def tj_jyw_zbjggs(province, html, text, lines, table_line, table):
res = {}
# jhgq = re.findall('工期:(\d+)日历天', text)
# if not jhgq:
# jhgq = get_value_by_split_maohao(lines, '中标工期')
# if not jhgq:
# jhgq = None
# res['jhgq'] = jhgq
res['zbr'] = get_value_by_split_maohao(lines, '招标人')
res['zbdl'] = get_value_by_split_maohao(lines, '招标代理')
htjg = re.findall('投标报价:(.*?)元', text)
if not htjg:
text_list = ['中标标价', '中标价']
htjg = get_value_by_split_maohao2(lines, text_list)
res['htjg'] = htjg
gsmc = re.findall('投标人名称:(.*?)（', text)
if not gsmc:
text_list = ['中标单位', '中标人名称']
gsmc = get_value_by_split_maohao2(lines, text_list)
res['gsmc'] = gsmc
name, zsmc, zsbh = '', '', ''
persons = re.findall('项目经理:(.*?)，(.*?)（(.*?)）', text)
if persons:
name = [x[0] for x in persons]
zsmc = [x[1] for x in persons]
zsbh = [x[2] for x in persons]
res['name'] = name
res['zsmc'] = zsmc
res['zsbh'] = zsbh
return res
def extract_jsgm(province, html, text, lines, table_line, table):
result=[]
# try:
# result1 = re.findall(
# r'(招标范围及内容|规模|拟建规模|内容和规模|招标项目简介:|建设概况:|工程规模:|项目概况:|工程内容及规模:|项目规模:|建设规模.|建设内容及规模|建设内容:)(.*?)(2[.]2|2[.]3|2[.]4|2[.]5|招标范围|建设地点)',
# text, re.S)[0][1]
# result1 = re.sub(' ', '', result1).strip()
# except:
# pass
get_value_by_split_maohao(lines, '规模',result)
get_value_by_next_td(html,'规模',result)
res=get_finally_result(result)
return res
def extract_kbdd(province, html, text, lines, table_line, table):
result = []
# try:
# result1 = \
# re.findall(r'(资格审查地点:|开标地点:?|地点为:?|网上递交网址为|送达:|网址|开标方式:)(.*?)(）|\d+\.|。|，|\s)', text, re.S)[0][1]
# result1 = re.sub(' ', '', result1).strip().replace(':', '')
# if result1: result.append(result1)
# except:
# pass
get_value_by_split_maohao(lines, '开标地点',result)
get_value_by_next_td(html, '开标地点',result)
res = get_finally_result(result)
return res
def extract_jhgq(province, html, text, lines, table_line, table):
result = []
get_value_by_split_maohao(lines, '工期',result)
result3 = get_data_from_table(table, '工期')
if result3: result.append(result3[0])
res = get_finally_result(result)
if res:
try:
res = int(re.findall('\d+', res)[0])
except:
pass
return res
def extract_xmbh(province, html, text, lines, table_line, table):
result = []
if province == 'bt':
try:
res = get_data_from_table(table, '标段编号')[0]
if res:result.append(res)
except:
pass
pattern = r'(标段|项目|招标).*?编号:?([0-9a-zA-Z_-]+)'
res = re.findall(pattern, text)
if res: result.append(res[0][1])
get_value_by_next_td(html, '工程编号',result)
bt_get_value_by_next_td(html, '项目编号',result)
get_value_by_split_maohao(lines,'项目编号',result)
res = get_finally_result(result)
return res
def extract_company(province, html, text, lines, table_line, table):
text_list = ['中标候选人', '单位名称']
res = get_data_from_table2(table, text_list)
if not res:
try:
res = re.findall('中标候选人.*?投标人名称:(.*?)(\s|（)', text, re.S)[0][0]
except:
pass
if not res:
r = get_value_by_split_maohao(lines, '第一中标')
if r: res.append(r)
r = get_value_by_split_maohao(lines, '第二中标')
if r: res.append(r)
r = get_value_by_split_maohao(lines, '第三中标')
if r: res.append(r)
return res
def extract_htjg(province, html, text, lines, table_line, table):
res = None
try:
res = get_data_from_table(table, '元')
except:
pass
if not res:
res = get_value_by_split_maohao('中标标价', text)
return res
def extract_jsgm(province, html, text, lines, table_line, table):
result1, result2, result3 = '', '', ''
try:
result1 = re.findall(
r'(招标范围及内容|规模|拟建规模|内容和规模|招标项目简介:|建设概况:|工程规模:|项目概况:|工程内容及规模:|项目规模:|建设规模.|建设内容及规模|建设内容:)(.*?)(2[.]2|2[.]3|2[.]4|2[.]5|招标范围|建设地点)',
text, re.S)[0][1]
result1 = re.sub(' ', '', result1).strip()
except:
pass
result2 = get_value_by_split_maohao(lines, '规模')
if result2:
return result2
return result1
def extract_kbdd(province, html, text, lines, table_line, table):
result1, result2, result3 = '', '', ''
# try:
# result1 = \
# re.findall(r'(资格审查地点:|开标地点:?|地点为:?|网上递交网址为|送达:|开标方式:)(.*?)(）|\d+\.|。|，|\s)', text, re.S)[0][1]
# result1 = re.sub(' ', '', result1).strip().replace(':', '')
# except:
# pass
result2 = get_value_by_split_maohao(lines, '开标地点')
if not result2:
result2 = get_value_by_next_td(html, '开标地点')
if result2:
return result2
else:
return result1
def extract_jbqk(province, html, text, lines, table_line, table):
result1, result2, result3 = '', '', ''
# try:
# result1 = re.findall(r'(项目概括|.与招标范围|项目概况.)(.*?)(资格人要求|.资格要求|.资格及要求|.业绩要求)', text, re.S)[0][1]
# result1 = re.sub(' ', '', result1).strip()
# except:
# pass
result2 = get_chapter_content(lines, '项目概况')
if not result2:
result2 = get_chapter_content(lines, '招标范围')
if not result2:
result2 = get_value_by_split_maohao(lines, '概况')
# result2+=get_value_by_split_maohao(lines, '招标范围')
if result2:
return result2
else:
return result1
def extract_zjly(province, html, text, lines, table_line, table):
result1, result2, result3 = '', '', ''
try:
result1 = re.findall('建设资金|建设资金来自|建设资金来源|资金来源为[:]|资金由(.*?)\s|[，,]|。',
text)[0].strip()
if len(result1) <= 50:
result1 = re.sub(' ', '', result1).replace('为', ' ').replace(
':', ' ').replace('来自', '').strip()
else:
result1 = ''
except:
pass
result2 = get_value_by_split_maohao(lines, '资金来源')
if result2:
if ':' not in result2:
return result2
else:
return result1
def extract_zbtj(province, html, text, lines, table_line, table):
result1, result2, result3 = '', '', ''
try:
result1 = re.findall(
r'招标条件(.*?)(.招标范围|项目概况、招标范围及发包价|项目概况与招标范围|工程概况|项目概括)', text,
re.S)[0][0]
result1 = re.sub(' ', '', result1).strip()
except:
pass
result2 = get_chapter_content(lines, '招标条件')
if not result2:
result2 = get_value_by_split_maohao(lines, '招标条件')
if not result2:
result2 = get_chapter_content(lines, '投标条件')
if result2:
if ':' not in result2:
return result2
else:
return result1
def extract_kbsj(province, html, text, lines, table_line, table):
res = ''
result1, result2, result3 = None, None, None
try:
result1 = \
re.findall(r'(开标时间:?|时间为:?)(.*?)(）|\d+\.|。|，|\s)', text, re.S)[0][1]
result1 = result1.strip().replace(':', '')
except:
try:
result1 = re.findall('于(.*?)进行开标', text)[0]
except:
pass
result2 = get_value_by_next_td(html, '开标时间')
if not result2:
result2 = get_value_by_split_maohao(lines, '开标时间')
if not res:
if result2:
res = result2
else:
res = result1
res = deal_date_str(res)
return res
def extract_tb_jzrq(province, html, text, lines, table_line, table):
res = get_value_by_split_maohao(lines, '投标截止')
if not res:
res = get_value_by_next_td(html, '投标截止')
res = deal_date_str(res)
return res
def extract_jzrq(province, html, text, lines, table_line, table):
res = get_value_by_split_maohao(lines, '截止日期')
res = deal_date_str(res)
return res
