- Removed excessive blank lines from various markdown and Python files to improve readability and maintainability. - Ensured consistent formatting across documentation and code files, enhancing overall project clarity. - Updated logging mechanisms for better consistency and debugging support.
154 lines
2.7 KiB
Python
154 lines
2.7 KiB
Python
"""福袋相关文本解析辅助函数。
|
||
|
||
本模块提供若干轻量级的解析函数,主要用于:
|
||
- 从 OCR 文本中抽取福袋内容/倒计时/价值/参与人数
|
||
- 方便在单元测试中独立验证文本处理逻辑
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from typing import Optional
|
||
import re
|
||
|
||
from douyin_utils import normalize_countdown_text, extract_prize_value_yuan
|
||
|
||
|
||
def _safe_str(text: Optional[str]) -> str:
|
||
"""将输入安全地转换为字符串,None -> 空字符串。"""
|
||
if text is None:
|
||
return ""
|
||
return str(text)
|
||
|
||
|
||
def extract_fudai_content(text: Optional[str]) -> str:
|
||
"""从 OCR 文本中提取“福袋内容”相关描述。
|
||
|
||
当前实现比较宽松:
|
||
- 优先截取 “福袋内容:xxx” 或 “内容:xxx” 之后的部分
|
||
- 否则返回原始文本(去掉首尾空白)
|
||
"""
|
||
t = _safe_str(text).strip()
|
||
if not t:
|
||
return ""
|
||
|
||
# 常见前缀:福袋内容:xxx / 奖品内容:xxx / 内容:xxx
|
||
m = re.search(r"(福袋内容|奖品内容|内容)[::]\s*(.+)", t)
|
||
if m:
|
||
return m.group(2).strip()
|
||
|
||
# 如果包含“福袋”关键字,简单返回整句,后续需要时可再细化
|
||
if "福袋" in t:
|
||
return t
|
||
|
||
return t
|
||
|
||
|
||
def extract_fudai_countdown(text: Optional[str]) -> str:
|
||
"""从 OCR 文本中提取倒计时字符串。
|
||
|
||
返回值示例:
|
||
- ``"05:30"`` / ``"05:30后开奖"``
|
||
- 若无法解析则返回空字符串。
|
||
"""
|
||
t = _safe_str(text)
|
||
if not t:
|
||
return ""
|
||
|
||
norm = normalize_countdown_text(t)
|
||
return norm or ""
|
||
|
||
|
||
def extract_fudai_value(text: Optional[str]) -> float:
|
||
"""从 OCR 文本中提取福袋价值金额(元)。
|
||
|
||
直接复用 ``douyin_utils.extract_prize_value_yuan``。
|
||
"""
|
||
return float(extract_prize_value_yuan(_safe_str(text)))
|
||
|
||
|
||
def extract_participants_count(text: Optional[str]) -> int:
|
||
"""从 OCR 文本中提取“参与人数”。
|
||
|
||
支持的常见格式示例:
|
||
- ``"共1份1173人已参与"``
|
||
- ``"已有1000人参与"``
|
||
- ``"1173人已参与"``
|
||
- 若无法解析则返回 0。
|
||
"""
|
||
t = _safe_str(text)
|
||
if not t:
|
||
return 0
|
||
|
||
# 优先匹配“xxxx人已参与 / xxxx人参与 / xxxx人”
|
||
m = re.search(r"(\d+)\s*人(?:已参与|参与)?", t)
|
||
if m:
|
||
try:
|
||
return int(m.group(1))
|
||
except ValueError:
|
||
return 0
|
||
|
||
# 退化:查找所有数字,取中等大小的一个,避免把“份数”等误当成人数
|
||
nums = [int(n) for n in re.findall(r"\d+", t) if n.isdigit()]
|
||
if not nums:
|
||
return 0
|
||
# 简化策略:返回最大值(通常人数是文本里最大的数字)
|
||
return max(nums)
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|