# urlimport.py

import sys
import importlib.abc
import imp
from urllib.request import urlopen
from urllib.error import HTTPError, URLError
from html.parser import HTMLParser

# Отладка
import logging

log = logging.getLogger(__name__)


# Получение ссылок из переданного URL
def _get_links(url):
    class LinkParser(HTMLParser):
        def handle_starttag(self, tag, attrs):
            if tag == 'a':
                attrs = dict(attrs)
                links.add(attrs.get('href').rstrip('/'))

    links = set()
    try:
        log.debug('Getting links from %s' % url)
        u = urlopen(url)
        parser = LinkParser()
        parser.feed(u.read().decode('utf-8'))
    except Exception as e:
        log.debug('Could not get links. %s', e)
    log.debug('links: %r', links)
    return links


class UrlMetaFinder(importlib.abc.MetaPathFinder):
    def __init__(self, baseurl):
        self._baseurl = baseurl
        self._links = {}
        self._loaders = {baseurl: UrlModuleLoader(baseurl)}

    def find_module(self, fullname, path=None):
        log.debug('find_module: fullname=%r, path=%r', fullname, path)
        if path is None:
            baseurl = self._baseurl
        else:
            if not path[0].startswith(self._baseurl):
                return None
            baseurl = path[0]

        parts = fullname.split('.')
        basename = parts[-1]
        log.debug('find_module: baseurl=%r, basename=%r', baseurl, basename)

        # Проверка кеша ссылок
        if basename not in self._links:
            self._links[baseurl] = _get_links(baseurl)

        # Проверка того, что это не пакет
        if basename in self._links[baseurl]:
            log.debug('find_module: trying package %r', fullname)
            fullurl = self._baseurl + '/' + basename
            # Попытка загрузить пакет (которая обращается к __init__.py)
            loader = UrlPackageLoader(fullurl)
            try:
                loader.load_module(fullname)
                self._links[fullurl] = _get_links(fullurl)
                self._loaders[fullurl] = UrlModuleLoader(fullurl)
                log.debug('find_module: package %r loaded', fullname)
            except ImportError as e:
                log.debug('find_module: package failed. %s', e)
                loader = None
            return loader

        # Обычный модуль
        filename = basename + '.py'
        if filename in self._links[baseurl]:
            log.debug('find_module: module %r found', fullname)
            return self._loaders[baseurl]
        else:
            log.debug('find_module: module %r not found', fullname)
            return None

    def invalidate_caches(self):
        log.debug('invalidating link cache')
        self._links.clear()


# Загрузчик модуля из URL
class UrlModuleLoader(importlib.abc.SourceLoader):
    def __init__(self, baseurl):
        self._baseurl = baseurl
        self._source_cache = {}

    def module_repr(self, module):
        return '<urlmodule %r from %r>' % (module.__name__, module.__file__)

    # Требуемый метод
    def load_module(self, fullname):
        code = self.get_code(fullname)
        mod = sys.modules.setdefault(fullname, imp.new_module(fullname))
        mod.__file__ = self.get_filename(fullname)
        mod.__loader__ = self
        mod.__package__ = fullname.rpartition('.')[0]
        exec(code, mod.__dict__)
        return mod

    # Необязательные расширения
    def get_code(self, fullname):
        src = self.get_source(fullname)
        return compile(src, self.get_filename(fullname), 'exec')

    def get_data(self, path):
        pass

    def get_filename(self, fullname):
        return self._baseurl + '/' + fullname.split('.')[-1] + '.py'

    def get_source(self, fullname):
        filename = self.get_filename(fullname)
        log.debug('loader: reading %r', filename)
        if filename in self._source_cache:
            log.debug('loader: cached %r', filename)
            return self._source_cache[filename]
        try:
            u = urlopen(filename)
            source = u.read().decode('utf-8')
            log.debug('loader: %r loaded', filename)
            self._source_cache[filename] = source
            return source
        except (HTTPError, URLError) as e:
            log.debug('loader: %r failed.  %s', filename, e)
            raise ImportError("Can't load %s" % filename)

    def is_package(self, fullname):
        return False


# Загрузчик пакета из URL
class UrlPackageLoader(UrlModuleLoader):
    def load_module(self, fullname):
        mod = super().load_module(fullname)
        mod.__path__ = [self._baseurl]
        mod.__package__ = fullname

    def get_filename(self, fullname):
        return self._baseurl + '/' + '__init__.py'

    def is_package(self, fullname):
        return True


# Вспомогательные функции для инсталляции/деинсталляции загрузчика
_installed_meta_cache = {}


def install_meta(address):
    if address not in _installed_meta_cache:
        finder = UrlMetaFinder(address)
        _installed_meta_cache[address] = finder
        sys.meta_path.append(finder)
        log.debug('%r installed on sys.meta_path', finder)


def remove_meta(address):
    if address in _installed_meta_cache:
        finder = _installed_meta_cache.pop(address)
        sys.meta_path.remove(finder)
        log.debug('%r removed from sys.meta_path', finder)


# ======== Начало добавления ================
# Класс для поиска пути в URL
class UrlPathFinder(importlib.abc.PathEntryFinder):
    def __init__(self, baseurl):
        self._links = None
        self._loader = UrlModuleLoader(baseurl)
        self._baseurl = baseurl

    def find_loader(self, fullname):
        log.debug('find_loader: %r', fullname)
        parts = fullname.split('.')
        basename = parts[-1]
        # Проверка кеша ссылок
        if self._links is None:
            self._links = []  # See discussion
            self._links = _get_links(self._baseurl)

        # Проверить, пакет ли это
        if basename in self._links:
            log.debug('find_loader: trying package %r', fullname)
            fullurl = self._baseurl + '/' + basename
            # Попытка загрузить пакет (которая обращается к __init__.py)
            loader = UrlPackageLoader(fullurl)
            try:
                loader.load_module(fullname)
                log.debug('find_loader: package %r loaded', fullname)
            except ImportError as e:
                log.debug('find_loader: %r is a namespace package', fullname)
                loader = None
            return (loader, [fullurl])

        # Обычный модуль
        filename = basename + '.py'
        if filename in self._links:
            log.debug('find_loader: module %r found', fullname)
            return (self._loader, [])
        else:
            log.debug('find_loader: module %r not found', fullname)
            return (None, [])

    def invalidate_caches(self):
        log.debug('invalidating link cache')
        self._links = None


# Проверка пути на предмет того, выглядит ли он как URL
_url_path_cache = {}


def handle_url(path):
    if path.startswith(('http://', 'https://')):
        log.debug('Handle path? %s. [Yes]', path)
        if path in _url_path_cache:
            finder = _url_path_cache[path]
        else:
            finder = UrlPathFinder(path)
           _url_path_cache[path] = finder
        return finder
    else:
        log.debug('Handle path? %s. [No]', path)


def install_path_hook():
    sys.path_hooks.append(handle_url)
    sys.path_importer_cache.clear()
    log.debug('Installing handle_url')


def remove_path_hook():
    sys.path_hooks.remove(handle_url)
    sys.path_importer_cache.clear()
    log.debug('Removing handle_url')

>>> # Первоначальный импорт не удается 
>>> import fib
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
ImportError: No module named 'fib'
>>> # Установка хука пути
>>> import urlimport
>>> urlimport.install_path_hook()
>>> # Импортирование все еще не удается (не в пути)
>>> import fib
Traceback (most recent call last):
File "<stdin>", line 1, in <modu1e>
ImportError: No module named 'fib'
>>> # Добавляем запись в sys.path и наблюдаем, как все отлично работает 
>>> import sys
>>> sys.path.append('http://localhost:15000')
>>> import fib 
I'm fib
>>> import grok.blah
I'm grok.__init__
I'm grok.blah
>>> grok.blah.__file__	
'http://localhost:15000/grok/blah.py'
>>>

>>> fib
<urlmodule 'fib' from 'http://localhost:15000/fib.py'>
>>> fib.__name__
'fib'
>>> fib.__file__
'http://localhost:15dee/fib.py'
>>> import inspect
>>> print(inspect.getsource(fib))
# fib.py 
print("I'm fib")

def fib(n):
    if n < 2:
        return 1
    else:
        return fib(n-1) + fib(n-2)
>>>