xhs_video_crawler/test_xhs.py
2026-05-27 15:11:42 +08:00

251 lines
11 KiB
Python

import importlib
import unittest
from unittest import mock
class FakeResponse:
def __init__(self, body, raw_body):
self.body = body
self.raw_body = raw_body
class FakeDownloadResponse:
def __init__(self, content: bytes, content_type: str = "video/mp4", status_code: int = 200):
self.content = content
self.headers = {"content-type": content_type}
self.status_code = status_code
def raise_for_status(self) -> None:
if self.status_code >= 400:
raise RuntimeError(f"HTTP {self.status_code}")
class FakeRequests:
def __init__(self, response: FakeDownloadResponse):
self.response = response
def get(self, video_url, headers, timeout):
return self.response
class XhsModuleTests(unittest.TestCase):
def test_module_can_import_without_optional_runtime_dependencies(self) -> None:
module = importlib.import_module("XHS")
self.assertIsNotNone(module)
def test_sanitize_filename_removes_invalid_characters(self) -> None:
module = importlib.import_module("XHS")
self.assertEqual(
module.sanitize_filename('a/b:c*?d"e<f>g|h\n'),
"a_b_c__d_e_f_g_h",
)
def test_truncate_utf8_bytes_keeps_valid_utf8(self) -> None:
module = importlib.import_module("XHS")
result = module.truncate_utf8_bytes("测试标题" * 20, 20)
self.assertLessEqual(len(result.encode("utf-8")), 20)
result.encode("utf-8")
def test_choose_video_url_prefers_master_url(self) -> None:
module = importlib.import_module("XHS")
candidates = [
module.VideoCandidate(
video_id="note-1",
title="标题",
video_url="https://example.com/backup.mp4",
author_name="作者",
source_key="backup_urls",
),
module.VideoCandidate(
video_id="note-1",
title="标题",
video_url="https://sns-video.xhscdn.com/master.mp4",
author_name="作者",
source_key="master_url",
),
]
self.assertEqual(module.choose_video_candidate(candidates).video_url, "https://sns-video.xhscdn.com/master.mp4")
def test_group_video_candidates_keeps_one_preferred_candidate_per_video_id(self) -> None:
module = importlib.import_module("XHS")
candidates = [
module.VideoCandidate("note-1", "标题", "https://example.com/backup.mp4", "作者", "backup_urls"),
module.VideoCandidate("note-1", "标题", "https://example.com/master.mp4", "作者", "master_url"),
module.VideoCandidate("note-2", "标题2", "https://example.com/two.mp4", "作者", "master_url"),
]
grouped = module.group_video_candidates(candidates)
self.assertEqual([item.video_id for item in grouped], ["note-1", "note-2"])
self.assertEqual(grouped[0].video_url, "https://example.com/master.mp4")
def test_extract_video_candidates_from_nested_feed_payload(self) -> None:
module = importlib.import_module("XHS")
payload = {
"data": {
"items": [
{
"id": "note123",
"note_card": {
"display_title": "海边日落",
"user": {"nickname": "摄影师"},
"video": {
"media": {
"stream": {
"h264": [
{
"master_url": "https://sns-video.xhscdn.com/stream/a.mp4?sign=1",
"backup_urls": [
"https://sns-video.xhscdn.com/stream/a-backup.mp4?sign=1"
],
}
]
}
}
},
},
}
]
}
}
candidates = module.extract_video_candidates(payload)
self.assertEqual(len(candidates), 2)
self.assertEqual(candidates[0].video_id, "note123")
self.assertEqual(candidates[0].title, "海边日落")
self.assertEqual(candidates[0].author_name, "摄影师")
self.assertEqual(candidates[0].source_key, "master_url")
def test_extract_video_candidates_ignores_plain_image_url_fields(self) -> None:
module = importlib.import_module("XHS")
payload = {
"id": "note-image",
"display_title": "图片笔记",
"user": {"nickname": "作者"},
"image_list": [
{"url": "https://sns-img.xhscdn.com/example.webp"},
{"url": "https://sns-img.xhscdn.com/example.jpg"},
],
}
self.assertEqual(module.extract_video_candidates(payload), [])
def test_extract_video_candidates_from_escaped_html_state(self) -> None:
module = importlib.import_module("XHS")
html = (
'<script>{"display_title":"视频标题","nickname":"作者",'
r'\"master_url\":\"http:\/\/sns-video-qc.xhscdn.com\/stream\/a.mp4?sign=1&t=2\"'
'}</script>'
)
candidates = module.extract_video_candidates_from_html(html, video_id="note123")
self.assertEqual(len(candidates), 1)
self.assertEqual(candidates[0].video_id, "note123")
self.assertEqual(candidates[0].video_url, "http://sns-video-qc.xhscdn.com/stream/a.mp4?sign=1&t=2")
self.assertEqual(candidates[0].source_key, "html_master_url")
def test_build_output_path_uses_author_title_and_video_id(self) -> None:
module = importlib.import_module("XHS")
candidate = module.VideoCandidate(
video_id="note123",
title="海边日落",
video_url="https://sns-video.xhscdn.com/a.mp4",
author_name="摄影师",
source_key="master_url",
)
output_path = module.build_output_path(candidate)
self.assertEqual(output_path.as_posix(), "video/[摄影师]海边日落-note123.mp4")
def test_build_browser_address_from_port(self) -> None:
module = importlib.import_module("XHS")
self.assertEqual(module.build_browser_address(9224), "127.0.0.1:9224")
self.assertIsNone(module.build_browser_address(None))
def test_ensure_browser_debug_port_ready_accepts_open_port(self) -> None:
module = importlib.import_module("XHS")
connection = mock.MagicMock()
connection.__enter__.return_value = connection
connection.__exit__.return_value = False
with mock.patch.object(module.socket, "create_connection", return_value=connection) as mocked_connect:
module.ensure_browser_debug_port_ready(9224)
mocked_connect.assert_called_once()
def test_ensure_browser_debug_port_ready_rejects_closed_port(self) -> None:
module = importlib.import_module("XHS")
with mock.patch.object(module.socket, "create_connection", side_effect=OSError("boom")):
with self.assertRaisesRegex(RuntimeError, "login_xhs.py"):
module.ensure_browser_debug_port_ready(9224)
def test_extract_feed_payload_uses_dict_body(self) -> None:
module = importlib.import_module("XHS")
response = FakeResponse({"data": {"items": []}}, "")
self.assertEqual(module.extract_feed_payload(response), {"data": {"items": []}})
def test_extract_feed_payload_falls_back_to_raw_json(self) -> None:
module = importlib.import_module("XHS")
response = FakeResponse("", '{"data": {"items": [{"id": "1"}]}}')
self.assertEqual(
module.extract_feed_payload(response),
{"data": {"items": [{"id": "1"}]}},
)
def test_build_parser_uses_expected_defaults(self) -> None:
module = importlib.import_module("XHS")
args = module.build_parser().parse_args([])
self.assertEqual(args.max_videos, 10)
self.assertEqual(args.output_dir, "video")
self.assertEqual(args.browser_port, 9224)
self.assertEqual(args.timeout, 20)
self.assertEqual(args.start_url, module.DEFAULT_EXPLORE_URL)
self.assertFalse(args.use_current_page)
def test_main_invokes_collect_videos_with_cli_values(self) -> None:
module = importlib.import_module("XHS")
with mock.patch.object(module, "collect_videos", return_value=3) as mocked_collect:
exit_code = module.main(
[
"--max-videos",
"3",
"--output-dir",
"downloads",
"--browser-port",
"9334",
"--timeout",
"7",
"--start-url",
"https://www.xiaohongshu.com/explore",
]
)
self.assertEqual(exit_code, 0)
mocked_collect.assert_called_once()
_, kwargs = mocked_collect.call_args
self.assertEqual(kwargs["max_videos"], 3)
self.assertEqual(kwargs["output_dir"].as_posix(), "downloads")
self.assertEqual(kwargs["browser_port"], 9334)
self.assertEqual(kwargs["timeout"], 7)
self.assertFalse(kwargs["use_current_page"])
def test_download_video_rejects_webp_response_before_writing_file(self) -> None:
module = importlib.import_module("XHS")
response = FakeDownloadResponse(b"RIFF....WEBP", content_type="image/webp")
with self.assertRaisesRegex(ValueError, "非视频响应"):
module.download_video(
requests_module=FakeRequests(response),
headers={},
video_url="https://sns-img.xhscdn.com/example.webp",
output_path=mock.MagicMock(),
)
def test_download_video_accepts_mp4_signature(self) -> None:
module = importlib.import_module("XHS")
output_path = mock.MagicMock()
output_path.parent.mkdir = mock.MagicMock()
output_path.write_bytes = mock.MagicMock()
response = FakeDownloadResponse(b"\x00\x00\x00\x18ftypmp42payload", content_type="application/octet-stream")
module.download_video(
requests_module=FakeRequests(response),
headers={},
video_url="https://sns-video.xhscdn.com/example.mp4",
output_path=output_path,
)
output_path.write_bytes.assert_called_once_with(b"\x00\x00\x00\x18ftypmp42payload")
if __name__ == "__main__":
unittest.main()