def extract_zbr(province, html, text, lines, table_line, table):
result = []
text_list = ['招标人', '招标单位']
get_value_by_split_maohao2(lines, text_list,result)
texts=['建设单位','招标单位']
r = get_value_by_next_td2(html, texts,result)
res = get_finally_result(result)
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_xmmc(province, html, text, lines, table_line, table):
result = []
# 项目及标段名称
texts = ['项目名称', '标段名称']
r1 = get_value_by_split_maohao2(lines, texts)
if ':' not in r1: result.append(r1)
get_value_by_table_line2(table_line, texts,result)
get_value_by_next_td(html, '项目名称',result)
get_value_by_next_td(html, '工程名称',result)
try:
result1 = \
re.findall(r'(项目名称:|标段名称:)(.*?)(\s|，|。)', text, re.S)[0][1].strip()
if len(result1) < 50:
result1 = re.sub(' ', '', result1).replace('为', ' ').replace('：', ' ').strip()
result.append(result1)
except:
pass
res = get_finally_result(result)
return res
def extract_zbdl(province, html, text, lines, table_line, table):
result = []
try:
result1 = \
re.findall(r'(招标代理机构是:?|招?标?代理机?构?单?位?:|招标代理:|招标代理为)(.*?)(\s|，|。|地|统一|\s$|地.{0.4}址)', text,
re.S)[0][1].strip()
if len(result1) < 50:
result1 = re.sub(' ', '', result1).replace('为', ' ').replace('：', ' ').strip()
if result1:result.append(result1)
except:
pass
texts = ['招标代理单位', '代理单位', '代理机构', '招标代理']
result2 = get_value_by_split_maohao2(lines, texts)
if result2:
if ':' not in result2:
result.append(result2)
texts = ['招标代理单位', '代理单位', '代理机构', '招标代理']
get_value_by_next_td2(lines, texts,result)
res = get_finally_result(result)
return res
def extract_gsq(province, html, text, lines, table_line, table):
result = []
try:
r = re.findall('公示期为(.*?)(,|，|。)', text)[0][0]
if r: result.append(r)
except:
pass
try:
gsq_start = get_value_by_next_td(html, '公示开始时间')
gsq_end = get_value_by_next_td(html, '公示截止时间')
if not gsq_end:
gsq_end = get_value_by_next_td(html, '公示结束时间')
if gsq_start:
gsq = gsq_start + '-' + gsq_end
result.append(gsq)
except:
pass
texts=['公示时间','公示日期']
get_value_by_split_maohao2(lines, texts,result)
texts=['公示时间',]
get_value_by_next_td(lines, texts,result)
res = get_finally_result(result)
return res