Request(injectd_url)
# Set User-Agent to look more credible
req.add_unredirected_header('User-Agent', '-')
# FIXME: We need a timeout on read here
injected_file = urllib2.urlopen(req, timeout=4).read()
# If the file is hosted on a SSL enabled host get the certificate
if re.match('^https', injectd_url, re.IGNORECASE):
proto, rest = urllib2.splittype(injectd_url)
host, rest = urllib2.splithost(rest)
host, port = urllib2.splitport(host)
if port is None:
port = 443
cert_file = ssl.get_server_certificate((host, int(port)))
cert_name = self.store_file(cert_file)
except IOError as e:
logger.exception("Failed to fetch injected file, I/O error: {0}".format(e))
# TODO: We want to handle the case where we can't download
# the injected file but pretend to be vulnerable.
file_name = None
else:
file_name, file_sha256 = self.store_file(injected_file)
return file_name, file_sha256
开发者ID:mushorg,项目名称:glastopf,代码行数:27,代码来源:rfi.py
示例7: request
def request(self, method, url, headers=None, params=None, proxies=None, cache=True, verify=False, *args, **kwargs):
if headers is None: headers = {}
if params is None: params = {}
if proxies is None: proxies = {}
headers['Accept-Encoding'] = 'gzip, deflate'
headers["User-Agent"] = sickrage.app.user_agent
# request session ssl verify
if sickrage.app.config.ssl_verify:
try:
verify = certifi.where()
except:
pass
# request session proxies
if 'Referer' not in headers and sickrage.app.config.proxy_setting:
sickrage.app.log.debug("Using global proxy: " + sickrage.app.config.proxy_setting)
scheme, address = urllib2.splittype(sickrage.app.config.proxy_setting)
address = ('http://{}'.format(sickrage.app.config.proxy_setting),
sickrage.app.config.proxy_setting)[scheme]
proxies.update({"http": address, "https": address})
headers.update({'Referer': address})
# setup caching adapter
if cache:
adapter = CacheControlAdapter(DBCache(os.path.abspath(os.path.join(sickrage.app.data_dir, 'sessions.db'))))
self.mount('http://', adapter)
self.mount('https://', adapter)
# get web response
response = super(WebSession, self).request(
method,
url,
headers=headers,
params=params,
verify=verify,
proxies=proxies,
hooks={'response': WebHooks.log_url},
*args, **kwargs
)
try:
# check web response for errors
response.raise_for_status()
except requests.exceptions.SSLError as e:
if ssl.OPENSSL_VERSION_INFO < (1, 0, 1, 5):
sickrage.app.log.info(
"SSL Error requesting url: '{}' You have {}, try upgrading OpenSSL to 1.0.1e+".format(
e.request.url, ssl.OPENSSL_VERSION))
if sickrage.app.config.ssl_verify:
sickrage.app.log.info(
"SSL Error requesting url: '{}', try disabling cert verification in advanced settings".format(
e.request.url))
except Exception:
pass
return response
开发者ID:gborri,项目名称:SiCKRAGE,代码行数:59,代码来源:__init__.py
示例8: request
def request(self, method, url, headers=None, params=None, proxies=None, cache=True, verify=False, *args, **kwargs):
if headers is None: headers = {}
if params is None: params = {}
if proxies is None: proxies = {}
url = self.normalize_url(url)
headers.update({'Accept-Encoding': 'gzip, deflate'})
headers.update(random.choice(USER_AGENTS))
# request session ssl verify
if sickrage.srCore.srConfig.SSL_VERIFY:
try:
verify = certifi.where()
except:
pass
# request session proxies
if 'Referer' not in headers and sickrage.srCore.srConfig.PROXY_SETTING:
sickrage.srCore.srLogger.debug("Using global proxy: " + sickrage.srCore.srConfig.PROXY_SETTING)
scheme, address = urllib2.splittype(sickrage.srCore.srConfig.PROXY_SETTING)
address = ('http://{}'.format(sickrage.srCore.srConfig.PROXY_SETTING),
sickrage.srCore.srConfig.PROXY_SETTING)[scheme]
proxies.update({"http": address, "https": address})
headers.update({'Referer': address})
# setup session caching
if cache:
cache_file = os.path.abspath(os.path.join(sickrage.DATA_DIR, 'sessions.db'))
self.__class__ = cachecontrol.CacheControl(self,
cache=DBCache(cache_file),
heuristic=ExpiresAfter(days=7)).__class__
# get web response
response = super(srSession, self).request(method,
url,
headers=headers,
params=params,
verify=verify,
proxies=proxies,
*args, **kwargs)
try:
# check web response for errors
response.raise_for_status()
except requests.exceptions.SSLError as e:
if ssl.OPENSSL_VERSION_INFO < (1, 0, 1, 5):
sickrage.srCore.srLogger.info(
"SSL Error requesting url: '{}' You have {}, try upgrading OpenSSL to 1.0.1e+".format(
e.request.url, ssl.OPENSSL_VERSION))
if sickrage.srCore.srConfig.SSL_VERIFY:
sickrage.srCore.srLogger.info(
"SSL Error requesting url: '{}', try disabling cert verification in advanced settings".format(
e.request.url))
except Exception:
pass
return response
开发者ID:djenniex,项目名称:SickBeard-TVRage,代码行数:59,代码来源:session.py
示例9: download
def download(self, url, insecure):
""" Tries to download a file from url.
Returns the path to the local file.
"""
scheme = urllib2.splittype(url)[0]
DL = downloaders.get(scheme, Downloader)
return DL(url, self, insecure).execute()
开发者ID:AnyarInc,项目名称:VisTrails,代码行数:8,代码来源:init.py
示例10: decorator
def decorator(*args, **kwargs):
request = args[0]
enabled_https = getattr(settings, 'SESSION_COOKIE_SECURE', False)
if enabled_https and not request.is_secure():
http_url = request.build_absolute_uri(request.get_full_path())
https_url = 'https:' + urllib2.splittype(http_url)[1]
return HttpResponseRedirect(https_url)
return func(*args, **kwargs)
开发者ID:JiaFeiX,项目名称:lernanta,代码行数:8,代码来源:decorators.py
示例11: get_local_name
def get_local_name(url):
url = url.strip()
url = re.sub('[\/]+$', '', url)
rest = urllib2.splittype(url)[1]
host, rest = urllib2.splithost(rest)
if rest is None or rest == '':
return host
return os.path.basename(rest)
开发者ID:inwotep,项目名称:lava-android-test,代码行数:8,代码来源:utils.py
示例12: _setUpSession
def _setUpSession(session=None, headers=None, params=None):
"""
Returns a session initialized with default cache and parameter settings
:param session: session object to (re)use
:param headers: Headers to pass to session
:return: session object
"""
# request session
if headers is None:
headers = {}
sessionCache = None
FileCacheDir = sickrage.srConfig.CACHE_DIR or get_temp_dir()
if FileCacheDir:
sessionCache = FileCache(os.path.join(FileCacheDir, 'sessions'), use_dir_lock=True)
session = cachecontrol.CacheControl(sess=session or requests.Session(), cache=sessionCache, cache_etags=False)
# request session headers
session.headers.update(headers)
session.headers.update({'Accept-Encoding': 'gzip,deflate'})
session.headers.update(random.choice(USER_AGENTS))
# request session clear residual referer
if 'Referer' in session.headers and 'Referer' not in headers:
session.headers.pop('Referer')
try:
# request session ssl verify
session.verify = False
if sickrage.srConfig.SSL_VERIFY:
session.verify = certifi.where()
except:pass
# request session proxies
if 'Referer' not in session.headers and sickrage.srConfig.PROXY_SETTING:
sickrage.srLogger.debug("Using global proxy: " + sickrage.srConfig.PROXY_SETTING)
scheme, address = urllib2.splittype(sickrage.srConfig.PROXY_SETTING)
address = ('http://{}'.format(sickrage.srConfig.PROXY_SETTING), sickrage.srConfig.PROXY_SETTING)[scheme]
session.proxies = {
"http": address,
"https": address,
}
session.headers.update({'Referer': address})
if 'Content-Type' in session.headers:
session.headers.pop('Content-Type')
if params and isinstance(params, (list, dict)):
for param in params:
if isinstance(params[param], unicode):
params[param] = params[param].encode('utf-8')
session.params = params
return session
开发者ID:Aeronaut,项目名称:SiCKRAGE,代码行数:56,代码来源:sessions.py
示例13: getRSSFeed
def getRSSFeed(self, url, params=None):
handlers = []
if sickrage.app.config.proxy_setting:
sickrage.app.log.debug("Using global proxy for url: " + url)
scheme, address = urllib2.splittype(sickrage.app.config.proxy_setting)
address = sickrage.app.config.proxy_setting if scheme else 'http://' + sickrage.app.config.proxy_setting
handlers = [urllib2.ProxyHandler({'http': address, 'https': address})]
return getFeed(url, params=params, handlers=handlers)
开发者ID:gborri,项目名称:SiCKRAGE,代码行数:10,代码来源:tv_cache.py
示例14: getRSSFeed
def getRSSFeed(self, url, params=None):
handlers = []
if sickrage.srCore.srConfig.PROXY_SETTING:
sickrage.srCore.srLogger.debug("Using global proxy for url: " + url)
scheme, address = urllib2.splittype(sickrage.srCore.srConfig.PROXY_SETTING)
address = sickrage.srCore.srConfig.PROXY_SETTING if scheme else 'http://' + sickrage.srCore.srConfig.PROXY_SETTING
handlers = [urllib2.ProxyHandler({'http': address, 'https': address})]
return getFeed(url, params=params, handlers=handlers)
开发者ID:djenniex,项目名称:SickBeard-TVRage,代码行数:10,代码来源:tv_cache.py
示例15: _setup_server
def _setup_server(self, server=None):
if server:
host, path = urllib2.splithost(urllib2.splittype(server)[-1])
if not path:
path = '/'
self.client_con = python_webdav.client.Client(host,
webdav_path=path)
self.client_con.set_connection('wibble', 'fish')
else:
print "I need a server!"
self.client_con = None
开发者ID:AOrazaev,项目名称:python-webdav,代码行数:11,代码来源:basic_shell.py
示例16: url_size
def url_size(url):
import httplib, urllib2
proto, url = urllib2.splittype(url)
assert(proto.lower() == 'http')
host, path = urllib2.splithost(url)
# http://stackoverflow.com/questions/107405/how-do-you-send-a-head-http-request-in-python
conn = httplib.HTTPConnection(host)
conn.request('HEAD', path)
res = conn.getresponse()
# FIXME: Follow any redirects
return int(res.getheader('content-length'))
开发者ID:AlessioRocco,项目名称:junk,代码行数:11,代码来源:wget2axel.py
示例17: lamda
def lamda(self,csblock):
href=csblock[0].Attr("href")
if not href:
href=csblock[1]
if href:
href=href.replace("\\","").replace("\"","")
if href and href[0:1]=="/":
proto, rest = urllib2.splittype(self.config.cfgUrl)
host, rest = urllib2.splithost(rest)
href=proto+"://"+host+href
return href
开发者ID:hn5092,项目名称:learn_python,代码行数:11,代码来源:cg_ali213_reyouwp_list.py
示例18: echo
echo(content)
except Exception as err:
pass
finally:
return content
def pageCsContentImage(self,cspage):
"""本地img替换为完全img路径"""
proto, rest = urllib2.splittype(self.config.cfgUrl)
host, rest = urllib2.splithost(rest)
csimgs=cspage.Find("img")
开发者ID:hn5092,项目名称:learn_python,代码行数:11,代码来源:build_result.py
示例19: parse_protocols
def parse_protocols(ctx, base_uri=None):
""" Parse ``protocols`` from a root context.
If protocols are not provided in root, use baseUri protocol.
"""
protocols = ctx.get_property_with_schema(
'protocols', RamlRoot.protocols)
if protocols is None and base_uri is not None:
protocols = [urllib2.splittype(base_uri)[0]]
if protocols:
protocols = [p.upper() for p in protocols]
return protocols
开发者ID:gooli,项目名称:pyraml-parser,代码行数:12,代码来源:parser.py
示例20: RemoteAccess
def RemoteAccess(url, *args, **kwargs):
"""Connect to a remote Subversion server
:param url: URL to connect to
:return: RemoteAccess object
"""
if isinstance(url, bytes):
url = url.decode("utf-8")
(type, opaque) = splittype(url)
if type not in url_handlers:
raise SubversionException("Unknown URL type '%s'" % type, ERR_BAD_URL)
return url_handlers[type](url, *args, **kwargs)
开发者ID:ardumont,项目名称:subvertpy,代码行数:12,代码来源:ra.py
注:本文中的urllib2.splittype函数示例由纯净天空整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论