|
|
@@ -10,9 +10,9 @@ idc = Blueprint("idc", __name__, url_prefix="/idc")
|
|
|
_MIN_SIZE = 46
|
|
|
_EXCLUDE_CHAR = "中国CHINA *#★☆"
|
|
|
__face_ptn = re.compile(
|
|
|
- r"[姓名]{0,2}(?P<name>.+?)[姓名]{0,2}"
|
|
|
+ r"[姓名]{0,2}(?P<name>.+?)[姓名]{0,2}" # 解决name在`姓名`之前，name字体较大
|
|
|
r"[性别]{1,2}(?P<gender>[男女])民族(?P<nation>.+?)"
|
|
|
- r"[出生]{1,2}(?P<year>\d{4})年(?P<month>\d+)月(?P<day>\d+)日"
|
|
|
+ r"([出生]{1,2}(?P<year>\d{4})年(?P<month>\d+)月(?P<day>\d+)日)?" # 测试中出现该行有较大概率未被识别
|
|
|
r"[住址]{1,2}(?P<addr>.+?)"
|
|
|
r"[公民身份号码]{1,6}(?P<idn>\d{17}[\dx])$",
|
|
|
re.I
|
|
|
@@ -29,16 +29,16 @@ def get_face_info(data_str: "str") -> "tuple[dict, bool]":
|
|
|
res = {"name": "", "gender": "", "nation": "", "birth": {"year": "", "month": "", "day": ""}, "addr": "", "idn": ""}
|
|
|
|
|
|
if match := __face_ptn.match(data_str):
|
|
|
+ res["idn"] = match.group("idn")
|
|
|
res["name"] = match.group("name")
|
|
|
res["gender"] = match.group("gender")
|
|
|
res["nation"] = match.group("nation")
|
|
|
res["birth"] = {
|
|
|
- "year": match.group("year"),
|
|
|
- "month": match.group("month"),
|
|
|
- "day": match.group("day")
|
|
|
+ "year": match.group("year") or res["idn"][6:10],
|
|
|
+ "month": match.group("month") or res["idn"][10:12],
|
|
|
+ "day": match.group("day") or res["idn"][12:14]
|
|
|
}
|
|
|
res["addr"] = match.group("addr")
|
|
|
- res["idn"] = match.group("idn")
|
|
|
return res, True
|
|
|
|
|
|
return res, False
|
Tinger