- 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.
283 lines
9.7 KiB
Python
283 lines
9.7 KiB
Python
import os
|
||
import re
|
||
from typing import Iterable
|
||
|
||
|
||
def normalize_countdown_text(text: str) -> str:
|
||
"""对福袋倒计时类 OCR 文本做标准化,抽离自 douyin_fudai.py,方便复用与单元测试。"""
|
||
if not text:
|
||
return ""
|
||
t = re.sub(r"\s+", "", str(text))
|
||
t = t.replace(":", ":")
|
||
# 常见 OCR 混淆纠正(只做轻量替换,避免影响其它文字)
|
||
t = t.translate(
|
||
str.maketrans(
|
||
{
|
||
"O": "0",
|
||
"o": "0",
|
||
"Q": "0",
|
||
"D": "0",
|
||
"I": "1",
|
||
"l": "1",
|
||
"|": "1",
|
||
"!": "1",
|
||
"S": "5",
|
||
"s": "5",
|
||
"B": "8",
|
||
"G": "6",
|
||
"Z": "2",
|
||
}
|
||
)
|
||
)
|
||
|
||
# 中文:x分y秒 / y秒
|
||
m = re.search(r"(\d{1,2})分(\d{1,2})秒", t)
|
||
if m:
|
||
mm = int(m.group(1))
|
||
ss = int(m.group(2))
|
||
if ss >= 60:
|
||
mm += ss // 60
|
||
ss = ss % 60
|
||
return f"{mm}:{ss:02d}"
|
||
# 仅分钟:x分钟
|
||
m = re.search(r"(\d{1,2})分钟", t)
|
||
if m:
|
||
mm = int(m.group(1))
|
||
return f"{mm}:00"
|
||
m = re.search(r"(\d{1,3})秒", t)
|
||
if m:
|
||
ss = int(m.group(1))
|
||
mm = ss // 60
|
||
ss = ss % 60
|
||
return f"{mm}:{ss:02d}"
|
||
# 标准样式:11:37后开奖 / 11:37后开奖
|
||
m = re.search(r"(\d{1,2})[::](\d{2}).*后开奖", t)
|
||
if m:
|
||
mm = int(m.group(1))
|
||
ss = int(m.group(2))
|
||
# 若分秒识别反了(例如 53:08 实际应为 08:53),优先选择 <= 15 分钟的解释
|
||
# 或者秒数不合法(>=60),也尝试交换
|
||
total1 = mm * 60 + ss
|
||
total2 = ss * 60 + mm
|
||
if (total1 > 900 and total2 <= 900) or (ss >= 60 and mm < 60):
|
||
mm, ss = ss, mm
|
||
return f"{mm}:{ss:02d}后开奖"
|
||
# 识别错序:54后开奖04
|
||
m = re.search(r"(\d{1,2})后开奖(\d{2})", t)
|
||
if m:
|
||
mm = int(m.group(1))
|
||
ss = int(m.group(2))
|
||
if (mm * 60 + ss) > 900 and (ss * 60 + mm) <= 900:
|
||
mm, ss = ss, mm
|
||
return f"{mm}:{ss:02d}后开奖"
|
||
# 纯 mm:ss 格式(不带"后开奖"):11:17 / 05:11
|
||
m = re.search(r"^(\d{1,2})[::](\d{1,2})$", t)
|
||
if m:
|
||
mm = int(m.group(1))
|
||
ss = int(m.group(2))
|
||
# 检查是否需要交换分秒:
|
||
# 1. 秒数不合法(>=60)且交换后合法
|
||
# 2. 总时间>15分钟且交换后<=15分钟
|
||
total1 = mm * 60 + ss
|
||
total2 = ss * 60 + mm
|
||
if (ss >= 60 and mm < 60) or (total1 > 900 and total2 <= 900):
|
||
mm, ss = ss, mm
|
||
# 如果秒数仍然>=60,进行进位处理
|
||
if ss >= 60:
|
||
mm += ss // 60
|
||
ss = ss % 60
|
||
return f"{mm}:{ss:02d}"
|
||
# 纯数字 1137 / 5404
|
||
digits = "".join(ch for ch in t if ch.isdigit())
|
||
if len(digits) == 4:
|
||
a = int(digits[:2])
|
||
b = int(digits[2:])
|
||
|
||
# 生成两种解释:mm:ss 以及交换后的 mm:ss
|
||
mm1, ss1 = a, b
|
||
mm2, ss2 = b, a
|
||
|
||
total1 = mm1 * 60 + ss1
|
||
total2 = mm2 * 60 + ss2
|
||
|
||
# 默认相信“从左到右”的顺序:前两位=分,后两位=秒。
|
||
# 只有在明显异常(>15分钟)或秒数不合法时才交换。
|
||
if ss1 >= 60 and ss2 < 60:
|
||
mm, ss = mm2, ss2
|
||
elif ss2 >= 60 and ss1 < 60:
|
||
mm, ss = mm1, ss1
|
||
elif total1 > 900 and total2 <= 900:
|
||
mm, ss = mm2, ss2
|
||
elif total2 > 900 and total1 <= 900:
|
||
mm, ss = mm1, ss1
|
||
else:
|
||
mm, ss = mm1, ss1
|
||
|
||
return f"{mm}:{ss:02d}"
|
||
# 3 位数字:934 => 09:34
|
||
if len(digits) == 3:
|
||
mm = int(digits[0])
|
||
ss = int(digits[1:])
|
||
if ss >= 60:
|
||
# 尝试 15:09(OCR 丢 0)
|
||
mm2 = int(digits[:2])
|
||
ss2 = int(digits[2])
|
||
if ss2 < 60:
|
||
return f"{mm2:02d}:{ss2:02d}"
|
||
mm += ss // 60
|
||
ss = ss % 60
|
||
return f"{mm:02d}:{ss:02d}"
|
||
# 2 位数字:31 => 00:31(更符合临近开奖)
|
||
if len(digits) == 2:
|
||
return f"00:{int(digits):02d}"
|
||
return t
|
||
|
||
|
||
def extract_prize_value_yuan(text: str) -> float:
|
||
"""从 OCR 文本中抽取奖品价值金额(元),抽离自 douyin_fudai.py。"""
|
||
if not text:
|
||
return 0.0
|
||
t = re.sub(r"\s+", "", str(text))
|
||
# 先去掉倒计时类数字,避免把 00:31 解析成 31 元
|
||
t = re.sub(r"\b\d{1,2}[::]\d{2}\b", "", t)
|
||
|
||
# 优先匹配带币种符号/单位的金额:参考价值¥199 / ¥199.9 / ¥199 / 199元
|
||
# 先尝试匹配带¥符号的金额(¥符号可能被OCR识别成各种形式)
|
||
currency_matches = re.findall(r"[¥¥\u00A5\uFFE5](\d+(?:\.\d+)?)", t)
|
||
yuan_matches = re.findall(r"(\d+(?:\.\d+)?)元", t)
|
||
tagged: Iterable[str] = list(currency_matches) + list(yuan_matches)
|
||
if tagged:
|
||
vals: list[float] = []
|
||
for n in tagged:
|
||
try:
|
||
vals.append(float(n))
|
||
except ValueError:
|
||
pass
|
||
if vals:
|
||
return max(vals)
|
||
|
||
# 清理¥符号:OCR可能把¥符号识别成数字或其他字符,先清理掉
|
||
# ¥符号的Unicode编码是 \u00A5,全角¥是 \uFFE5
|
||
# 使用更精确的匹配:只在数字前清理¥符号
|
||
t = re.sub(r"[¥¥\u00A5\uFFE5]\s*(\d)", r"\1", t) # 清理¥符号(保留后面的数字)
|
||
# 处理¥被识别成Y/y的情况:Y/y后跟数字
|
||
t = re.sub(r"[Yy]\s*(\d)", r"\1", t) # 清理Y/y(保留后面的数字)
|
||
|
||
# 注意:不在这里处理¥被识别成8的情况,因为真正的8199元是合理的
|
||
# 将在后续提取整数时,根据上下文更智能地判断
|
||
|
||
# 清理后再次尝试匹配"元"后缀
|
||
yuan_matches_after_clean = re.findall(r"(\d+(?:\.\d+)?)元", t)
|
||
if yuan_matches_after_clean:
|
||
vals_after_clean: list[float] = []
|
||
for n in yuan_matches_after_clean:
|
||
try:
|
||
vals_after_clean.append(float(n))
|
||
except ValueError:
|
||
pass
|
||
if vals_after_clean:
|
||
return max(vals_after_clean)
|
||
|
||
# 去掉常见干扰:份数/参与人数
|
||
t = re.sub(r"共\d+份", "", t)
|
||
t = re.sub(r"\d+人已参与", "", t)
|
||
|
||
# 退化:抓小数
|
||
decimals = re.findall(r"\d+\.\d+", t)
|
||
if decimals:
|
||
vals = []
|
||
for n in decimals:
|
||
try:
|
||
val = float(n)
|
||
# 过滤掉明显不合理的值(比如小数点前有多个数字,可能是误识别)
|
||
if 0.01 <= val <= 99999.99:
|
||
vals.append(val)
|
||
except ValueError:
|
||
pass
|
||
if vals:
|
||
return max(vals)
|
||
|
||
# 再退化:抓整数
|
||
ints = re.findall(r"\d+", t)
|
||
if ints:
|
||
vals = []
|
||
for n in ints:
|
||
try:
|
||
v = int(n)
|
||
# 处理¥被识别成8的情况:需要更智能的判断,避免误识别真正的8199元
|
||
# 只在以下情况才考虑去掉第一个8:
|
||
# 1. 数字非常大(>=50000),且去掉8后的数字在合理范围内(100-9999)
|
||
# 2. 文本中没有明确的单位(如"元"),说明可能是纯数字OCR误识别
|
||
# 3. 如果数字本身就在合理范围内(1-99999),优先保留原值(可能是真正的8199元)
|
||
if len(n) >= 5 and n.startswith("8"): # 5位以上数字才考虑
|
||
corrected = int(n[1:])
|
||
# 只在原数字非常大(>=50000)且去掉8后数字在合理范围(100-9999)时,才考虑修正
|
||
# 这样可以避免把真正的8199、81999等误识别
|
||
if v >= 50000 and 100 <= corrected <= 9999:
|
||
# 检查文本中是否有"元"等明确单位
|
||
has_yuan_unit = "元" in t
|
||
# 如果没有明确单位,更可能是误识别(¥被识别成8)
|
||
if not has_yuan_unit:
|
||
vals.append(float(corrected))
|
||
else:
|
||
# 有明确单位,保留原值(可能是真正的价值,如81999元)
|
||
if 1 <= v <= 99999:
|
||
vals.append(float(v))
|
||
elif 1 <= v <= 99999:
|
||
# 数字在合理范围内,保留原值(包括8199、81999等)
|
||
vals.append(float(v))
|
||
elif 1 <= v <= 99999:
|
||
vals.append(float(v))
|
||
except ValueError:
|
||
continue
|
||
if vals:
|
||
return max(vals)
|
||
|
||
return 0.0
|
||
|
||
|
||
def parse_countdown_seconds(text: str) -> int:
|
||
"""
|
||
将福袋倒计时文本解析为总秒数。
|
||
|
||
这是对 ``normalize_countdown_text`` 的简单封装,方便在其它模块或测试中直接得到秒数。
|
||
|
||
示例::
|
||
|
||
>>> parse_countdown_seconds("5分30秒")
|
||
330
|
||
>>> parse_countdown_seconds("30秒")
|
||
30
|
||
>>> parse_countdown_seconds("5:00")
|
||
300
|
||
"""
|
||
norm = normalize_countdown_text(text)
|
||
if not norm:
|
||
return 0
|
||
# 期望格式 "mm:ss" 或 "mm:ss后开奖"
|
||
m = re.search(r"(\d{1,3}):(\d{1,2})", norm)
|
||
if not m:
|
||
return 0
|
||
try:
|
||
mm = int(m.group(1))
|
||
ss = int(m.group(2))
|
||
except ValueError:
|
||
return 0
|
||
return mm * 60 + ss
|
||
|
||
|
||
class Tee:
|
||
"""将 print 输出同时写入多个文件对象的简单工具类。"""
|
||
|
||
def __init__(self, *files):
|
||
self.files = files
|
||
|
||
def write(self, obj):
|
||
for f in self.files:
|
||
f.write(obj)
|
||
f.flush()
|
||
|
||
def flush(self):
|
||
for f in self.files:
|
||
f.flush()
|