ultimate-sitemap-parser 1.2.0__py3-none-any.whl → 1.3.1__py3-none-any.whl

{ultimate_sitemap_parser-1.2.0.dist-info → ultimate_sitemap_parser-1.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ultimate-sitemap-parser
-Version: 1.2.0
+Version: 1.3.1
 Summary: A performant library for parsing and crawling sitemaps
 License: GPL-3.0-or-later
 Keywords: sitemap,crawler,indexing,xml,rss,atom,google news
@@ -8,7 +8,7 @@ Author: Linas Valiukas
 Author-email: linas@media.mit.edu
 Maintainer: Freddy Heppell
 Maintainer-email: f.heppell@sheffield.ac.uk
-Requires-Python: >=3.8
+Requires-Python: >=3.9
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Information Technology
@@ -16,7 +16,6 @@ Classifier: License :: OSI Approved :: GNU General Public License v3 or later (G
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11

ultimate_sitemap_parser-1.3.1.dist-info/RECORD

@@ -0,0 +1,21 @@
+usp/__init__.py,sha256=_jshbOBBUHRZ5ko4SdI7GRFiF9xKGJVCEPgL9lZJ81o,124
+usp/cli/__init__.py,sha256=mGrjSftUYfM2SGp9yEN2dTJndl5thOdv77-EAe6ocWo,37
+usp/cli/_ls.py,sha256=V0pMsDiQK_9RZ5MyUS2toW8b6e2FJ4spb3Grw6PayAI,3419
+usp/cli/_util.py,sha256=OrT9en350tATnaUrUn0peXr7aFPyYaaHGbEXGY6O4wI,2015
+usp/cli/cli.py,sha256=2byuqhBUhb7c1qUpBfTTufG-jvtiEWWq97GvCgv-s44,777
+usp/exceptions.py,sha256=9KTgnocYYZCfyaCf9BrBN7Ok4cwn7_DlrNFbhUfFsGM,634
+usp/fetch_parse.py,sha256=69U1uAKawUym41N4nwJXLW9tQ0WXO4Pi63hnljYCXPM,43524
+usp/helpers.py,sha256=FeIZcEuEM3Uz8tHeNucgoB3_27Ax6qCatfalPIHHGUY,8862
+usp/objects/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+usp/objects/page.py,sha256=vz2QXC9Z3E65Cxf68tKfQkubIc_OB0m6pNYH146Qx_8,14253
+usp/objects/sitemap.py,sha256=_t0ej2UmNsIb0NkxYkwYGxBqX_LHEJfNc-cRulQXyIk,11495
+usp/tree.py,sha256=MdnVxfIIMqWrudsYxFI8yQTXnlmNLFEcQEOkXbnuBr4,4395
+usp/web_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+usp/web_client/abstract_client.py,sha256=EWY4lPYJqpV7ge0DTZESTAOofAjNMIJnDm_2PPeZ9z4,7007
+usp/web_client/requests_client.py,sha256=sFYtJ8Q5z27WlTG1PgBzcvbS75pJ0pYUastEFmxa95U,5888
+ultimate_sitemap_parser-1.3.1.dist-info/LICENSE,sha256=ixuiBLtpoK3iv89l7ylKkg9rs2GzF9ukPH7ynZYzK5s,35148
+ultimate_sitemap_parser-1.3.1.dist-info/METADATA,sha256=GUU8qLo24ZGBtAd4CYaHxY927eFFGvKlVPhc6jfg5so,4397
+ultimate_sitemap_parser-1.3.1.dist-info/NOTICE,sha256=3ANZA5R9rYnCOnUoroGfFUOZ__ww_yG01NUAx0X6J7E,632
+ultimate_sitemap_parser-1.3.1.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+ultimate_sitemap_parser-1.3.1.dist-info/entry_points.txt,sha256=v60w5WzqYlPOucntZUy0ydzlYwuAPSwoQY0KdT5ragQ,36
+ultimate_sitemap_parser-1.3.1.dist-info/RECORD,,

usp/cli/_ls.py

@@ -2,7 +2,7 @@ import argparse
 import sys
 from typing import Iterator
 
-from usp.cli._util import format_help, tabs
+from usp.cli._util import CountAction, format_help, setup_logging, tabs
 from usp.objects.sitemap import AbstractSitemap
 from usp.tree import sitemap_tree_for_homepage
 
@@ -26,7 +26,7 @@ def register(subparsers):
         choices=LS_FORMATS,
         default="tabtree",
         help=format_help(LS_FORMATS, "set output format"),
-        metavar="",
+        metavar="FORMAT",
     )
     ls_parser.add_argument(
         "-r",
@@ -46,6 +46,21 @@ def register(subparsers):
         action="store_true",
         help="strip the supplied URL from each page and sitemap URL",
     )
+    ls_parser.add_argument(
+        "-v",
+        "--verbose",
+        action=CountAction,
+        help="increase output verbosity (-v=INFO, -vv=DEBUG)",
+        dest="verbosity",
+        default=0,
+        max_count=2,
+    )
+    ls_parser.add_argument(
+        "-l",
+        "--log-file",
+        type=str,
+        help="write log to this file and suppress console output",
+    )
     ls_parser.set_defaults(no_robots=False, no_known=False, strip_url=False)
 
     ls_parser.set_defaults(func=ls)
@@ -85,6 +100,8 @@ def _output_pages(sitemap: AbstractSitemap, strip_prefix: str = ""):
 
 
 def ls(args):
+    setup_logging(args.verbosity, args.log_file)
+
     tree = sitemap_tree_for_homepage(
         args.url,
         use_robots=not args.no_robots,

usp/cli/_util.py

@@ -1,4 +1,6 @@
-from typing import Dict
+import logging
+from argparse import Action
+from typing import Dict, Optional
 
 
 def format_help(choices: Dict[str, str], opt_help: str) -> str:
@@ -19,3 +21,57 @@ def format_help(choices: Dict[str, str], opt_help: str) -> str:
 def tabs(n: int):
     """Generate n tabs."""
     return "\t" * n
+
+
+_log_levels = {
+    0: logging.WARNING,
+    1: logging.INFO,
+    2: logging.DEBUG,
+}
+
+
+class CountAction(Action):
+    """Modified version of argparse._CountAction to output better help."""
+
+    def __init__(
+        self,
+        option_strings,
+        dest,
+        default=None,
+        required=False,
+        help=None,
+        max_count=None,
+    ):
+        super().__init__(
+            option_strings=option_strings,
+            dest=dest,
+            nargs=0,
+            default=default,
+            required=required,
+            help=help,
+        )
+        self.max_count = max_count
+
+    def __call__(self, parser, namespace, values, option_string=None):
+        count = getattr(namespace, self.dest, None)
+        if count is None:
+            count = 0
+        if self.max_count:
+            count = min(count, self.max_count)
+        setattr(namespace, self.dest, count + 1)
+
+    def format_usage(self):
+        option_str = self.option_strings[0]
+        if self.max_count is None:
+            return option_str
+        letter = self.option_strings[0][1]
+        usages = [f"-{letter * i}" for i in range(1, self.max_count + 1)]
+        return "/".join(usages)
+
+
+def setup_logging(verbosity: int, log_path: Optional[str]) -> None:
+    log_level = _log_levels.get(verbosity, logging.DEBUG)
+    if log_path is not None:
+        logging.basicConfig(level=log_level, filename=log_path)
+    else:
+        logging.basicConfig(level=log_level)

usp/cli/cli.py

@@ -1,10 +1,11 @@
 from argparse import ArgumentParser
+from typing import Optional
 
 from usp import __version__
 from usp.cli import _ls as ls_cmd
 
 
-def main():
+def parse_args(arg_list: Optional[list[str]]):
     parser = ArgumentParser(prog="usp", description="Ultimate Sitemap Parser")
     parser.add_argument(
         "-v", "--version", action="version", version=f"%(prog)s v{__version__}"
@@ -13,7 +14,12 @@ def main():
     subparsers = parser.add_subparsers(required=False, title="commands", metavar="")
     ls_cmd.register(subparsers)
 
-    args = parser.parse_args()
+    args = parser.parse_args(arg_list)
+    return args, parser
+
+
+def main(arg_list: Optional[list[str]] = None):
+    args, parser = parse_args(arg_list)
 
     if "func" in args:
         args.func(args)

usp/fetch_parse.py

@@ -13,7 +13,7 @@ import re
 import xml.parsers.expat
 from collections import OrderedDict
 from decimal import Decimal, InvalidOperation
-from typing import Dict, Optional, Union
+from typing import Dict, Optional, Set
 
 from .exceptions import SitemapException, SitemapXMLParsingException
 from .helpers import (
@@ -43,8 +43,10 @@ from .objects.sitemap import (
 )
 from .web_client.abstract_client import (
     AbstractWebClient,
+    AbstractWebClientResponse,
     AbstractWebClientSuccessResponse,
     LocalWebClient,
+    LocalWebClientSuccessResponse,
     NoWebClientException,
     WebClientErrorResponse,
 )
@@ -64,12 +66,17 @@ class SitemapFetcher:
     Spec says it might be up to 50 MB but let's go for the full 100 MB here."""
 
     __MAX_RECURSION_LEVEL = 11
-    """Max. recursion level in iterating over sub-sitemaps."""
+    """Max. depth level in iterating over sub-sitemaps.
+    
+    Recursive sitemaps (i.e. child sitemaps pointing to their parent) are stopped immediately.
+    """
 
     __slots__ = [
         "_url",
         "_recursion_level",
         "_web_client",
+        "_parent_urls",
+        "_quiet_404",
     ]
 
     def __init__(
@@ -77,14 +84,19 @@ class SitemapFetcher:
         url: str,
         recursion_level: int,
         web_client: Optional[AbstractWebClient] = None,
+        parent_urls: Optional[Set[str]] = None,
+        quiet_404: bool = False,
     ):
         """
 
         :param url: URL of the sitemap to fetch and parse.
         :param recursion_level: current recursion level of parser
         :param web_client: Web client to use. If ``None``, a :class:`~.RequestsWebClient` will be used.
+        :param parent_urls: Set of parent URLs that led to this sitemap.
+        :param quiet_404: Whether 404 errors are expected and should be logged at a reduced level, useful for speculative fetching of known URLs.
 
         :raises SitemapException: If the maximum recursion depth is exceeded.
+        :raises SitemapException: If the URL is in the parent URLs set.
         :raises SitemapException: If the URL is not an HTTP(S) URL
         """
         if recursion_level > self.__MAX_RECURSION_LEVEL:
@@ -92,9 +104,19 @@ class SitemapFetcher:
                 f"Recursion level exceeded {self.__MAX_RECURSION_LEVEL} for URL {url}."
             )
 
+        log.debug(f"Parent URLs is {parent_urls}")
+
         if not is_http_url(url):
             raise SitemapException(f"URL {url} is not a HTTP(s) URL.")
 
+        parent_urls = parent_urls or set()
+
+        if url in parent_urls:
+            # Likely a sitemap index points to itself/a higher level index
+            raise SitemapException(
+                f"Recursion detected in URL {url} with parent URLs {parent_urls}."
+            )
+
         if not web_client:
             web_client = RequestsWebClient()
 
@@ -103,19 +125,15 @@ class SitemapFetcher:
         self._url = url
         self._web_client = web_client
         self._recursion_level = recursion_level
+        self._parent_urls = parent_urls or set()
+        self._quiet_404 = quiet_404
 
-    def _fetch(self) -> Union[str, WebClientErrorResponse]:
+    def _fetch(self) -> AbstractWebClientResponse:
         log.info(f"Fetching level {self._recursion_level} sitemap from {self._url}...")
         response = get_url_retry_on_client_errors(
-            url=self._url, web_client=self._web_client
+            url=self._url, web_client=self._web_client, quiet_404=self._quiet_404
         )
-
-        if isinstance(response, WebClientErrorResponse):
-            return response
-
-        assert isinstance(response, AbstractWebClientSuccessResponse)
-
-        return ungzipped_response_content(url=self._url, response=response)
+        return response
 
     def sitemap(self) -> AbstractSitemap:
         """
@@ -124,13 +142,27 @@ class SitemapFetcher:
         :return: the parsed sitemap. Will be a child of :class:`~.AbstractSitemap`.
             If an HTTP error is encountered, or the sitemap cannot be parsed, will be :class:`~.InvalidSitemap`.
         """
-        response_content = self._fetch()
+        response = self._fetch()
 
-        if isinstance(response_content, WebClientErrorResponse):
+        if isinstance(response, WebClientErrorResponse):
             return InvalidSitemap(
                 url=self._url,
-                reason=f"Unable to fetch sitemap from {self._url}: {response_content.message()}",
+                reason=f"Unable to fetch sitemap from {self._url}: {response.message()}",
             )
+        assert isinstance(response, AbstractWebClientSuccessResponse)
+
+        response_url = response.url()
+        log.debug(f"Response URL is {response_url}")
+        if response_url in self._parent_urls:
+            # Likely a sitemap has redirected to a parent URL
+            return InvalidSitemap(
+                url=self._url,
+                reason=f"Recursion detected when {self._url} redirected to {response_url} with parent URLs {self._parent_urls}.",
+            )
+
+        self._url = response_url
+
+        response_content = ungzipped_response_content(url=self._url, response=response)
 
         # MIME types returned in Content-Type are unpredictable, so peek into the content instead
         if response_content[:20].strip().startswith("<"):
@@ -140,6 +172,7 @@ class SitemapFetcher:
                 content=response_content,
                 recursion_level=self._recursion_level,
                 web_client=self._web_client,
+                parent_urls=self._parent_urls,
             )
 
         else:
@@ -150,6 +183,7 @@ class SitemapFetcher:
                     content=response_content,
                     recursion_level=self._recursion_level,
                     web_client=self._web_client,
+                    parent_urls=self._parent_urls,
                 )
             else:
                 parser = PlainTextSitemapParser(
@@ -157,6 +191,7 @@ class SitemapFetcher:
                     content=response_content,
                     recursion_level=self._recursion_level,
                     web_client=self._web_client,
+                    parent_urls=self._parent_urls,
                 )
 
         log.info(f"Parsing sitemap from URL {self._url}...")
@@ -186,8 +221,8 @@ class SitemapStrParser(SitemapFetcher):
         )
         self._static_content = static_content
 
-    def _fetch(self) -> Union[str, WebClientErrorResponse]:
-        return self._static_content
+    def _fetch(self) -> AbstractWebClientResponse:
+        return LocalWebClientSuccessResponse(url=self._url, data=self._static_content)
 
 
 class AbstractSitemapParser(metaclass=abc.ABCMeta):
@@ -198,6 +233,7 @@ class AbstractSitemapParser(metaclass=abc.ABCMeta):
         "_content",
         "_web_client",
         "_recursion_level",
+        "_parent_urls",
     ]
 
     def __init__(
@@ -206,11 +242,13 @@ class AbstractSitemapParser(metaclass=abc.ABCMeta):
         content: str,
         recursion_level: int,
         web_client: AbstractWebClient,
+        parent_urls: Set[str],
     ):
         self._url = url
         self._content = content
         self._recursion_level = recursion_level
         self._web_client = web_client
+        self._parent_urls = parent_urls
 
     @abc.abstractmethod
     def sitemap(self) -> AbstractSitemap:
@@ -231,12 +269,14 @@ class IndexRobotsTxtSitemapParser(AbstractSitemapParser):
         content: str,
         recursion_level: int,
         web_client: AbstractWebClient,
+        parent_urls: Set[str],
     ):
         super().__init__(
             url=url,
             content=content,
             recursion_level=recursion_level,
             web_client=web_client,
+            parent_urls=parent_urls,
         )
 
         if not self._url.endswith("/robots.txt"):
@@ -271,6 +311,7 @@ class IndexRobotsTxtSitemapParser(AbstractSitemapParser):
                     url=sitemap_url,
                     recursion_level=self._recursion_level + 1,
                     web_client=self._web_client,
+                    parent_urls=self._parent_urls | {self._url},
                 )
                 fetched_sitemap = fetcher.sitemap()
             except NoWebClientException:
@@ -333,12 +374,14 @@ class XMLSitemapParser(AbstractSitemapParser):
         content: str,
         recursion_level: int,
         web_client: AbstractWebClient,
+        parent_urls: Set[str],
     ):
         super().__init__(
             url=url,
             content=content,
             recursion_level=recursion_level,
             web_client=web_client,
+            parent_urls=parent_urls,
         )
 
         # Will be initialized when the type of sitemap is known
@@ -432,6 +475,7 @@ class XMLSitemapParser(AbstractSitemapParser):
                     url=self._url,
                     web_client=self._web_client,
                     recursion_level=self._recursion_level,
+                    parent_urls=self._parent_urls,
                 )
 
             elif name == "rss":
@@ -545,14 +589,22 @@ class IndexXMLSitemapParser(AbstractXMLSitemapParser):
         "_recursion_level",
         # List of sub-sitemap URLs found in this index sitemap
         "_sub_sitemap_urls",
+        "_parent_urls",
     ]
 
-    def __init__(self, url: str, web_client: AbstractWebClient, recursion_level: int):
+    def __init__(
+        self,
+        url: str,
+        web_client: AbstractWebClient,
+        recursion_level: int,
+        parent_urls: Set[str],
+    ):
         super().__init__(url=url)
 
         self._web_client = web_client
         self._recursion_level = recursion_level
         self._sub_sitemap_urls = []
+        self._parent_urls = parent_urls
 
     def xml_element_end(self, name: str) -> None:
         if name == "sitemap:loc":
@@ -578,6 +630,7 @@ class IndexXMLSitemapParser(AbstractXMLSitemapParser):
                     url=sub_sitemap_url,
                     recursion_level=self._recursion_level + 1,
                     web_client=self._web_client,
+                    parent_urls=self._parent_urls | {self._url},
                 )
                 fetched_sitemap = fetcher.sitemap()
             except NoWebClientException:

usp/helpers.py

@@ -7,6 +7,7 @@ import logging
 import re
 import sys
 import time
+from http import HTTPStatus
 from typing import Optional
 from urllib.parse import unquote_plus, urlparse, urlunparse
 
@@ -130,11 +131,15 @@ def parse_rfc2822_date(date_string: str) -> Optional[datetime.datetime]:
         return None
 
 
+_404_log_message = f"{HTTPStatus.NOT_FOUND} {HTTPStatus.NOT_FOUND.phrase}"
+
+
 def get_url_retry_on_client_errors(
     url: str,
     web_client: AbstractWebClient,
     retry_count: int = 5,
     sleep_between_retries: int = 1,
+    quiet_404: bool = False,
 ) -> AbstractWebClientResponse:
     """
     Fetch URL, retry on retryable errors.
@@ -143,6 +148,8 @@ def get_url_retry_on_client_errors(
     :param web_client: Web client object to use for fetching.
     :param retry_count: How many times to retry fetching the same URL.
     :param sleep_between_retries: How long to sleep between retries, in seconds.
+    :param quiet_404: Whether to log 404 errors at a lower level.
+
     :return: Web client response object.
     """
     assert retry_count > 0, "Retry count must be positive."
@@ -153,7 +160,11 @@ def get_url_retry_on_client_errors(
         response = web_client.get(url)
 
         if isinstance(response, WebClientErrorResponse):
-            log.warning(f"Request for URL {url} failed: {response.message()}")
+            if quiet_404 and response.message() == _404_log_message:
+                log_level = logging.INFO
+            else:
+                log_level = logging.WARNING
+            log.log(log_level, f"Request for URL {url} failed: {response.message()}")
 
             if response.retryable():
                 log.info(f"Retrying URL {url} in {sleep_between_retries} seconds...")

usp/objects/sitemap.py

@@ -9,17 +9,19 @@
 """
 
 import abc
+import logging
 import os
 import pickle
 import tempfile
-from functools import lru_cache
+from functools import cache
 from typing import Iterator, List, Tuple
 
 from .page import SitemapPage
 
+log = logging.getLogger(__name__)
 
-# TODO: change to functools.cache when dropping py3.8
-@lru_cache(maxsize=None)
+
+@cache
 def _all_slots(target_cls):
     mro = target_cls.__mro__
 
@@ -153,6 +155,7 @@ class InvalidSitemap(AbstractSitemap):
         """
         super().__init__(url=url)
         self.__reason = reason
+        log.info(f"Invalid sitemap: {url}, reason: {reason}")
 
     def __eq__(self, other) -> bool:
         if not isinstance(other, InvalidSitemap):
@@ -222,8 +225,8 @@ class AbstractPagesSitemap(AbstractSitemap, metaclass=abc.ABCMeta):
         self._dump_pages(pages)
 
     def _dump_pages(self, pages: List[SitemapPage]):
-        temp_file, self.__pages_temp_file_path = tempfile.mkstemp()
-        with open(self.__pages_temp_file_path, "wb") as tmp:
+        fd, self.__pages_temp_file_path = tempfile.mkstemp()
+        with os.fdopen(fd, "wb") as tmp:
             pickle.dump(pages, tmp, protocol=pickle.HIGHEST_PROTOCOL)
 
     def __del__(self):

usp/tree.py

@@ -75,7 +75,10 @@ def sitemap_tree_for_homepage(
     sitemap_urls_found_in_robots_txt = set()
     if use_robots:
         robots_txt_fetcher = SitemapFetcher(
-            url=robots_txt_url, web_client=web_client, recursion_level=0
+            url=robots_txt_url,
+            web_client=web_client,
+            recursion_level=0,
+            parent_urls=set(),
         )
         robots_txt_sitemap = robots_txt_fetcher.sitemap()
         if not isinstance(robots_txt_sitemap, InvalidSitemap):
@@ -95,6 +98,8 @@ def sitemap_tree_for_homepage(
                     url=unpublished_sitemap_url,
                     web_client=web_client,
                     recursion_level=0,
+                    parent_urls=sitemap_urls_found_in_robots_txt,
+                    quiet_404=True,
                 )
                 unpublished_sitemap = unpublished_sitemap_fetcher.sitemap()
 

usp/web_client/abstract_client.py

@@ -101,6 +101,15 @@ class AbstractWebClientSuccessResponse(
         """
         raise NotImplementedError("Abstract method.")
 
+    @abc.abstractmethod
+    def url(self) -> str:
+        """
+        Return the actual URL fetched, after any redirects.
+
+        :return: URL fetched.
+        """
+        raise NotImplementedError("Abstract method.")
+
 
 class WebClientErrorResponse(AbstractWebClientResponse, metaclass=abc.ABCMeta):
     """
@@ -191,6 +200,27 @@ class LocalWebClient(AbstractWebClient):
         raise NoWebClientException
 
 
+class LocalWebClientSuccessResponse(AbstractWebClientSuccessResponse):
+    def __init__(self, url: str, data: str):
+        self._url = url
+        self._data = data
+
+    def status_code(self) -> int:
+        return 200
+
+    def status_message(self) -> str:
+        return "OK"
+
+    def header(self, case_insensitive_name: str) -> Optional[str]:
+        return None
+
+    def raw_data(self) -> bytes:
+        return self._data.encode("utf-8")
+
+    def url(self) -> str:
+        return self._url
+
+
 class RequestWaiter:
     """
     Manages waiting between requests.

usp/web_client/requests_client.py

@@ -62,6 +62,9 @@ class RequestsWebClientSuccessResponse(AbstractWebClientSuccessResponse):
 
         return data
 
+    def url(self) -> str:
+        return self.__requests_response.url
+
 
 class RequestsWebClientErrorResponse(WebClientErrorResponse):
     """
@@ -162,7 +165,7 @@ class RequestsWebClient(AbstractWebClient):
                 )
             else:
                 message = f"{response.status_code} {response.reason}"
-                log.info(f"Response content: {response.text}")
+                log.debug(f"Response content: {response.text}")
 
                 if response.status_code in RETRYABLE_HTTP_STATUS_CODES:
                     return RequestsWebClientErrorResponse(

ultimate_sitemap_parser-1.2.0.dist-info/RECORD

@@ -1,21 +0,0 @@
-usp/__init__.py,sha256=_jshbOBBUHRZ5ko4SdI7GRFiF9xKGJVCEPgL9lZJ81o,124
-usp/cli/__init__.py,sha256=mGrjSftUYfM2SGp9yEN2dTJndl5thOdv77-EAe6ocWo,37
-usp/cli/_ls.py,sha256=BjF5bGuhe_E_Ak-yyY0cDM83LFstl5tA3XNIrGZJujs,2954
-usp/cli/_util.py,sha256=UL5WiRZlpiDOI_QvSU1PdjcS6iCmfcLQlO1Mm1wjSAw,505
-usp/cli/cli.py,sha256=ySNyYHoCQ440KfxmpTkzLXgqtbnt5ru-TgPs2Zw2-LI,592
-usp/exceptions.py,sha256=9KTgnocYYZCfyaCf9BrBN7Ok4cwn7_DlrNFbhUfFsGM,634
-usp/fetch_parse.py,sha256=VJrJSAG1X8oQyW2p9wSepuGWfHlMDNoJG8jn3an2XUY,41396
-usp/helpers.py,sha256=S9d8fEhHzZqVCx3SkcWVTgW1JYKujH-tM86urjORNWA,8482
-usp/objects/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-usp/objects/page.py,sha256=vz2QXC9Z3E65Cxf68tKfQkubIc_OB0m6pNYH146Qx_8,14253
-usp/objects/sitemap.py,sha256=yt5qe6fyKfmvJmV60mB8kc7yooGcpYhuIcNlmUqFGFA,11486
-usp/tree.py,sha256=pwSTp1Zok4evzrNFavP-hh5i9xGGzObj_sKUqjk72UU,4237
-usp/web_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-usp/web_client/abstract_client.py,sha256=7MpIfqQpi1_yojEmuReT8iy9kFUWCD3i2LMpHmBOwV0,6291
-usp/web_client/requests_client.py,sha256=1nyXXBxiapDNN5jNpCAXRL5rgjptK4oKvaJhV5nhLsA,5816
-ultimate_sitemap_parser-1.2.0.dist-info/LICENSE,sha256=ixuiBLtpoK3iv89l7ylKkg9rs2GzF9ukPH7ynZYzK5s,35148
-ultimate_sitemap_parser-1.2.0.dist-info/METADATA,sha256=46wVZspA5eUgbXefu2Fu7xtE03TbFsgjEwLL5BT-mj0,4447
-ultimate_sitemap_parser-1.2.0.dist-info/NOTICE,sha256=3ANZA5R9rYnCOnUoroGfFUOZ__ww_yG01NUAx0X6J7E,632
-ultimate_sitemap_parser-1.2.0.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-ultimate_sitemap_parser-1.2.0.dist-info/entry_points.txt,sha256=v60w5WzqYlPOucntZUy0ydzlYwuAPSwoQY0KdT5ragQ,36
-ultimate_sitemap_parser-1.2.0.dist-info/RECORD,,