def to_ot_judge_base(self, old):
""" 抽取字段 """
#import pdb
# pdb.set_trace()
print old.url
# if self.p_type and old.id > self.pages:
# os._exit(0)
if MODLE == "CourtGovCnMergeProcesserLawyer":
data = {"max": old.id, "up": DATAS[2]}
id_or_name(fname="./keyword/id.json", mode="write", indata=data)
if MODLE == "CourtGovCnMergeProcesserLawyerUp":
if DATAS[1] < old.id:
print "更新模式父id已大于普通模式下的父id, 请使用非更新模式进行抽取!"
os._exit(0)
elif DATAS[1] >= old.id:
data = {"max": DATAS[1], "up": old.id}
id_or_name(
fname="./keyword/id.json", mode="write", indata=data)
# 如果此id已抽取过, 则直接返回
if old.id in OLD_ID:
return
for attr in ('content', 'case_sign', 'case_type', 'department', 'end_date'):
if getattr(old, attr) is None:
return
# 只分析以下类型的裁判文书
if old.case_type not in self.case_mode:
return
#import pdb
# pdb.set_trace()
# 如果没有匹配的律师, 则直接返回
result = self.check_lawyer(old)
if not result[0]:
return
else:
OLD_ID.add(old.id)
data = {"id": list(OLD_ID)}
id_or_name(fname="./keyword/oldid.json", mode="write", indata=data)
new = ot_judge_base()
new.content = '<p>' + '</p><p>'.join(old.content.split('\n')) + '</p>'
new.content_md5 = md5(new.content.encode('utf8')).hexdigest()
new.case_sign = '<p>' + \
'</p><p>'.join(old.case_sign.split('\n')) + '</p>'
new.case_type = old.case_type
for item in TYPE_ID:
if item["name"] == new.case_type.encode("gbk"):
new.case_type_id = item["value"]
break
new.type = new.case_type[:-3]
# 如果是仲裁,那属于民事
if new.type == u'仲裁':
new.type = u'民事'
new.case_number = old.case_number
new.title = re.split("\n", old.content_all)[0].strip()
ff = False
title = new.title
# 先把标题中裁判文书类型文字去掉
for item in self.case_mode:
if item in title:
title = title.replace(item, "")
for ca in self.cause_of_actions:
if ca in title:
new.anyou = ca
ff = True
break
if not ff:
for ca in self.cause_of_actions:
if ca in old.content_all:
new.anyou = ca
break
else:
return
new.anyou_id = self.cause_of_action_id[new.anyou]
new.department = old.department
new.chief_judge = old.chief_judge
new.judge = old.judge
new.acting_judges = old.acting_judges
new.clerk = old.clerk
new.plaintiff = ';'.join(
u"%s:%s:%s" % client for client in old.clients_attr[u'原告'])
new.plaintiff_lawyers = ';'.join(
u"%s:%s" % lawyer for lawyer in old.lawyers_attr[u'原告'])
new.defendant = ';'.join(
u"%s:%s:%s" % client for client in old.clients_attr[u'被告'])
new.defendant_lawyers = ';'.join(
u"%s:%s" % lawyer for lawyer in old.lawyers_attr[u'被告'])
new.procedure = old.procedure
new.end_date = arrow.get(old.end_date, 'Asia/Shanghai').timestamp
# 分析地区
area = self.area_parse.ident(new.department.encode('gbk'))
if area:
new.areacode = area['areano']
new.url = old.referer
#import pdb
# pdb.set_trace()
# 把某某都去掉
# new.replace_data = json.dumps(
# {k: v for k, v in old.replace_data.iteritems() if not re.match(ur'.*(某|X|x|\*).*', k)}
#)
dic = {}
for k, v in old.replace_data.iteritems():
if not re.match(ur".*(某|X|x|\*).*", k):
dic.update({k: v})
from pybamboo import Bamboo
import json
from flcrawl.config import DB_URL
from flcrawl.processers.judgment.lawyer import id_or_name, local_lawyers, lawyers
bamboo = Bamboo()
LAWYER_TYPE = (u"委托代理人", u"代理人", u"指定代理人", u"指定委托代理人", u"指定辩护人", u"辩护人")
MODLE = sys.argv[2].split(".")[-1]
#import pdb
# pdb.set_trace()
DATAS = lawyers(mode=MODLE)
OLD_ID = id_or_name(fname="./keyword/oldid.json", mode="read")
OLD_ID = set(OLD_ID["id"])
def check_case_type_id():
""" 216库中查找案件类型的id """
dbarg = {"sql_host": "192.168.1.216", "sql_user": "******",
"sql_db": "judge_center", "sql_pass": "******", "sql_port": 33669}
sql = "select name, value from ot_judge_dict"
res, desc = dbtool.exec_sql(dbarg, sql)
if desc and desc[0]:
return desc
TYPE_ID = check_case_type_id()
