def handle_401(self, resp, **kwargs):
# We only care about 401 responses, anything else we want to just
# pass through the actual response
if resp.status_code != 401:
return resp
# We are not able to prompt the user so simply return the response
if not self.prompting:
return resp
parsed = urllib_parse.urlparse(resp.url)
# Prompt the user for a new username and password
username = six.moves.input("User for %s: " % parsed.netloc)
password = getpass.getpass("Password: "******"", password or "")(resp.request)
# Send our new request
new_resp = resp.connection.send(req, **kwargs)
new_resp.history.append(resp)
return new_resp
def __call__(self, req):
parsed = urllib_parse.urlparse(req.url)
# Get the netloc without any embedded credentials
netloc = parsed.netloc.rsplit("@", 1)[-1]
# Set the url of the request to the url without any credentials
req.url = urllib_parse.urlunparse(parsed[:1] + (netloc, ) + parsed[2:])
# Use any stored credentials that we have for this netloc
username, password = self.passwords.get(netloc, (None, None))
# Extract credentials embedded in the url if we have none stored
if username is None:
username, password = self.parse_credentials(parsed.netloc)
# Get creds from netrc if we still don't have them
if username is None and password is None:
netrc_auth = get_netrc_auth(req.url)
username, password = netrc_auth if netrc_auth else (None, None)
if username or password:
# Store the username and password
self.passwords[netloc] = (username, password)
# Send the basic auth with this request
req = HTTPBasicAuth(username or "", password or "")(req)
# Attach a hook to handle 401 responses
req.register_hook("response", self.handle_401)
return req
def __init__(self, requirement_string):
try:
req = REQUIREMENT.parseString(requirement_string)
except ParseException as e:
raise InvalidRequirement(
"Invalid requirement, parse error at \"{0!r}\"".format(
requirement_string[e.loc:e.loc + 8]))
self.name = req.name
if req.url:
parsed_url = urlparse.urlparse(req.url)
if not (parsed_url.scheme and parsed_url.netloc) or (
not parsed_url.scheme and not parsed_url.netloc):
raise InvalidRequirement("Invalid URL given")
self.url = req.url
else:
self.url = None
self.extras = set(req.extras.asList() if req.extras else [])
self.specifier = SpecifierSet(req.specifier)
self.marker = req.marker if req.marker else None
def get_page(cls, link, skip_archives=True, session=None):
if session is None:
raise TypeError(
"get_page() missing 1 required keyword argument: 'session'"
)
url = link.url
url = url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
from pip9.vcs import VcsSupport
for scheme in VcsSupport.schemes:
if url.lower().startswith(scheme) and url[len(scheme)] in '+:':
logger.debug('Cannot look at %s URL %s', scheme, link)
return None
try:
if skip_archives:
filename = link.filename
for bad_ext in ARCHIVE_EXTENSIONS:
if filename.endswith(bad_ext):
content_type = cls._get_content_type(
url, session=session,
)
if content_type.lower().startswith('text/html'):
break
else:
logger.debug(
'Skipping page %s because of Content-Type: %s',
link,
content_type,
)
return
logger.debug('Getting page %s', url)
# Tack index.html onto file:// URLs that point to directories
(scheme, netloc, path, params, query, fragment) = \
urllib_parse.urlparse(url)
if (scheme == 'file' and
os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
resp = session.get(
url,
headers={
"Accept": "text/html",
"Cache-Control": "max-age=600",
},
)
resp.raise_for_status()
# The check for archives above only works if the url ends with
# something that looks like an archive. However that is not a
# requirement of an url. Unless we issue a HEAD request on every
# url we cannot know ahead of time for sure if something is HTML
# or not. However we can check after we've downloaded it.
content_type = resp.headers.get('Content-Type', 'unknown')
if not content_type.lower().startswith("text/html"):
logger.debug(
'Skipping page %s because of Content-Type: %s',
link,
content_type,
)
return
inst = cls(resp.content, resp.url, resp.headers)
except requests.HTTPError as exc:
cls._handle_fail(link, exc, url)
except SSLError as exc:
reason = ("There was a problem confirming the ssl certificate: "
"%s" % exc)
cls._handle_fail(link, reason, url, meth=logger.info)
except requests.ConnectionError as exc:
cls._handle_fail(link, "connection error: %s" % exc, url)
except requests.Timeout:
cls._handle_fail(link, "timed out", url)
else:
return inst
def _validate_secure_origin(self, logger, location):
# Determine if this url used a secure transport mechanism
parsed = urllib_parse.urlparse(str(location))
origin = (parsed.scheme, parsed.hostname, parsed.port)
# The protocol to use to see if the protocol matches.
# Don't count the repository type as part of the protocol: in
# cases such as "git+ssh", only use "ssh". (I.e., Only verify against
# the last scheme.)
protocol = origin[0].rsplit('+', 1)[-1]
# Determine if our origin is a secure origin by looking through our
# hardcoded list of secure origins, as well as any additional ones
# configured on this PackageFinder instance.
for secure_origin in (SECURE_ORIGINS + self.secure_origins):
if protocol != secure_origin[0] and secure_origin[0] != "*":
continue
try:
# We need to do this decode dance to ensure that we have a
# unicode object, even on Python 2.x.
addr = ipaddress.ip_address(
origin[1]
if (
isinstance(origin[1], six.text_type) or
origin[1] is None
)
else origin[1].decode("utf8")
)
network = ipaddress.ip_network(
secure_origin[1]
if isinstance(secure_origin[1], six.text_type)
else secure_origin[1].decode("utf8")
)
except ValueError:
# We don't have both a valid address or a valid network, so
# we'll check this origin against hostnames.
if (origin[1] and
origin[1].lower() != secure_origin[1].lower() and
secure_origin[1] != "*"):
continue
else:
# We have a valid address and network, so see if the address
# is contained within the network.
if addr not in network:
continue
# Check to see if the port patches
if (origin[2] != secure_origin[2] and
secure_origin[2] != "*" and
secure_origin[2] is not None):
continue
# If we've gotten here, then this origin matches the current
# secure origin and we should return True
return True
# If we've gotten to this point, then the origin isn't secure and we
# will not accept it as a valid location to search. We will however
# log a warning that we are ignoring it.
logger.warning(
"The repository located at %s is not a trusted or secure host and "
"is being ignored. If this repository is available via HTTPS it "
"is recommended to use HTTPS instead, otherwise you may silence "
"this warning and allow it anyways with '--trusted-host %s'.",
parsed.hostname,
parsed.hostname,
)
return False
def __init__(self, find_links, index_urls, allow_all_prereleases=False,
trusted_hosts=None, process_dependency_links=False,
session=None, format_control=None, platform=None,
versions=None, abi=None, implementation=None):
"""Create a PackageFinder.
:param format_control: A FormatControl object or None. Used to control
the selection of source packages / binary packages when consulting
the index and links.
:param platform: A string or None. If None, searches for packages
that are supported by the current system. Otherwise, will find
packages that can be built on the platform passed in. These
packages will only be downloaded for distribution: they will
not be built locally.
:param versions: A list of strings or None. This is passed directly
to pep425tags.py in the get_supported() method.
:param abi: A string or None. This is passed directly
to pep425tags.py in the get_supported() method.
:param implementation: A string or None. This is passed directly
to pep425tags.py in the get_supported() method.
"""
if session is None:
raise TypeError(
"PackageFinder() missing 1 required keyword argument: "
"'session'"
)
# Build find_links. If an argument starts with ~, it may be
# a local file relative to a home directory. So try normalizing
# it and if it exists, use the normalized version.
# This is deliberately conservative - it might be fine just to
# blindly normalize anything starting with a ~...
self.find_links = []
for link in find_links:
if link.startswith('~'):
new_link = normalize_path(link)
if os.path.exists(new_link):
link = new_link
self.find_links.append(link)
self.index_urls = index_urls
self.dependency_links = []
# These are boring links that have already been logged somehow:
self.logged_links = set()
self.format_control = format_control or FormatControl(set(), set())
# Domains that we won't emit warnings for when not using HTTPS
self.secure_origins = [
("*", host, "*")
for host in (trusted_hosts if trusted_hosts else [])
]
# Do we want to allow _all_ pre-releases?
self.allow_all_prereleases = allow_all_prereleases
# Do we process dependency links?
self.process_dependency_links = process_dependency_links
# The Session we'll use to make requests
self.session = session
# Kenneth's Hack.
self.extra = None
# The valid tags to check potential found wheel candidates against
self.valid_tags = get_supported(
versions=versions,
platform=platform,
abi=abi,
impl=implementation,
)
# If we don't have TLS enabled, then WARN if anyplace we're looking
# relies on TLS.
if not HAS_TLS:
for link in itertools.chain(self.index_urls, self.find_links):
parsed = urllib_parse.urlparse(link)
if parsed.scheme == "https":
logger.warning(
"pip is configured with locations that require "
"TLS/SSL, however the ssl module in Python is not "
"available."
)
break
def __init__(self, index_url, session, use_datetime=False):
xmlrpc_client.Transport.__init__(self, use_datetime)
index_parts = urllib_parse.urlparse(index_url)
self._scheme = index_parts.scheme
self._session = session
