Python URL.path_segments方法代码示例

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
class Segments(object):
    def __init__(self, base, path, segments, defaults):
        self.base = PURL(base, path=path)
        self.segments = OrderedDict(zip(segments, defaults))

    def build(self):
        segments = self.base.path_segments() + tuple(self.segments.values())
        url = self.base.path_segments(segments)
        return url

    def __str__(self):
        return self.build().as_string()

    def _get_segment(self, segment):
        return self.segments[segment]

    def _set_segment(self, segment, value):
        self.segments[segment] = value

    @classmethod
    def _segment(cls, segment):
        return property(
                fget=lambda x: cls._get_segment(x, segment),
                fset=lambda x, v: cls._set_segment(x, segment, v),
                )

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
    def info(self, url):
        """Interface method to be called when processing new images.

        This method ties together the DataProvider workflow.
        """
        url = URL(url)
        return self.postprocess(
            self.info_for_id(self.id_from_url(url, url.host(), url.path_segments())))

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
def cached_path(args, url, rel):
    if url.startswith('/'):
        return url
    url_ = URL(url)
    cached = args.data_file('edmond', url_.path_segments()[-1])
    if not cached.exists():
        fname, headers = urlretrieve(url, '%s' % cached)
    return str(cached)

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
class Segments(object):
    """
    URL segment handler, not intended for direct use. The URL is constructed by
    joining base, path and segments.
    """
    def __init__(self, base, path, segments, defaults):
        # Preserve the base URL
        self.base = PURL(base, path=path)
        # Map the segments and defaults lists to an ordered dict
        self.segments = OrderedDict(zip(segments, defaults))

    def build(self):
        # Join base segments and segments
        segments = self.base.path_segments() + tuple(self.segments.values())

        # Create a new URL with the segments replaced
        url = self.base.path_segments(segments)
        return url

    def full_path(self):
        full_path = self.build().as_string()
        full_path = full_path.replace(self.base.host(), '')
        full_path = full_path.replace(self.base.scheme(), '')
        return full_path[4:]

    def __str__(self):
        return self.build().as_string()

    def _get_segment(self, segment):
        return self.segments[segment]

    def _set_segment(self, segment, value):
        self.segments[segment] = value

    @classmethod
    def _segment(cls, segment):
        """
        Returns a property capable of setting and getting a segment.
        """
        return property(
            fget=lambda x: cls._get_segment(x, segment),
            fset=lambda x, v: cls._set_segment(x, segment, v),
        )

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
def get_links(instr):
    """
    Given a link-value, generate individual links as dict.
    """
    if instr:
        for link in [h.strip() for h in link_splitter.findall(instr)]:
            url, params = link.split(">", 1)
            url = URL(url[1:])
            fname = url.path_segments()[-1] if url.path_segments() else ''
            info = {
                'url': url.as_string(),
                'ext': fname.split('.', 1)[1] if '.' in fname else None,
                'rel': 'related',
                'type': 'application/octet-stream'}
            for param in _splitstring(params, PARAMETER, "\s*;\s*"):
                try:
                    a, v = param.split("=", 1)
                    info[a.lower()] = _unquotestring(v)
                except ValueError:  # pragma: no cover
                    info[param.lower()] = None
            yield info

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
 def get(self, url, **kw):
     url = URL(url)
     content = get_resource(
         url.path_segment(-1) if url.path_segments() else 'dataset', self.prefix)
     if content:
         return MagicMock(
             mimetype='application/rdf+xml',
             content=content,
             links=[dict(
                 url='{0}.html'.format(url.as_string),
                 ext='.html',
                 rel='alternate',
                 type='text/html')],
             canonical_url=url.as_string())

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
    def __call__(self, index, row):
        if index == 0:
            self.cols = {col: i for i, col in enumerate(row)}
            return row

        url = URL(row[self.cols['src']])
        try:
            for filename in url.path_segments():
                if filename in self.md:
                    if self.md[filename].get('source_url'):
                        row[self.cols['source']] = self.md[filename]['source_url']
                        self.count += 1
                        break
        except IndexError:
            pass
        return row

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
 def url_parts(self, url):
     url = URL(url)
     return url, url.host(), url.path_segments()

# 需要导入模块: from purl import URL [as 别名]
# 或者: from purl.URL import path_segments [as 别名]
def get_image_info(img):
    for field in ['source', 'source_url', 'id']:
        for provider in PROVIDERS:
            url = URL(img[field])
            if provider.id_from_url(url, url.host(), url.path_segments()):
                return provider.info(img[field])