def Querst_request():
"""通过GET网页获取网页的URL,并且更新库内的url值
"""
session = returns_session('Sqlextend')()
to = ot_baidu_search_info
data = session.query(to).filter('id > 694').all()
if not data:
return
for item in data:
new = ot_baidu_search_info()
new.id = item.id
while True:
try:
r_url = get(item.url)
break
except:
time.sleep(1)
print 'retry sleep 1'
if r_url.ok:
new.url = r_url.request.url
print 'Update old_url = %s, New_url = %s' % (item.url, new.url)
session.merge(new)
try:
session.commit()
except:
continue
else:
print item.id
session.close()
def Web_Api_Error(Judgmentid):
"""提供WEB API接口使用 GET方法
"""
Session_to = returns_session('Judgment')
session = Session_to()
result = ot_judge_base
result_data = session.query(result).filter('id = %s' % Judgmentid).first()
if not result_data:
return {'Error': u'没有找到文书ID的相应记录', 'status': -3}
if 'openlaw' in result_data.url:
to = Open
else:
to = Otraw
try:
data = session.query(to).filter(
'id = %s' % result_data.parent_id).first()
except SQLAlchemyError:
return {'Error': u'相关的详细数据', 'status': -4}
finally:
session.close()
if data:
analy = Analyse()
analy.text = data.content_all
_header, part, content, case_sign = analy.split_to_four_parts()
ero = Judgment_checking(_header, part, content, case_sign)
#: 检查案由
ero.Checking_anyou(result_data.anyou.decode('utf8'),
result_data.type.decode('utf8'))
#: 检查原告被告
ero.Checking_people(result_data.plaintiff.decode('utf8'),
result_data.defendant.decode('utf8'))
#: 检查原告被告律师
ero.Checking_lawyer(result_data.plaintiff_lawyers.decode('utf8'),
result_data.defendant_lawyers.decode('utf8'))
#: 检查署名信息
ero.Checking_sign()
#: 检查地区信息
ero.Checking_area(result_data.areacode,
result_data.department.decode('utf8'))
#: 审理机构检查
ero.Checking_department(result_data.department.decode('utf8'))
ero.errors['status'] = 0
if ero.errors:
return ero.errors
else:
return {'Error': u'没有错误信息', 'status': 0}
else:
return {'Error': u'没有找到相关的记录', 'status': -4}
def Web_Api_On_Check(**keyword):
"""提供POST方法， 可供分析字段
"""
Session_to = returns_session('Judgment')
session = Session_to()
result = ot_judge_base
result_data = session.query(result).filter(
'id = %s' % keyword['pid']).first()
if not result_data:
return {'Error': u'没有找到文书ID的相应记录', 'status': -3}
if 'openlaw' in result_data.url:
to = Open
else:
to = Otraw
try:
data = session.query(to).filter(
'id = %s' % result_data.parent_id).first()
except SQLAlchemyError:
return {'Error': u'相关的详细数据', 'status': -4}
finally:
session.close()
if data:
#: 载入分析方法
analy = Analyse()
analy.text = data.content_all
#: 将文本分为4个段落
_header, part, content, case_sign = analy.split_to_four_parts()
ero = Judgment_checking(_header, part, content, case_sign)
#: 检查案由
ero.Checking_anyou(keyword['anyou'], result_data.type)
#: 检查原告被告
ero.Checking_people(keyword['plaintiff'], keyword['defendant'])
#: 检查原告被告律师
ero.Checking_lawyer(
keyword['plaintiff_lawyers'], keyword['defendant_lawyers'])
#： 载入发过来的署名信息买，存入一个字典当中
keys = {}
keys['chief_judge'] = keyword['chief_judge']
keys['judge'] = keyword['judge']
keys['acting_judges'] = keyword['acting_judges']
keys['clerk'] = keyword['clerk']
#: 检查署名信息
#: ero.Checking_sign(keys) 可不传递keys传递时会给出更加精确的判断
ero.Checking_sign(keys)
#: 检查地区信息
ero.Checking_area(
keyword['areacode'], result_data.department.decode('utf8'))
if ero.errors:
# status=0 必须放在这里！不然其他程序调用时就不是那么好判断了
ero.errors['status'] = 0
return ero.errors
else:
return {'Error': u'没有错误信息', 'status': 0}
else:
return {'Error': u'没有找到相关的记录', 'status': -4}
上海婚姻律师 上海离婚律师 上海离婚纠纷律师
上海劳动纠纷律师 上海劳动仲裁律师
上海刑事辩护律师 上海刑事律师
上海公司律师 上海公司纠纷律师 上海股权纠纷律师
上海合同律师 上海合同纠纷律师
上海房产律师 上海房产纠纷律师 上海房地产律师
上海交通事故律师
上海债权债务律师 上海债务律师 上海债务纠纷律师 上海债权律师
上海损害赔偿律师
上海知识产权律师 上海商标律师 上海专利律师
上海医疗纠纷律师 上海医疗损害律师 上海医疗事故律师
""".split()
keys.extend(plus)
for item in plus:
keys.append(item.replace(u'上海', u'北京'))
session = returns_session('Sqlextend')()
to = ot_baidu_search_info
diff = session.query(to.key).group_by(to.key).all()
#keys = keys - dif
if not diff:
pass
else:
for item in diff:
keys.remove(item[0])
#keys = [u'北京律师', u'上海律师']
# Querst_request()
Search = BD_Search_Request(keys)
# Search.Format_url_to_domain()
Search.Querst_request()
