Python setuptools.extern.six.moves.urllib() Examples
The following are 30
code examples of setuptools.extern.six.moves.urllib().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
setuptools.extern.six.moves
, or try the search function
.
Example #1
Source File: package_index.py From scylla with Apache License 2.0 | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #2
Source File: package_index.py From ironpython2 with Apache License 2.0 | 6 votes |
def __init__( self, index_url="https://pypi.org/simple/", hosts=('*',), ca_bundle=None, verify_ssl=True, *args, **kw ): Environment.__init__(self, *args, **kw) self.index_url = index_url + "/" [:not index_url.endswith('/')] self.scanned_urls = {} self.fetched_urls = {} self.package_pages = {} self.allows = re.compile('|'.join(map(translate, hosts))).match self.to_scan = [] use_ssl = ( verify_ssl and ssl_support.is_available and (ca_bundle or ssl_support.find_ca_bundle()) ) if use_ssl: self.opener = ssl_support.opener_for(ca_bundle) else: self.opener = urllib.request.urlopen
Example #3
Source File: package_index.py From ironpython2 with Apache License 2.0 | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #4
Source File: package_index.py From lambda-packs with MIT License | 6 votes |
def _download_svn(self, url, filename): warnings.warn("SVN download support is deprecated", UserWarning) url = url.split('#', 1)[0] # remove any fragment for svn's sake creds = '' if url.lower().startswith('svn:') and '@' in url: scheme, netloc, path, p, q, f = urllib.parse.urlparse(url) if not netloc and path.startswith('//') and '/' in path[2:]: netloc, path = path[2:].split('/', 1) auth, host = urllib.parse.splituser(netloc) if auth: if ':' in auth: user, pw = auth.split(':', 1) creds = " --username=%s --password=%s" % (user, pw) else: creds = " --username=" + auth netloc = host parts = scheme, netloc, url, p, q, f url = urllib.parse.urlunparse(parts) self.info("Doing subversion checkout from %s to %s", url, filename) os.system("svn checkout%s -q %s %s" % (creds, url, filename)) return filename
Example #5
Source File: package_index.py From lambda-packs with MIT License | 6 votes |
def __init__( self, index_url="https://pypi.org/simple/", hosts=('*',), ca_bundle=None, verify_ssl=True, *args, **kw ): Environment.__init__(self, *args, **kw) self.index_url = index_url + "/" [:not index_url.endswith('/')] self.scanned_urls = {} self.fetched_urls = {} self.package_pages = {} self.allows = re.compile('|'.join(map(translate, hosts))).match self.to_scan = [] use_ssl = ( verify_ssl and ssl_support.is_available and (ca_bundle or ssl_support.find_ca_bundle()) ) if use_ssl: self.opener = ssl_support.opener_for(ca_bundle) else: self.opener = urllib.request.urlopen
Example #6
Source File: package_index.py From lambda-packs with MIT License | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #7
Source File: package_index.py From lambda-packs with MIT License | 6 votes |
def _encode_auth(auth): """ A function compatible with Python 2.3-3.3 that will encode auth from a URL suitable for an HTTP header. >>> str(_encode_auth('username%3Apassword')) 'dXNlcm5hbWU6cGFzc3dvcmQ=' Long auth strings should not cause a newline to be inserted. >>> long_auth = 'username:' + 'password'*10 >>> chr(10) in str(_encode_auth(long_auth)) False """ auth_s = urllib.parse.unquote(auth) # convert to bytes auth_bytes = auth_s.encode() encoded_bytes = base64.b64encode(auth_bytes) # convert back to a string encoded = encoded_bytes.decode() # strip the trailing carriage return return encoded.replace('\n', '')
Example #8
Source File: package_index.py From ironpython2 with Apache License 2.0 | 6 votes |
def _download_svn(self, url, filename): warnings.warn("SVN download support is deprecated", UserWarning) url = url.split('#', 1)[0] # remove any fragment for svn's sake creds = '' if url.lower().startswith('svn:') and '@' in url: scheme, netloc, path, p, q, f = urllib.parse.urlparse(url) if not netloc and path.startswith('//') and '/' in path[2:]: netloc, path = path[2:].split('/', 1) auth, host = _splituser(netloc) if auth: if ':' in auth: user, pw = auth.split(':', 1) creds = " --username=%s --password=%s" % (user, pw) else: creds = " --username=" + auth netloc = host parts = scheme, netloc, url, p, q, f url = urllib.parse.urlunparse(parts) self.info("Doing subversion checkout from %s to %s", url, filename) os.system("svn checkout%s -q %s %s" % (creds, url, filename)) return filename
Example #9
Source File: package_index.py From ironpython2 with Apache License 2.0 | 6 votes |
def _encode_auth(auth): """ A function compatible with Python 2.3-3.3 that will encode auth from a URL suitable for an HTTP header. >>> str(_encode_auth('username%3Apassword')) 'dXNlcm5hbWU6cGFzc3dvcmQ=' Long auth strings should not cause a newline to be inserted. >>> long_auth = 'username:' + 'password'*10 >>> chr(10) in str(_encode_auth(long_auth)) False """ auth_s = urllib.parse.unquote(auth) # convert to bytes auth_bytes = auth_s.encode() encoded_bytes = base64.b64encode(auth_bytes) # convert back to a string encoded = encoded_bytes.decode() # strip the trailing carriage return return encoded.replace('\n', '')
Example #10
Source File: package_index.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #11
Source File: package_index.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def __init__( self, index_url="https://pypi.org/simple/", hosts=('*',), ca_bundle=None, verify_ssl=True, *args, **kw ): Environment.__init__(self, *args, **kw) self.index_url = index_url + "/" [:not index_url.endswith('/')] self.scanned_urls = {} self.fetched_urls = {} self.package_pages = {} self.allows = re.compile('|'.join(map(translate, hosts))).match self.to_scan = [] use_ssl = ( verify_ssl and ssl_support.is_available and (ca_bundle or ssl_support.find_ca_bundle()) ) if use_ssl: self.opener = ssl_support.opener_for(ca_bundle) else: self.opener = urllib.request.urlopen
Example #12
Source File: package_index.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def _download_svn(self, url, filename): warnings.warn("SVN download support is deprecated", UserWarning) url = url.split('#', 1)[0] # remove any fragment for svn's sake creds = '' if url.lower().startswith('svn:') and '@' in url: scheme, netloc, path, p, q, f = urllib.parse.urlparse(url) if not netloc and path.startswith('//') and '/' in path[2:]: netloc, path = path[2:].split('/', 1) auth, host = _splituser(netloc) if auth: if ':' in auth: user, pw = auth.split(':', 1) creds = " --username=%s --password=%s" % (user, pw) else: creds = " --username=" + auth netloc = host parts = scheme, netloc, url, p, q, f url = urllib.parse.urlunparse(parts) self.info("Doing subversion checkout from %s to %s", url, filename) os.system("svn checkout%s -q %s %s" % (creds, url, filename)) return filename
Example #13
Source File: package_index.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def _encode_auth(auth): """ A function compatible with Python 2.3-3.3 that will encode auth from a URL suitable for an HTTP header. >>> str(_encode_auth('username%3Apassword')) 'dXNlcm5hbWU6cGFzc3dvcmQ=' Long auth strings should not cause a newline to be inserted. >>> long_auth = 'username:' + 'password'*10 >>> chr(10) in str(_encode_auth(long_auth)) False """ auth_s = urllib.parse.unquote(auth) # convert to bytes auth_bytes = auth_s.encode() encoded_bytes = base64.b64encode(auth_bytes) # convert back to a string encoded = encoded_bytes.decode() # strip the trailing carriage return return encoded.replace('\n', '')
Example #14
Source File: package_index.py From anpr with Creative Commons Attribution 4.0 International | 6 votes |
def _download_svn(self, url, filename): url = url.split('#', 1)[0] # remove any fragment for svn's sake creds = '' if url.lower().startswith('svn:') and '@' in url: scheme, netloc, path, p, q, f = urllib.parse.urlparse(url) if not netloc and path.startswith('//') and '/' in path[2:]: netloc, path = path[2:].split('/', 1) auth, host = urllib.parse.splituser(netloc) if auth: if ':' in auth: user, pw = auth.split(':', 1) creds = " --username=%s --password=%s" % (user, pw) else: creds = " --username=" + auth netloc = host parts = scheme, netloc, url, p, q, f url = urllib.parse.urlunparse(parts) self.info("Doing subversion checkout from %s to %s", url, filename) os.system("svn checkout%s -q %s %s" % (creds, url, filename)) return filename
Example #15
Source File: package_index.py From anpr with Creative Commons Attribution 4.0 International | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #16
Source File: package_index.py From GraphicDesignPatternByPython with MIT License | 6 votes |
def _encode_auth(auth): """ A function compatible with Python 2.3-3.3 that will encode auth from a URL suitable for an HTTP header. >>> str(_encode_auth('username%3Apassword')) 'dXNlcm5hbWU6cGFzc3dvcmQ=' Long auth strings should not cause a newline to be inserted. >>> long_auth = 'username:' + 'password'*10 >>> chr(10) in str(_encode_auth(long_auth)) False """ auth_s = urllib.parse.unquote(auth) # convert to bytes auth_bytes = auth_s.encode() # use the legacy interface for Python 2.3 support encoded_bytes = base64.encodestring(auth_bytes) # convert back to a string encoded = encoded_bytes.decode() # strip the trailing carriage return return encoded.replace('\n', '')
Example #17
Source File: package_index.py From GraphicDesignPatternByPython with MIT License | 6 votes |
def _download_svn(self, url, filename): url = url.split('#', 1)[0] # remove any fragment for svn's sake creds = '' if url.lower().startswith('svn:') and '@' in url: scheme, netloc, path, p, q, f = urllib.parse.urlparse(url) if not netloc and path.startswith('//') and '/' in path[2:]: netloc, path = path[2:].split('/', 1) auth, host = urllib.parse.splituser(netloc) if auth: if ':' in auth: user, pw = auth.split(':', 1) creds = " --username=%s --password=%s" % (user, pw) else: creds = " --username=" + auth netloc = host parts = scheme, netloc, url, p, q, f url = urllib.parse.urlunparse(parts) self.info("Doing subversion checkout from %s to %s", url, filename) os.system("svn checkout%s -q %s %s" % (creds, url, filename)) return filename
Example #18
Source File: package_index.py From GraphicDesignPatternByPython with MIT License | 6 votes |
def __init__( self, index_url="https://pypi.org/simple/", hosts=('*',), ca_bundle=None, verify_ssl=True, *args, **kw ): Environment.__init__(self, *args, **kw) self.index_url = index_url + "/" [:not index_url.endswith('/')] self.scanned_urls = {} self.fetched_urls = {} self.package_pages = {} self.allows = re.compile('|'.join(map(translate, hosts))).match self.to_scan = [] use_ssl = ( verify_ssl and ssl_support.is_available and (ca_bundle or ssl_support.find_ca_bundle()) ) if use_ssl: self.opener = ssl_support.opener_for(ca_bundle) else: self.opener = urllib.request.urlopen
Example #19
Source File: package_index.py From GraphicDesignPatternByPython with MIT License | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #20
Source File: package_index.py From deepWordBug with Apache License 2.0 | 6 votes |
def _encode_auth(auth): """ A function compatible with Python 2.3-3.3 that will encode auth from a URL suitable for an HTTP header. >>> str(_encode_auth('username%3Apassword')) 'dXNlcm5hbWU6cGFzc3dvcmQ=' Long auth strings should not cause a newline to be inserted. >>> long_auth = 'username:' + 'password'*10 >>> chr(10) in str(_encode_auth(long_auth)) False """ auth_s = urllib.parse.unquote(auth) # convert to bytes auth_bytes = auth_s.encode() encoded_bytes = base64.b64encode(auth_bytes) # convert back to a string encoded = encoded_bytes.decode() # strip the trailing carriage return return encoded.replace('\n', '')
Example #21
Source File: package_index.py From deepWordBug with Apache License 2.0 | 6 votes |
def _download_svn(self, url, filename): warnings.warn("SVN download support is deprecated", UserWarning) url = url.split('#', 1)[0] # remove any fragment for svn's sake creds = '' if url.lower().startswith('svn:') and '@' in url: scheme, netloc, path, p, q, f = urllib.parse.urlparse(url) if not netloc and path.startswith('//') and '/' in path[2:]: netloc, path = path[2:].split('/', 1) auth, host = _splituser(netloc) if auth: if ':' in auth: user, pw = auth.split(':', 1) creds = " --username=%s --password=%s" % (user, pw) else: creds = " --username=" + auth netloc = host parts = scheme, netloc, url, p, q, f url = urllib.parse.urlunparse(parts) self.info("Doing subversion checkout from %s to %s", url, filename) os.system("svn checkout%s -q %s %s" % (creds, url, filename)) return filename
Example #22
Source File: package_index.py From deepWordBug with Apache License 2.0 | 6 votes |
def __init__( self, index_url="https://pypi.org/simple/", hosts=('*',), ca_bundle=None, verify_ssl=True, *args, **kw ): Environment.__init__(self, *args, **kw) self.index_url = index_url + "/" [:not index_url.endswith('/')] self.scanned_urls = {} self.fetched_urls = {} self.package_pages = {} self.allows = re.compile('|'.join(map(translate, hosts))).match self.to_scan = [] use_ssl = ( verify_ssl and ssl_support.is_available and (ca_bundle or ssl_support.find_ca_bundle()) ) if use_ssl: self.opener = ssl_support.opener_for(ca_bundle) else: self.opener = urllib.request.urlopen
Example #23
Source File: package_index.py From deepWordBug with Apache License 2.0 | 6 votes |
def find_external_links(url, page): """Find rel="homepage" and rel="download" links in `page`, yielding URLs""" for match in REL.finditer(page): tag, rel = match.groups() rels = set(map(str.strip, rel.lower().split(','))) if 'homepage' in rels or 'download' in rels: for match in HREF.finditer(tag): yield urllib.parse.urljoin(url, htmldecode(match.group(1))) for tag in ("<th>Home Page", "<th>Download URL"): pos = page.find(tag) if pos != -1: match = HREF.search(page, pos) if match: yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
Example #24
Source File: package_index.py From anpr with Creative Commons Attribution 4.0 International | 6 votes |
def _encode_auth(auth): """ A function compatible with Python 2.3-3.3 that will encode auth from a URL suitable for an HTTP header. >>> str(_encode_auth('username%3Apassword')) 'dXNlcm5hbWU6cGFzc3dvcmQ=' Long auth strings should not cause a newline to be inserted. >>> long_auth = 'username:' + 'password'*10 >>> chr(10) in str(_encode_auth(long_auth)) False """ auth_s = urllib.parse.unquote(auth) # convert to bytes auth_bytes = auth_s.encode() # use the legacy interface for Python 2.3 support encoded_bytes = base64.encodestring(auth_bytes) # convert back to a string encoded = encoded_bytes.decode() # strip the trailing carriage return return encoded.replace('\n', '')
Example #25
Source File: package_index.py From anpr with Creative Commons Attribution 4.0 International | 6 votes |
def __init__( self, index_url="https://pypi.python.org/simple", hosts=('*',), ca_bundle=None, verify_ssl=True, *args, **kw ): Environment.__init__(self, *args, **kw) self.index_url = index_url + "/" [:not index_url.endswith('/')] self.scanned_urls = {} self.fetched_urls = {} self.package_pages = {} self.allows = re.compile('|'.join(map(translate, hosts))).match self.to_scan = [] use_ssl = ( verify_ssl and ssl_support.is_available and (ca_bundle or ssl_support.find_ca_bundle()) ) if use_ssl: self.opener = ssl_support.opener_for(ca_bundle) else: self.opener = urllib.request.urlopen
Example #26
Source File: package_index.py From deepWordBug with Apache License 2.0 | 5 votes |
def _download_url(self, scheme, url, tmpdir): # Determine download filename # name, fragment = egg_info_for_url(url) if name: while '..' in name: name = name.replace('..', '.').replace('\\', '_') else: name = "__downloaded__" # default if URL has no path contents if name.endswith('.egg.zip'): name = name[:-4] # strip the extra .zip before download filename = os.path.join(tmpdir, name) # Download the file # if scheme == 'svn' or scheme.startswith('svn+'): return self._download_svn(url, filename) elif scheme == 'git' or scheme.startswith('git+'): return self._download_git(url, filename) elif scheme.startswith('hg+'): return self._download_hg(url, filename) elif scheme == 'file': return urllib.request.url2pathname(urllib.parse.urlparse(url)[2]) else: self.url_ok(url, True) # raises error if not allowed return self._attempt_download(url, filename)
Example #27
Source File: package_index.py From deepWordBug with Apache License 2.0 | 5 votes |
def _download_to(self, url, filename): self.info("Downloading %s", url) # Download the file fp = None try: checker = HashChecker.from_url(url) fp = self.open_url(url) if isinstance(fp, urllib.error.HTTPError): raise DistutilsError( "Can't download %s: %s %s" % (url, fp.code, fp.msg) ) headers = fp.info() blocknum = 0 bs = self.dl_blocksize size = -1 if "content-length" in headers: # Some servers return multiple Content-Length headers :( sizes = get_all_headers(headers, 'Content-Length') size = max(map(int, sizes)) self.reporthook(url, filename, blocknum, bs, size) with open(filename, 'wb') as tfp: while True: block = fp.read(bs) if block: checker.feed(block) tfp.write(block) blocknum += 1 self.reporthook(url, filename, blocknum, bs, size) else: break self.check_hash(checker, filename, tfp) return headers finally: if fp: fp.close()
Example #28
Source File: package_index.py From deepWordBug with Apache License 2.0 | 5 votes |
def open_url(self, url, warning=None): if url.startswith('file:'): return local_open(url) try: return open_with_auth(url, self.opener) except (ValueError, http_client.InvalidURL) as v: msg = ' '.join([str(arg) for arg in v.args]) if warning: self.warn(warning, msg) else: raise DistutilsError('%s %s' % (url, msg)) except urllib.error.HTTPError as v: return v except urllib.error.URLError as v: if warning: self.warn(warning, v.reason) else: raise DistutilsError("Download error for %s: %s" % (url, v.reason)) except http_client.BadStatusLine as v: if warning: self.warn(warning, v.line) else: raise DistutilsError( '%s returned a bad status line. The server might be ' 'down, %s' % (url, v.line) ) except (http_client.HTTPException, socket.error) as v: if warning: self.warn(warning, v) else: raise DistutilsError("Download error for %s: %s" % (url, v))
Example #29
Source File: package_index.py From lambda-packs with MIT License | 5 votes |
def _download_url(self, scheme, url, tmpdir): # Determine download filename # name, fragment = egg_info_for_url(url) if name: while '..' in name: name = name.replace('..', '.').replace('\\', '_') else: name = "__downloaded__" # default if URL has no path contents if name.endswith('.egg.zip'): name = name[:-4] # strip the extra .zip before download filename = os.path.join(tmpdir, name) # Download the file # if scheme == 'svn' or scheme.startswith('svn+'): return self._download_svn(url, filename) elif scheme == 'git' or scheme.startswith('git+'): return self._download_git(url, filename) elif scheme.startswith('hg+'): return self._download_hg(url, filename) elif scheme == 'file': return urllib.request.url2pathname(urllib.parse.urlparse(url)[2]) else: self.url_ok(url, True) # raises error if not allowed return self._attempt_download(url, filename)
Example #30
Source File: package_index.py From lambda-packs with MIT License | 5 votes |
def open_url(self, url, warning=None): if url.startswith('file:'): return local_open(url) try: return open_with_auth(url, self.opener) except (ValueError, http_client.InvalidURL) as v: msg = ' '.join([str(arg) for arg in v.args]) if warning: self.warn(warning, msg) else: raise DistutilsError('%s %s' % (url, msg)) except urllib.error.HTTPError as v: return v except urllib.error.URLError as v: if warning: self.warn(warning, v.reason) else: raise DistutilsError("Download error for %s: %s" % (url, v.reason)) except http_client.BadStatusLine as v: if warning: self.warn(warning, v.line) else: raise DistutilsError( '%s returned a bad status line. The server might be ' 'down, %s' % (url, v.line) ) except (http_client.HTTPException, socket.error) as v: if warning: self.warn(warning, v) else: raise DistutilsError("Download error for %s: %s" % (url, v))