def open_local_file(self, url):
import mimetypes, mimetools, email.utils
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
host, file = splithost(url)
localname = url2pathname(file)
try:
stats = os.stat(localname)
except OSError as e:
raise IOError(e.errno, e.strerror, e.filename)
size = stats.st_size
modified = email.utils.formatdate(stats.st_mtime, usegmt=True)
mtype = mimetypes.guess_type(url)[0]
headers = mimetools.Message(StringIO('Content-Type: %s\nContent-Length: %d\nLast-modified: %s\n' % (mtype or 'text/plain', size, modified)))
if not host:
urlfile = file
if file[:1] == '/':
urlfile = 'file://' + file
return addinfourl(open(localname, 'rb'), headers, urlfile)
host, port = splitport(host)
if not port and socket.gethostbyname(host) in (localhost(), thishost()):
urlfile = file
if file[:1] == '/':
urlfile = 'file://' + file
return addinfourl(open(localname, 'rb'), headers, urlfile)
raise IOError, ('local file error', 'not on local host')
def _parse_image(self, element):
image_path = element.attrib['src']
image_path = nturl2path.url2pathname(image_path)
name = ''
# Find caption text
found_prev = self._find_prev_caption_text(element)
if found_prev['found']:
name = found_prev['prev'].text
else:
found_next = self._find_next_caption_text(element)
if found_next['found']:
name = found_next['next'].text
if name != '':
new_path = '{}.jpg'.format(
re.sub(r'(?:[^a-zä-ö0-9]|(?<=[\'"])s)',
r'',
name,
flags=re.IGNORECASE))
file_prefix = os.path.basename(
os.path.splitext(self._save_path)[0])
new_path = os.path.join('{}_images'.format(file_prefix), new_path)
self._copy_rename_image_files(new_path, image_path)
self._images.append({
'name': self._convert_image_name(name),
'image': new_path
})
def retrieve(self, url, filename = None, reporthook = None, data = None):
url = unwrap(toBytes(url))
if self.tempcache and url in self.tempcache:
return self.tempcache[url]
type, url1 = splittype(url)
if filename is None and (not type or type == 'file'):
try:
fp = self.open_local_file(url1)
hdrs = fp.info()
fp.close()
return (url2pathname(splithost(url1)[1]), hdrs)
except IOError:
pass
fp = self.open(url, data)
try:
headers = fp.info()
if filename:
tfp = open(filename, 'wb')
else:
import tempfile
garbage, path = splittype(url)
garbage, path = splithost(path or '')
path, garbage = splitquery(path or '')
path, garbage = splitattr(path or '')
suffix = os.path.splitext(path)[1]
fd, filename = tempfile.mkstemp(suffix)
self.__tempfiles.append(filename)
tfp = os.fdopen(fd, 'wb')
try:
result = (filename, headers)
if self.tempcache is not None:
self.tempcache[url] = result
bs = 8192
size = -1
read = 0
blocknum = 0
if reporthook:
if 'content-length' in headers:
size = int(headers['Content-Length'])
reporthook(blocknum, bs, size)
while 1:
block = fp.read(bs)
if block == '':
break
read += len(block)
tfp.write(block)
blocknum += 1
if reporthook:
reporthook(blocknum, bs, size)
finally:
tfp.close()
finally:
fp.close()
if size >= 0 and read < size:
raise ContentTooShortError('retrieval incomplete: got only %i out of %i bytes' % (read, size), result)
return result
def open_local_file(self, url):
import mimetypes, mimetools, email.utils
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
host, file = splithost(url)
localname = url2pathname(file)
try:
stats = os.stat(localname)
except OSError as e:
raise IOError(e.errno, e.strerror, e.filename)
size = stats.st_size
modified = email.utils.formatdate(stats.st_mtime, usegmt=True)
mtype = mimetypes.guess_type(url)[0]
headers = mimetools.Message(
StringIO(
'Content-Type: %s\nContent-Length: %d\nLast-modified: %s\n' %
(mtype or 'text/plain', size, modified)))
if not host:
urlfile = file
if file[:1] == '/':
urlfile = 'file://' + file
return addinfourl(open(localname, 'rb'), headers, urlfile)
host, port = splitport(host)
if not port and socket.gethostbyname(host) in (localhost(),
thishost()):
urlfile = file
if file[:1] == '/':
urlfile = 'file://' + file
return addinfourl(open(localname, 'rb'), headers, urlfile)
raise IOError, ('local file error', 'not on local host')
def OnLinkClicked(self, linkinfo):
href = linkinfo.GetHref().split('.html')
if len(href) == 1:
anchor = href[0]
if anchor == '.':
self.index()
elif anchor[:5] == 'file:':
self.open(nturl2path.url2pathname(anchor[5:]))
else:
self.loadDoc(self.moduleName, anchor)
elif len(href) == 2:
moduleName, anchor = href
self.loadDoc(moduleName, anchor)
def OnLinkClicked(self, linkinfo):
href = linkinfo.GetHref().split('.html')
if len(href)==1:
anchor = href[0]
if anchor == '.':
self.index()
elif anchor[:5]== 'file:':
self.open(nturl2path.url2pathname(anchor[5:]))
else:
self.loadDoc(self.moduleName,anchor)
elif len(href)==2:
moduleName, anchor = href
self.loadDoc(moduleName,anchor)
import nturl2path file = r"c:\my\little\pony" print(nturl2path.pathname2url(file)) print(nturl2path.url2pathname(nturl2path.pathname2url(file))) ## ///C|/my/little/pony ## C:\my\little\pony
import nturl2path file = r"c:\my\little\pony" print nturl2path.pathname2url(file) print nturl2path.url2pathname(nturl2path.pathname2url(file)) ## ///C|/my/little/pony ## C:\my\little\pony
def retrieve(self, url, filename=None, reporthook=None, data=None):
url = unwrap(toBytes(url))
if self.tempcache and url in self.tempcache:
return self.tempcache[url]
else:
type, url1 = splittype(url)
if filename is None and (not type or type == 'file'):
try:
fp = self.open_local_file(url1)
hdrs = fp.info()
fp.close()
return (url2pathname(splithost(url1)[1]), hdrs)
except IOError:
pass
fp = self.open(url, data)
try:
headers = fp.info()
if filename:
tfp = open(filename, 'wb')
else:
import tempfile
garbage, path = splittype(url)
garbage, path = splithost(path or '')
path, garbage = splitquery(path or '')
path, garbage = splitattr(path or '')
suffix = os.path.splitext(path)[1]
fd, filename = tempfile.mkstemp(suffix)
self.__tempfiles.append(filename)
tfp = os.fdopen(fd, 'wb')
try:
result = (filename, headers)
if self.tempcache is not None:
self.tempcache[url] = result
bs = 8192
size = -1
read = 0
blocknum = 0
if 'content-length' in headers:
size = int(headers['Content-Length'])
if reporthook:
reporthook(blocknum, bs, size)
while 1:
block = fp.read(bs)
if block == '':
break
read += len(block)
tfp.write(block)
blocknum += 1
if reporthook:
reporthook(blocknum, bs, size)
finally:
tfp.close()
finally:
fp.close()
if size >= 0 and read < size:
raise ContentTooShortError(
'retrieval incomplete: got only %i out of %i bytes' %
(read, size), result)
return result
def update_event(self, inp=-1):
self.set_output_val(0, nturl2path.url2pathname(self.input(0)))
