|
|
@@ -685,7 +685,7 @@ class PREMPredict():
|
|
|
elif re.search('尊敬的供应商：', text):
|
|
|
label = 0
|
|
|
values[label] = 0.501
|
|
|
- elif re.search('[^\w]中标候选人：', text) and re.search('[1一]', text) == None: #修复第4以上的预测错为中标人
|
|
|
+ elif re.search('[^\w]中标候选人', text[:15]) and re.search('[1一]', text[:15]) == None: #修复第4以上的预测错为中标人
|
|
|
label = 5
|
|
|
values[label] = 0.5
|
|
|
elif re.search('是否中标：是，供应商', text) and label == 5:
|
|
|
@@ -1156,8 +1156,8 @@ class RoleRulePredictor():
|
|
|
self.pattern_winTenderer_left = "(?P<winTenderer_left>(乙|承做|施工|供货|承包|承建|承租|竞得|受让|签约)(候选)?(人|单位|机构|供应商|方|公司|厂商|商)[：:是为]+$|" \
|
|
|
"(选定单位|指定的中介服务机构|实施主体|承制单位|供方)[：:是为]+$|((评审结果|名次|排名|中标结果)[:：]*第?[一1]名?)[：:是为]+$|" \
|
|
|
"单一来源(采购)?(供应商|供货商|服务商|方式向)$|((中标|成交)(结果|信息))[：:是为]+$|(供应|供货|承销|承保|承包|承接|服务|实施|合作)(机构|单位|商|方)(名称)?[：:是为]+$)"
|
|
|
- self.pattern_winTenderer_left_w0 = "(?P<winTenderer_left_w1>(，|。|^)((中标(投标)?|中选|中价|成交)(候选)?(人|单位|机构|供应商|客户|方|公司|厂商|商)|第?[一1]名)(名称)?[,，]?([(（]按综合排名排序[)）])?[：:,，]$)" #解决表头识别不到加逗号情况，需前面为，。空
|
|
|
- self.pattern_winTenderer_left_w1 = "(?P<winTenderer_left_w1>(中标|中选|中价|成交|入选)(候选)?(人|单位|机构|供应商|客户|方|公司|厂商|商)(名称)?([(（]按综合排名排序[)）])?[：:是为]+$)" #取消逗号 并拒绝执行改进计划的供应商，华新水泥将可能终止与其合作关系
|
|
|
+ self.pattern_winTenderer_left_w0 = "(?P<winTenderer_left_w1>(，|。|^)((中标(投标)?|中选|中价|成交)(人|单位|机构|供应商|客户|方|公司|厂商|商)|第?[一1]名)(名称)?[,，]?([(（]按综合排名排序[)）])?[：:,，]$)" #解决表头识别不到加逗号情况，需前面为，。空
|
|
|
+ self.pattern_winTenderer_left_w1 = "(?P<winTenderer_left_w1>(中标|中选|中价|成交|入选)(人|单位|机构|供应商|客户|方|公司|厂商|商)(名称)?([(（]按综合排名排序[)）])?[：:是为]+$)" #取消逗号 并拒绝执行改进计划的供应商，华新水泥将可能终止与其合作关系 # 中标候选人不能作为中标
|
|
|
# self.pattern_winTenderer_center = "(?P<winTenderer_center>第[一1].{,20}[是为]((中标|中选|中价|成交|施工)(人|单位|机构|供应商|公司)|供应商)[：:是为])"
|
|
|
# self.pattern_winTenderer_right = "(?P<winTenderer_right>(^[是为\(]((采购(供应商|供货商|服务商)|(第[一1]|预)?(拟?(中标|中选|中价|成交)(候选)?(人|单位|机构|供应商|公司|厂商)))))|^(报价|价格)最低，确定为本项目成交供应商)"
|
|
|
self.pattern_winTenderer_right = "(?P<winTenderer_right>(^[是为]((采购|中标)(供应商|供货商|服务商)|(第[一1]|预)?(拟?(中标|中选|中价|成交)(候选)?(人|单位|机构|供应商|公司|厂商)))|" \
|
|
|
@@ -2580,7 +2580,7 @@ class ProductAttributesPredictor():
|
|
|
if order_begin_year>=2050 or order_end_year>=2050:
|
|
|
order_begin = order_end = ""
|
|
|
# print(product,demand,budget,order_begin)
|
|
|
- if product!= "" and demand != "" and budget!="" and order_begin != "":
|
|
|
+ if product!= "" and demand != "" and budget!="" and order_begin != "" and len(budget)<15: # 限制金额小于15位数的才要
|
|
|
link = {'project_name': product, 'product': [], 'demand': demand, 'budget': budget,
|
|
|
'order_begin': order_begin, 'order_end': order_end}
|
|
|
if link not in demand_link:
|
|
|
@@ -2607,7 +2607,7 @@ class ProductAttributesPredictor():
|
|
|
if len(set([re.sub('[:：]','',td) for td in tds]) & self.header_set) > len(tds) * 0.2:
|
|
|
# if len(set(tds) & self.header_set) > len(tds) * 0.2:
|
|
|
header_dic, found_header, header_list, header_list2 = self.find_header(tds, self.p1, self.p2)
|
|
|
- if found_header:
|
|
|
+ if found_header and len(headers)<1: # 只保留出现的第一个表头
|
|
|
headers.append('_'.join(header_list))
|
|
|
headers_demand.append('_'.join(header_list2))
|
|
|
header_colnum = len(tds)
|
|
|
@@ -2653,7 +2653,7 @@ class ProductAttributesPredictor():
|
|
|
brand = ""
|
|
|
if id5 != "":
|
|
|
if re.search('\w', tds[id5]):
|
|
|
- specs = tds[id5]
|
|
|
+ specs = tds[id5][:500] # 限制最多500字
|
|
|
else:
|
|
|
specs = ""
|
|
|
if id6 != "":
|
|
|
@@ -2676,6 +2676,9 @@ class ProductAttributesPredictor():
|
|
|
order_time = tds[id8].strip()
|
|
|
order_begin, order_end = self.fix_time(order_time, html, page_time)
|
|
|
if quantity != "" or unitPrice != "" or brand != "" or specs != "":
|
|
|
+ if len(unitPrice) > 15 or len(product)>100: # 单价大于15位数或 产品名称长于100字
|
|
|
+ i += 1
|
|
|
+ continue
|
|
|
link = {'product': product, 'quantity': quantity, 'unitPrice': unitPrice,
|
|
|
'brand': brand[:50], 'specs':specs}
|
|
|
if link not in product_link:
|
|
|
@@ -2683,7 +2686,7 @@ class ProductAttributesPredictor():
|
|
|
mat = re.match('([0-9.,]+)[(（]?\w{,3}[)）]?$', link['quantity'])
|
|
|
if link['unitPrice'] != "" and mat:
|
|
|
try:
|
|
|
- total_product_money += float(link['unitPrice'])*float(mat.group(1).replace(',', ''))
|
|
|
+ total_product_money += float(link['unitPrice'])*float(mat.group(1).replace(',', '')) if float(mat.group(1).replace(',', ''))<50000 else 0
|
|
|
except:
|
|
|
log('产品属性单价数量相乘出错, 单价： %s, 数量： %s'%(link['unitPrice'], link['quantity']))
|
|
|
if order_begin != "" and order_end != "":
|
|
|
@@ -2804,88 +2807,88 @@ class ProductAttributesPredictor():
|
|
|
headers.append('_'.join(header_list))
|
|
|
headers_demand.append('_'.join(header_list2))
|
|
|
header_col.append('_'.join(tmp_head_list))
|
|
|
- # print('header_dic: ',header_dic)
|
|
|
- id1 = header_dic.get('名称', "")
|
|
|
- id2 = header_dic.get('数量', "")
|
|
|
- id3 = header_dic.get('单价', "")
|
|
|
- id4 = header_dic.get('品牌', "")
|
|
|
- id5 = header_dic.get('规格', "")
|
|
|
-
|
|
|
- id6 = header_dic.get('需求', "")
|
|
|
- id7 = header_dic.get('预算', "")
|
|
|
- id8 = header_dic.get('时间', "")
|
|
|
- if re.search('[a-zA-Z\u4e00-\u9fa5]', deal_list[id1]) and deal_list[id1] not in self.header_set and \
|
|
|
- re.search('备注|汇总|合计|总价|价格|金额|公司|附件|详见|无$|xxx', deal_list[id1]) == None:
|
|
|
- product = deal_list[id1]
|
|
|
- if id2 != "":
|
|
|
- if re.search('\d+|[壹贰叁肆伍陆柒捌玖拾一二三四五六七八九十]', deal_list[id2]):
|
|
|
- quantity = deal_list[id2]
|
|
|
- else:
|
|
|
- quantity = ""
|
|
|
- if id3 != "":
|
|
|
- if re.search('\d+|[零壹贰叁肆伍陆柒捌玖拾佰仟萬億十百千万亿元角分]{3,}', deal_list[id3]):
|
|
|
- _unitPrice = deal_list[id3]
|
|
|
- re_price = re.findall("[零壹贰叁肆伍陆柒捌玖拾佰仟萬億圆十百千万亿元角分]{3,}|\d[\d,]*(?:\.\d+)?万?",_unitPrice)
|
|
|
- if re_price:
|
|
|
- _unitPrice = re_price[0]
|
|
|
- if '万元' in header_list[2] and '万' not in _unitPrice:
|
|
|
- _unitPrice += '万元'
|
|
|
- unitPrice = str(getUnifyMoney(_unitPrice))
|
|
|
- if id4 != "":
|
|
|
- if re.search('\w', deal_list[id4]):
|
|
|
- brand = deal_list[id4]
|
|
|
- else:
|
|
|
- brand = ""
|
|
|
- if id5 != "":
|
|
|
- if re.search('\w', deal_list[id5]):
|
|
|
- specs = deal_list[id5]
|
|
|
- else:
|
|
|
- specs = ""
|
|
|
- if id6 != "":
|
|
|
- if re.search('\w', deal_list[id6]):
|
|
|
- demand = deal_list[id6]
|
|
|
- else:
|
|
|
- demand = ""
|
|
|
- if id7 != "":
|
|
|
- if re.search('\d+|[零壹贰叁肆伍陆柒捌玖拾佰仟萬億十百千万亿元角分]{3,}', deal_list[id7]):
|
|
|
- _budget = deal_list[id7]
|
|
|
- re_price = re.findall("[零壹贰叁肆伍陆柒捌玖拾佰仟萬億圆十百千万亿元角分]{3,}|\d[\d,]*(?:\.\d+)?万?",_budget)
|
|
|
- if re_price:
|
|
|
- _budget = re_price[0]
|
|
|
- if '万元' in header_list2[2] and '万' not in _budget:
|
|
|
- _budget += '万元'
|
|
|
- budget = str(getUnifyMoney(_budget))
|
|
|
-
|
|
|
- if id8 != "":
|
|
|
- if re.search('\w', deal_list[id8]):
|
|
|
- order_time = deal_list[id8].strip()
|
|
|
- order_begin, order_end = self.fix_time(order_time, html, page_time)
|
|
|
- # print(quantity,unitPrice,brand,specs)
|
|
|
- if quantity != "" or unitPrice != "" or brand != "" or specs != "":
|
|
|
- link = {'product': product, 'quantity': quantity, 'unitPrice': unitPrice,
|
|
|
- 'brand': brand[:50], 'specs': specs}
|
|
|
- if link not in product_link:
|
|
|
- product_link.append(link)
|
|
|
- # mat = re.match('([0-9.,]+)[(（]?\w{,3}[)）]?$', link['quantity'])
|
|
|
- # if link['unitPrice'] != "" and mat:
|
|
|
- # try:
|
|
|
- # total_product_money += float(link['unitPrice']) * float(
|
|
|
- # mat.group(1).replace(',', ''))
|
|
|
- # except:
|
|
|
- # log('产品属性单价数量相乘出错, 单价： %s, 数量： %s' % (
|
|
|
- # link['unitPrice'], link['quantity']))
|
|
|
- if order_begin != "" and order_end != "":
|
|
|
- order_begin_year = int(order_begin.split("-")[0])
|
|
|
- order_end_year = int(order_end.split("-")[0])
|
|
|
- # 限制附件错误识别时间
|
|
|
- if order_begin_year >= 2050 or order_end_year >= 2050:
|
|
|
- order_begin = order_end = ""
|
|
|
- # print(budget, order_time)
|
|
|
- if budget != "" and order_time != "":
|
|
|
- link = {'project_name': product, 'product': [], 'demand': demand, 'budget': budget,
|
|
|
- 'order_begin': order_begin, 'order_end': order_end}
|
|
|
- if link not in demand_link:
|
|
|
- demand_link.append(link)
|
|
|
+ # print('header_dic: ',header_dic)
|
|
|
+ id1 = header_dic.get('名称', "")
|
|
|
+ id2 = header_dic.get('数量', "")
|
|
|
+ id3 = header_dic.get('单价', "")
|
|
|
+ id4 = header_dic.get('品牌', "")
|
|
|
+ id5 = header_dic.get('规格', "")
|
|
|
+
|
|
|
+ id6 = header_dic.get('需求', "")
|
|
|
+ id7 = header_dic.get('预算', "")
|
|
|
+ id8 = header_dic.get('时间', "")
|
|
|
+ if re.search('[a-zA-Z\u4e00-\u9fa5]', deal_list[id1]) and deal_list[id1] not in self.header_set and \
|
|
|
+ re.search('备注|汇总|合计|总价|价格|金额|公司|附件|详见|无$|xxx', deal_list[id1]) == None:
|
|
|
+ product = deal_list[id1]
|
|
|
+ if id2 != "":
|
|
|
+ if re.search('\d+|[壹贰叁肆伍陆柒捌玖拾一二三四五六七八九十]', deal_list[id2]):
|
|
|
+ quantity = deal_list[id2]
|
|
|
+ else:
|
|
|
+ quantity = ""
|
|
|
+ if id3 != "":
|
|
|
+ if re.search('\d+|[零壹贰叁肆伍陆柒捌玖拾佰仟萬億十百千万亿元角分]{3,}', deal_list[id3]):
|
|
|
+ _unitPrice = deal_list[id3]
|
|
|
+ re_price = re.findall("[零壹贰叁肆伍陆柒捌玖拾佰仟萬億圆十百千万亿元角分]{3,}|\d[\d,]*(?:\.\d+)?万?",_unitPrice)
|
|
|
+ if re_price:
|
|
|
+ _unitPrice = re_price[0]
|
|
|
+ if '万元' in header_list[2] and '万' not in _unitPrice:
|
|
|
+ _unitPrice += '万元'
|
|
|
+ unitPrice = str(getUnifyMoney(_unitPrice))
|
|
|
+ if id4 != "":
|
|
|
+ if re.search('\w', deal_list[id4]):
|
|
|
+ brand = deal_list[id4]
|
|
|
+ else:
|
|
|
+ brand = ""
|
|
|
+ if id5 != "":
|
|
|
+ if re.search('\w', deal_list[id5]):
|
|
|
+ specs = deal_list[id5]
|
|
|
+ else:
|
|
|
+ specs = ""
|
|
|
+ if id6 != "":
|
|
|
+ if re.search('\w', deal_list[id6]):
|
|
|
+ demand = deal_list[id6]
|
|
|
+ else:
|
|
|
+ demand = ""
|
|
|
+ if id7 != "":
|
|
|
+ if re.search('\d+|[零壹贰叁肆伍陆柒捌玖拾佰仟萬億十百千万亿元角分]{3,}', deal_list[id7]):
|
|
|
+ _budget = deal_list[id7]
|
|
|
+ re_price = re.findall("[零壹贰叁肆伍陆柒捌玖拾佰仟萬億圆十百千万亿元角分]{3,}|\d[\d,]*(?:\.\d+)?万?",_budget)
|
|
|
+ if re_price:
|
|
|
+ _budget = re_price[0]
|
|
|
+ if '万元' in header_list2[2] and '万' not in _budget:
|
|
|
+ _budget += '万元'
|
|
|
+ budget = str(getUnifyMoney(_budget))
|
|
|
+
|
|
|
+ if id8 != "":
|
|
|
+ if re.search('\w', deal_list[id8]):
|
|
|
+ order_time = deal_list[id8].strip()
|
|
|
+ order_begin, order_end = self.fix_time(order_time, html, page_time)
|
|
|
+ # print(quantity,unitPrice,brand,specs)
|
|
|
+ if quantity != "" or unitPrice != "" or brand != "" or specs != "":
|
|
|
+ link = {'product': product, 'quantity': quantity, 'unitPrice': unitPrice,
|
|
|
+ 'brand': brand[:50], 'specs': specs}
|
|
|
+ if link not in product_link:
|
|
|
+ product_link.append(link)
|
|
|
+ # mat = re.match('([0-9.,]+)[(（]?\w{,3}[)）]?$', link['quantity'])
|
|
|
+ # if link['unitPrice'] != "" and mat:
|
|
|
+ # try:
|
|
|
+ # total_product_money += float(link['unitPrice']) * float(
|
|
|
+ # mat.group(1).replace(',', ''))
|
|
|
+ # except:
|
|
|
+ # log('产品属性单价数量相乘出错, 单价： %s, 数量： %s' % (
|
|
|
+ # link['unitPrice'], link['quantity']))
|
|
|
+ if order_begin != "" and order_end != "":
|
|
|
+ order_begin_year = int(order_begin.split("-")[0])
|
|
|
+ order_end_year = int(order_end.split("-")[0])
|
|
|
+ # 限制附件错误识别时间
|
|
|
+ if order_begin_year >= 2050 or order_end_year >= 2050:
|
|
|
+ order_begin = order_end = ""
|
|
|
+ # print(budget, order_time)
|
|
|
+ if budget != "" and order_time != "":
|
|
|
+ link = {'project_name': product, 'product': [], 'demand': demand, 'budget': budget,
|
|
|
+ 'order_begin': order_begin, 'order_end': order_end}
|
|
|
+ if link not in demand_link:
|
|
|
+ demand_link.append(link)
|
|
|
|
|
|
if len(product_link) > 0:
|
|
|
attr_dic = {'product_attrs': {'data': product_link, 'header': list(set(headers)), 'header_col': list(set(header_col))}}
|
|
|
@@ -2958,7 +2961,7 @@ class DocChannel():
|
|
|
self.life_dic = {
|
|
|
'采购意向': '采购意向|招标意向|选取意向|意向公告|意向公示',
|
|
|
'招标预告': '(预计|计划)(采购|招标)(时间|日期)|采购(计划编号|需求方案|预告|预案)|(预|需求)公示|需求(方案|信息|论证|公告|公示)',
|
|
|
- '招标公告': '(采购|招标|竞选|报名)条件|报名(时间|流程|方法|\w{,5}材料)|参加竞价采购交易资格|(申请人|投标人|供应商|报价人|参选人)的?资格要求|获取(采购|招标|询价|议价|竞价|比价|比选|遴选|邀请|邀标|磋商|洽谈|约谈|谈判|竞谈|应答)文件|(采购|招标|询价|议价|竞价|比价|比选|遴选|邀请|邀标|磋商|洽谈|约谈|谈判|竞谈|应答)文件的?(获取|领取)',
|
|
|
+ '招标公告': '(采购|招标|竞选|报名)条件|报名(时间|流程|方法|要求|\w{,5}材料)[：\s]|参加竞价采购交易资格|(申请人|投标人|供应商|报价人|参选人)的?资格要求|获取(采购|招标|询价|议价|竞价|比价|比选|遴选|邀请|邀标|磋商|洽谈|约谈|谈判|竞谈|应答)文件|(采购|招标|询价|议价|竞价|比价|比选|遴选|邀请|邀标|磋商|洽谈|约谈|谈判|竞谈|应答)文件的?(获取|领取)',
|
|
|
'资审结果': '资审及业绩公示|资审结果及业绩|资格后审情况报告|资格(后审|预审|审查)结果(公告|公示)|(预审|审查)工作已经?结束|未通过原因', #|资格
|
|
|
'招标答疑': '现澄清(为|如下)|答疑补遗|澄清内容如下|第[0-9一二三四五]次澄清|答疑澄清|(最高(投标)?限价|控制价|拦标价)公示', # |异议的回复
|
|
|
'公告变更': '第[\d一二]次变更|(更正|变更)(公告|公示|信息|内容|事项|原因|理由|日期|时间|如下)|原公告((主要)?(信息|内容)|发布时间)|(变更|更正)[前后]内容|现?在?(变更|更正|修改|更改)(内容)?为|(公告|如下|信息|内容|事项|结果|文件|发布|时间|日期)(更正|变更)',
|
|
|
@@ -2970,7 +2973,8 @@ class DocChannel():
|
|
|
# |确定成交供应商[：，\s]
|
|
|
'合同公告': '合同(公告|公示|信息|内容)|合同(编号|名称|主体|基本情况|签订日期)|(供应商乙方|乙方供应商)：|合同总?金额',
|
|
|
'废标公告': '(终止|中止|废标|流标|失败|作废|异常|撤销)(结果)?(公告|公示|招标|采购|竞价)|(谈判结果为|结果类型)：?废标|((本|该)(项目|标段|合同|合同包|采购包|次)\w{,5})((失败|终止|流标|废标)|予以废标|(按|做|作)?(流标|废标)处理)|(采购|招标|询价|议价|竞价|比价|比选|遴选|邀请|邀标|磋商|洽谈|约谈|谈判|竞谈|应答|项目)(终止|中止|废标|流标|失败|作废|异常|撤销)',
|
|
|
- '废标公告2': '(无效|中止|终止|废标|流标|失败|作废|异常|撤销)的?(原因|理由)|本项目因故取消|本(项目|次)(公开)?\w{2}失败|已终止\s*原因：|(人|人数|供应商|单位)(不足|未达\w{,3}数量)|已终止|不足[3三]家|无（废标）|成交情况：\s*[流废]标'
|
|
|
+ '废标公告2': '(无效|中止|终止|废标|流标|失败|作废|异常|撤销)的?(原因|理由)|本项目因故取消|本(项目|次)(公开)?\w{2}失败|已终止\s*原因：|(人|人数|供应商|单位)(不足|未达\w{,3}数量)|已终止|不足[3三]家|无（废标）|成交情况：\s*[流废]标',
|
|
|
+ '废标公告neg': '超过此报价将作为[废流]标处理|否则按[废流]标处理|终止规则：|视为流标'
|
|
|
}
|
|
|
self.title_life_dic = {
|
|
|
'采购意向': '采购意向|招标意向|选取意向|意向公告|意向公示|意向公开',
|
