Python pip._internal.download.is_url() Examples

The following are 27 code examples of pip._internal.download.is_url(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module pip._internal.download , or try the search function .
Example #1
Source File: index.py    From learn_python3_spider with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #2
Source File: index.py    From twitter-stock-recommendation with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #3
Source File: index.py    From fxxkpython with GNU General Public License v3.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #4
Source File: index.py    From fxxkpython with GNU General Public License v3.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #5
Source File: index.py    From fxxkpython with GNU General Public License v3.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #6
Source File: index.py    From fxxkpython with GNU General Public License v3.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #7
Source File: index.py    From android_universal with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #8
Source File: index.py    From V1EngineeringInc-Docs with Creative Commons Attribution Share Alike 4.0 International 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #9
Source File: index.py    From Carnets with BSD 3-Clause "New" or "Revised" License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #10
Source File: index.py    From coffeegrindsize with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #11
Source File: index.py    From guildai with Apache License 2.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #12
Source File: index.py    From Weapon-Detection-And-Classification with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #13
Source File: index.py    From Hands-On-Application-Development-with-PyCharm with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #14
Source File: index.py    From stopstalk-deployment with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #15
Source File: index.py    From Python24 with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #16
Source File: index.py    From scylla with Apache License 2.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #17
Source File: index.py    From Building-Recommendation-Systems-with-Python with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #18
Source File: index.py    From Building-Recommendation-Systems-with-Python with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #19
Source File: index.py    From pySINDy with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #20
Source File: index.py    From hacktoberfest2018 with GNU General Public License v3.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #21
Source File: index.py    From hacktoberfest2018 with GNU General Public License v3.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #22
Source File: index.py    From GraphicDesignPatternByPython with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #23
Source File: index.py    From deepWordBug with Apache License 2.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #24
Source File: index.py    From Mastering-Elasticsearch-7.0 with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #25
Source File: index.py    From Mastering-Elasticsearch-7.0 with MIT License 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        # type: (Sequence[str], bool) -> Tuple[List[str], List[str]]
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                    else:
                        logger.warning(
                            "Path '{0}' is ignored: "
                            "it is a directory.".format(path),
                        )
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #26
Source File: index.py    From FuYiSpider with Apache License 2.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls 
Example #27
Source File: index.py    From FuYiSpider with Apache License 2.0 4 votes vote down vote up
def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url,
                    )
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url,
                )

        return files, urls