Python urlparse.unquote函数代码示例

def _parse_qs(qs):
    pairs = (s2 for s1 in qs.split('&') for s2 in s1.split(';'))
    retval = odict()

    for name_value in pairs:
        if name_value is None or len(name_value) == 0:
            continue
        nv = name_value.split('=', 1)

        if len(nv) != 2:
            # Handle case of a control-name with no equal sign
            nv.append(None)

        name = unquote(nv[0].replace('+', ' '))

        value = None
        if nv[1] is not None:
            value = unquote(nv[1].replace('+', ' '))

        l = retval.get(name, None)
        if l is None:
            l = retval[name] = []
        l.append(value)

    return retval

def db_url_parse(url, engine=None, conn_max_age=0):
    """
    Parses a database URL.
    """
    if url == "sqlite://:memory:":
        # urlparse will choke on :memory:
        return {
            "ENGINE": DATABASE_ENGINE_SCHEMES["sqlite"],
            "NAME": ":memory:",
        }

    config = {}
    url = urlparse.urlparse(url)

    # split query strings from path
    path = url.path[1:]
    if "?" in path and not url.query:
        path, query = path.split("?", 2)
    else:
        path, query = path, url.query
    query = urlparse.parse_qs(query)

    # sqlite with no path should assume :memory: (sqlalchemy behavior)
    if url.scheme == "sqlite" and path == "":
        path = ":memory:"

    # handle postgresql percent-encoded paths
    hostname = url.hostname or ""
    if "%2f" in hostname.lower():
        hostname = hostname.replace("%2f", "/").replace("%2F", "/")

    config.update({
        "NAME": urlparse.unquote(path or ""),
        "USER": urlparse.unquote(url.username or ""),
        "PASSWORD": urlparse.unquote(url.password or ""),
        "HOST": hostname,
        "PORT": url.port or "",
        "CONN_MAX_AGE": conn_max_age,
    })

    engine = DATABASE_ENGINE_SCHEMES[url.scheme] if engine is None else engine

    # pass the query string into OPTIONS
    options = {}
    for key, values in query.items():
        if url.scheme == "mysql" and key == "ssl-ca":
            options["ssl"] = {"ca": values[-1]}
            continue
        options[key] = values[-1]

    # postgresql schema URLs
    if "currentSchema" in options and engine == "django.db.backends.postgresql_psycopg2":
        options["options"] = "-c search_path={0}".format(options["currentSchema"])

    if options:
        config["OPTIONS"] = options
    if engine:
        config["ENGINE"] = engine

    return config

 def get(self, moduleID, title, institution, teachDate, instructors, description):
     account = get_account()
     if account:
         newCourse = dict()
         newCourse["CourseURL"] = urlparse.unquote(
             self.request.get('courseURL'))
         newCourse["Title"] = title
         newCourse["Institution"] = institution
         newCourse["TeachingDate"] = teachDate
         newCourse["Instructors"] = instructors
         newCourse["Description"] = description
         newCourse["DownloadPageLink"] = urlparse.unquote(
             self.request.get('materials'))
         newCourse["scoreRanking"] = 1
         moduleID = int(moduleID)
         match = Module.query(Module.category == moduleID).fetch()
         match = match[0]
         moduleCourses = match.courses
         newCourse['ID'] = len(moduleCourses)
         moduleCourses.append(newCourse)
         match.courses = moduleCourses
         match.courses = sorted(
             match.courses, key=lambda k: k['scoreRanking'], reverse=True)
         match.put()
         response = {'success': 'Course submitted successfully.'}
     else:
         response = {'error': 'You are not logged in. '}
     self.response.headers['Content-Type'] = 'application/json'
     self.response.write(json.dumps(response))

def parse_url(url):
    port = path = auth = userid = password = None
    # parse with HTTP URL semantics
    scheme = urlparse(url).scheme
    parts = urlparse(url.replace("%s://" % (scheme, ), "http://"))

    # The first pymongo.Connection() argument (host) can be
    # a mongodb connection URI. If this is the case, don't
    # use port but let pymongo get the port(s) from the URI instead.
    # This enables the use of replica sets and sharding.
    # See pymongo.Connection() for more info.
    if scheme == 'mongodb':
        # strip the scheme since it is appended automatically.
        hostname = url[len('mongodb://'):]
    else:
        netloc = parts.netloc
        if '@' in netloc:
            auth, _, netloc = parts.netloc.partition('@')
            userid, _, password = auth.partition(':')
        hostname, _, port = netloc.partition(':')
        path = parts.path or ""
        if path and path[0] == '/':
            path = path[1:]
        port = port and int(port) or port

    return dict({"hostname": unquote(hostname or "") or None,
                 "port": port or None,
                 "userid": unquote(userid or "") or None,
                 "password": unquote(password or "") or None,
                 "transport": scheme,
                 "virtual_host": unquote(path or "") or None},
                **kwdict(dict(parse_qsl(parts.query))))

    def __init__(self, parsed_url):
        super(S3Source, self).__init__(parsed_url)
        self.acccess_key_id = urlparse.unquote(parsed_url.username)
        self.secret_access_key = urlparse.unquote(parsed_url.password)

        self.conn = boto.connect_s3(self.acccess_key_id, self.secret_access_key)
        self.bucket_name = parsed_url.hostname
        self.bucket = self.conn.get_bucket(self.bucket_name, validate=False)

	def getSongs(self):
		format = "%Y-%m-%d %H:%M:%S"
		for trackid,attributes in self.il['Tracks'].iteritems():
			s = Song()
			s.name = attributes.get('Name')
			s.artist = attributes.get('Artist')
			s.album_artist = attributes.get('Album Artist')
			s.composer = attributes.get('Composer')
			s.album = attributes.get('Album')
			s.genre = attributes.get('Genre')
			s.kind = attributes.get('Kind')
			if attributes.get('Size'):
				s.size = int(attributes.get('Size'))
			s.total_time = attributes.get('Total Time')
			s.track_number = attributes.get('Track Number')
			if attributes.get('Track Count'):
				s.track_count = int(attributes.get('Track Count'))
			if attributes.get('Disc Number'):
				s.disc_number = int(attributes.get('Disc Number'))
			if attributes.get('Disc Count'):
				s.disc_count = int(attributes.get('Disc Count'))
			if attributes.get('Year'):
				s.year = int(attributes.get('Year'))
			if attributes.get('Date Modified'):
				s.date_modified = time.strptime(str(attributes.get('Date Modified')),format)
			if attributes.get('Date Added'):
				s.date_added = time.strptime(str(attributes.get('Date Added')),format)
			if attributes.get('Bit Rate'):
				s.bit_rate = int(attributes.get('Bit Rate'))
			if attributes.get('Sample Rate'):
				s.sample_rate = int(attributes.get('Sample Rate'))
			s.comments = attributes.get("Comments	")
			if attributes.get('Rating'):
				s.rating = int(attributes.get('Rating'))
			if attributes.get('Play Count'):
				s.play_count = int(attributes.get('Play Count'))
			if attributes.get('Location'):
				if ( self.musicPathXML is None or self.musicPathSystem is None ):
					s.location = unicode(urlparse.unquote(urlparse.urlparse(attributes.get('Location')).path[1:]),"utf8")
				else:
					s.location = unicode(urlparse.unquote(urlparse.urlparse(attributes.get('Location')).path[1:]).replace(self.musicPathXML,self.musicPathSystem),"utf8")
			s.compilation = 'Compilation' in attributes
			if attributes.get('Play Date UTC'):
				s.lastplayed = time.strptime(str(attributes.get('Play Date UTC')),format)
			if attributes.get('Total Time'):
				s.length = int(attributes.get('Total Time'))
			if attributes.get('Grouping'):
				s.grouping = attributes.get('Grouping')
			if self.filesOnly==True and attributes.get('Track Type') == 'File':
				if self.legacymode:
					self.songs.append(s)
				else:
					self.songs[int(trackid)] = s
			elif self.filesOnly==False:
				if self.legacymode:
					self.songs.append(s)
				else:
					self.songs[int(trackid)] = s

def internalapi_testcaps(args):
    indexer = urlparse.unquote(args["indexer"])
    apikey = args["apikey"]
    host = urlparse.unquote(args["host"])
    logger.debug("Check caps for %s" % indexer)

    try:
        result = check_caps(host, apikey)

        return jsonify({"success": True, "result": result})
    except IndexerResultParsingException as e:
        return jsonify({"success": False, "message": e.message})

def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):
    """This was a slightly modified version of the function with the same name
    that is defined in urlparse.py . I modified it, and then reverted the patch
    to have different handling of '+':

    -        name = unquote(nv[0].replace('+', ' '))
    -        value = unquote(nv[1].replace('+', ' '))
    +        name = unquote(nv[0])
    +        value = unquote(nv[1])

    Due to this [0] bug: "Proxy (and maybe others) affected by querystring +
    not being decoded by URL class #9139", I reverted my changes to the function
    but kept it here for better docs.

    [0] https://github.com/andresriancho/w3af/issues/9139

    Arguments:

    qs: percent-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in
        percent-encoded queries should be treated as blank strings.  A
        true value indicates that blanks should be retained as blank
        strings.  The default false value indicates that blank values
        are to be ignored and treated as if they were  not included.

    strict_parsing: flag indicating what to do with parsing errors. If
        false (the default), errors are silently ignored. If true,
        errors raise a ValueError exception.

    Returns a list, as G-d intended.
    """
    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
    r = []
    for name_value in pairs:
        if not name_value and not strict_parsing:
            continue
        nv = name_value.split('=', 1)
        if len(nv) != 2:
            if strict_parsing:
                raise ValueError("bad query field: %r" % name_value)
            # Handle case of a control-name with no equal sign
            if keep_blank_values:
                nv.append('')
            else:
                continue
        if len(nv[1]) or keep_blank_values:
            name = urlparse.unquote(nv[0].replace('+', ' '))
            value = urlparse.unquote(nv[1].replace('+', ' '))
            r.append((name, value))

    return r

def compare_urls(url_a, url_b):
    if url_a.netloc != url_b.netloc or url_a.query != url_b.query:
        return False

    # remove / from the end of the url if required
    path_a = url_a.path[:-1]\
        if url_a.path.endswith('/')\
        else url_a.path
    path_b = url_b.path[:-1]\
        if url_b.path.endswith('/')\
        else url_b.path

    return unquote(path_a) == unquote(path_b)

def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):
    """This is a slightly modified version of the function with the same name
    that is defined in urlparse.py . I had to modify it in order to have
    '+' handled in the way w3af needed it. Note that the only change is:

    -        name = unquote(nv[0].replace('+', ' '))
    -        value = unquote(nv[1].replace('+', ' '))
    +        name = unquote(nv[0])
    +        value = unquote(nv[1])

    In other words, keep those + !

    Parse a query given as a string argument.

    Arguments:

    qs: percent-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in
        percent-encoded queries should be treated as blank strings.  A
        true value indicates that blanks should be retained as blank
        strings.  The default false value indicates that blank values
        are to be ignored and treated as if they were  not included.

    strict_parsing: flag indicating what to do with parsing errors. If
        false (the default), errors are silently ignored. If true,
        errors raise a ValueError exception.

    Returns a list, as G-d intended.
    """
    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
    r = []
    for name_value in pairs:
        if not name_value and not strict_parsing:
            continue
        nv = name_value.split('=', 1)
        if len(nv) != 2:
            if strict_parsing:
                raise ValueError, "bad query field: %r" % (name_value,)
            # Handle case of a control-name with no equal sign
            if keep_blank_values:
                nv.append('')
            else:
                continue
        if len(nv[1]) or keep_blank_values:
            name = urlparse.unquote(nv[0])
            value = urlparse.unquote(nv[1])
            r.append((name, value))

    return r

    def handle(self, *args, **options):
    	for templatename in args:
#	    if templatename[0:1] == 't':
 		print templatename
		f = open(templatename, "r")
		lines = f.readlines()
		f.close()
#		print lines
		attribs = []
		for line in lines:
			currentattrib = line.split('=',1)
			attribs.append(currentattrib)
			print currentattrib[0]
			print urlparse.unquote(currentattrib[1]).strip()

def internalapi_testcaps(args):
    indexer = urlparse.unquote(args["indexer"])
    apikey = args["apikey"]
    host = urlparse.unquote(args["host"])
    logger.debug("Check caps for %s" % indexer)

    try:
        ids, types = check_caps(host, apikey)
        ids = sorted(list(ids))
        types = sorted(list(types))

        return jsonify({"success": True, "ids": ids, "types": types})
    except IndexerResultParsingException as e:
        return jsonify({"success": False, "message": e.message})

 def download_request(self, request, spider):
     p = urlparse_cached(request)
     scheme = 'https' if request.meta.get('is_secure') else 'http'
     bucket = p.hostname
     path = p.path + '?' + p.query if p.query else p.path
     url = '%s://%s.s3.amazonaws.com%s' % (scheme, bucket, path)
     signed_headers = self.conn.make_request(
             method=request.method,
             bucket=bucket,
             key=unquote(p.path),
             query_args=unquote(p.query),
             headers=request.headers,
             data=request.body)
     httpreq = request.replace(url=url, headers=signed_headers)
     return self._download_http(httpreq, spider)

    def do_GET(self):
        """Respond to GET requests"""

        from urlparse import unquote

        path, headers, data = self._ParseBaseRequest('GET')
        if None is path: return

        if ('mpd' == path[0]) and (2 == len(path)):
            self._AlterMPD(unquote(path[1]), headers, data)
        elif ('subtitles' == path[0]) and (3 == len(path)):
            self._TranscodeSubtitle(unquote(path[1]), headers, data, path[2])
        else:
            Log('[PS] Invalid request received', Log.DEBUG)
            self.send_error(501, 'Invalid request')

def score_results(results):
    flat_res = filter(
        None, chain.from_iterable(izip_longest(*results.values())))
    flat_len = len(flat_res)
    engines_len = len(results)
    results = []
    # deduplication + scoring
    for i, res in enumerate(flat_res):

        res['parsed_url'] = urlparse(res['url'])

        res['host'] = res['parsed_url'].netloc

        if res['host'].startswith('www.'):
            res['host'] = res['host'].replace('www.', '', 1)

        res['engines'] = [res['engine']]
        weight = 1.0

        if hasattr(engines[res['engine']], 'weight'):
            weight = float(engines[res['engine']].weight)

        score = int((flat_len - i) / engines_len) * weight + 1
        duplicated = False

        for new_res in results:
            p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path  # noqa
            p2 = new_res['parsed_url'].path[:-1] if new_res['parsed_url'].path.endswith('/') else new_res['parsed_url'].path  # noqa
            if res['host'] == new_res['host'] and\
               unquote(p1) == unquote(p2) and\
               res['parsed_url'].query == new_res['parsed_url'].query and\
               res.get('template') == new_res.get('template'):
                duplicated = new_res
                break
        if duplicated:
            if res.get('content') > duplicated.get('content'):
                duplicated['content'] = res['content']
            duplicated['score'] += score
            duplicated['engines'].append(res['engine'])
            if duplicated['parsed_url'].scheme == 'https':
                continue
            elif res['parsed_url'].scheme == 'https':
                duplicated['url'] = res['parsed_url'].geturl()
                duplicated['parsed_url'] = res['parsed_url']
        else:
            res['score'] = score
            results.append(res)
    return sorted(results, key=itemgetter('score'), reverse=True)