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)))
python类parse()的实例源码
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#', 1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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', '')
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)))
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#', 1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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', '')
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)))
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 = 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
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#', 1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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', '')
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)))
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 = 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
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#',1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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','')
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)))
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 = 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
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#', 1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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', '')
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)))
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 = 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
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#',1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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','')
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)))
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 = 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
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#', 1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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', '')
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)))
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 = 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
def _vcs_split_rev_from_url(url, pop_prefix=False):
scheme, netloc, path, query, frag = urllib.parse.urlsplit(url)
scheme = scheme.split('+', 1)[-1]
# Some fragment identification fails
path = path.split('#', 1)[0]
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
# Also, discard fragment
url = urllib.parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
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)))
