Sitelet https://github.com/NanmiCoder/MediaCrawler/pull/978/files
Skip to content

fix(weibo): detail 模式支持传入微博帖子 URL #978

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ybwbqg9379 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(weibo): detail 模式支持传入微博帖子 URL #978

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion cmd_arg/arg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,6 +143,17 @@ def _normalize_tieba_note_id(value: str) -> str:
return match.group(1) if match else value


def _normalize_weibo_note_id(value: str) -> str:
"""Accept a raw Weibo note id or a post URL.

Handles the common post URL shapes:
https://weibo.com/<uid>/<bid>, https://m.weibo.cn/detail/<mid>, https://m.weibo.cn/status/<bid>
"""
value = value.strip()
match = re.search(r"weibo\.(?:com|cn)/(?:\d+|detail|status)/([A-Za-z0-9]+)", value)
return match.group(1) if match else value


def _normalize_tieba_creator_url(value: str) -> str:
"""Accept a Tieba creator homepage URL or a portrait id."""
value = value.strip()
Expand Down Expand Up @@ -375,7 +386,9 @@ def main(
elif platform == PlatformEnum.DOUYIN:
config.DY_SPECIFIED_ID_LIST = specified_id_list
elif platform == PlatformEnum.WEIBO:
config.WEIBO_SPECIFIED_ID_LIST = specified_id_list
config.WEIBO_SPECIFIED_ID_LIST = [
_normalize_weibo_note_id(item) for item in specified_id_list
]
elif platform == PlatformEnum.KUAISHOU:
config.KS_SPECIFIED_ID_LIST = specified_id_list
elif platform == PlatformEnum.TIEBA:
Expand Down
53 changes: 53 additions & 0 deletions tests/test_cmd_arg_weibo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
# -*- coding: utf-8 -*-
# Copyright (c) 2025 relakkes@gmail.com
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/tests/test_cmd_arg_weibo.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
# 3. 不得进行大规模爬取或对平台造成运营干扰。
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
# 5. 不得用于任何非法或不当的用途。
#
# 详细许可条款请参阅项目根目录下的LICENSE文件。
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。

import config
import pytest
from cmd_arg import parse_cmd
from cmd_arg.arg import _normalize_weibo_note_id


@pytest.mark.parametrize(
"raw, expected",
[
("R3bk1ydAR", "R3bk1ydAR"),
("4982041758140155", "4982041758140155"),
("https://weibo.com/7798025479/R3bk1ydAR?refer_flag=1001030103_", "R3bk1ydAR"),
("https://m.weibo.cn/detail/4982041758140155", "4982041758140155"),
("https://m.weibo.cn/status/R3bk1ydAR", "R3bk1ydAR"),
(" https://weibo.com/7798025479/R3bk1ydAR ", "R3bk1ydAR"),
],
)
def test_normalize_weibo_note_id(raw, expected):
assert _normalize_weibo_note_id(raw) == expected


@pytest.mark.asyncio
async def test_weibo_detail_cli_sets_specified_ids():
await parse_cmd(
[
"--platform",
"wb",
"--type",
"detail",
"--specified_id",
"https://weibo.com/7798025479/R3bk1ydAR?refer_flag=1001030103_,4982041758140155",
]
)

assert config.WEIBO_SPECIFIED_ID_LIST == ["R3bk1ydAR", "4982041758140155"]