feat: 提交热榜评论分析工具 MVP 基线
This commit is contained in:
@@ -0,0 +1,117 @@
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from datetime import UTC, datetime
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
|
||||
|
||||
@dataclass
|
||||
class HotspotData:
|
||||
source_hot_id: str | None
|
||||
title: str
|
||||
rank: int | None = None
|
||||
heat_value: str | None = None
|
||||
raw_data: dict[str, Any] | None = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class ContentItemData:
|
||||
source_item_id: str
|
||||
item_type: str
|
||||
title: str | None = None
|
||||
summary: str | None = None
|
||||
url: str | None = None
|
||||
raw_data: dict[str, Any] | None = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class CommentData:
|
||||
source_comment_id: str | None
|
||||
content: str
|
||||
author: str | None = None
|
||||
like_count: int | None = None
|
||||
comment_time: datetime | None = None
|
||||
raw_data: dict[str, Any] | None = None
|
||||
|
||||
|
||||
class PlatformAPIError(Exception):
|
||||
def __init__(self, message: str, *, error_type: str, status_code: int | None = None):
|
||||
super().__init__(message)
|
||||
self.error_type = error_type
|
||||
self.status_code = status_code
|
||||
|
||||
|
||||
class TikHubClient:
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
timeout_seconds: int = 20,
|
||||
max_retries: int = 3,
|
||||
http_client: httpx.Client | None = None,
|
||||
) -> None:
|
||||
self.base_url = base_url.rstrip("/")
|
||||
self.api_key = api_key
|
||||
self.timeout_seconds = timeout_seconds
|
||||
self.max_retries = max_retries
|
||||
self._http_client = http_client or httpx.Client(timeout=timeout_seconds)
|
||||
|
||||
def get(self, path: str, *, params: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
return self._request("GET", path, params=params)
|
||||
|
||||
def post(self, path: str, *, json: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
return self._request("POST", path, json=json)
|
||||
|
||||
def _request(self, method: str, path: str, **kwargs) -> dict[str, Any]:
|
||||
url = f"{self.base_url}{path}"
|
||||
headers = {"Authorization": f"Bearer {self.api_key}"} if self.api_key else {}
|
||||
last_status: int | None = None
|
||||
for attempt in range(self.max_retries + 1):
|
||||
try:
|
||||
response = self._http_client.request(method, url, headers=headers, **kwargs)
|
||||
except httpx.RequestError as exc:
|
||||
if attempt >= self.max_retries:
|
||||
raise PlatformAPIError("External API request failed", error_type="network_error") from exc
|
||||
time.sleep(2**attempt)
|
||||
continue
|
||||
|
||||
last_status = response.status_code
|
||||
if response.status_code == 429:
|
||||
if attempt >= self.max_retries:
|
||||
raise PlatformAPIError(
|
||||
"External API rate limited",
|
||||
error_type="rate_limited",
|
||||
status_code=response.status_code,
|
||||
)
|
||||
time.sleep(2**attempt)
|
||||
continue
|
||||
if response.is_error:
|
||||
raise PlatformAPIError(
|
||||
f"External API returned HTTP {response.status_code}",
|
||||
error_type="api_error",
|
||||
status_code=response.status_code,
|
||||
)
|
||||
return response.json()
|
||||
|
||||
raise PlatformAPIError("External API request failed", error_type="api_error", status_code=last_status)
|
||||
|
||||
|
||||
def parse_timestamp(value: Any) -> datetime | None:
|
||||
if value in (None, ""):
|
||||
return None
|
||||
try:
|
||||
number = int(value)
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
if number > 10_000_000_000:
|
||||
number = number // 1000
|
||||
return datetime.fromtimestamp(number, tz=UTC)
|
||||
|
||||
|
||||
def first_present(data: dict[str, Any], *keys: str) -> Any:
|
||||
for key in keys:
|
||||
if key in data and data[key] not in (None, ""):
|
||||
return data[key]
|
||||
return None
|
||||
Reference in New Issue
Block a user