知微
fa45d8aa5f
- health_checklist.json: 192.168.1.122→node122
- ocr_client.py: docstring IP→node122
- docs/market-data-requirements.md: IP→node122
- 所有API调用通过ProxyHandler({})绕过系统代理
Privoxy对node122:18003返回500，直连正常
53 lines
1.9 KiB
Python
53 lines
1.9 KiB
Python
# Copyright 2022-present, the HuggingFace Inc. team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
"""Contains utilities to handle pagination on Huggingface Hub."""
|
|
|
|
from collections.abc import Iterable
|
|
from typing import Any
|
|
|
|
import httpx
|
|
|
|
from . import get_session, hf_raise_for_status, http_backoff, logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
def paginate(path: str, params: dict | list[tuple[str, Any]], headers: dict, timeout: float | None = None) -> Iterable:
|
|
"""Fetch a list of models/datasets/spaces and paginate through results.
|
|
|
|
This is using the same "Link" header format as GitHub.
|
|
See:
|
|
- https://requests.readthedocs.io/en/latest/api/#requests.Response.links
|
|
- https://docs.github.com/en/rest/guides/traversing-with-pagination#link-header
|
|
"""
|
|
session = get_session()
|
|
r = session.get(path, params=params, headers=headers, timeout=timeout)
|
|
hf_raise_for_status(r)
|
|
yield from r.json()
|
|
|
|
# Follow pages
|
|
# Next link already contains query params
|
|
next_page = _get_next_page(r)
|
|
while next_page is not None:
|
|
logger.debug(f"Pagination detected. Requesting next page: {next_page}")
|
|
r = http_backoff("GET", next_page, headers=headers, timeout=timeout)
|
|
hf_raise_for_status(r)
|
|
yield from r.json()
|
|
next_page = _get_next_page(r)
|
|
|
|
|
|
def _get_next_page(response: httpx.Response) -> str | None:
|
|
return response.links.get("next", {}).get("url")
|