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_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_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 ln_jyw_zbjggs(province, html, text, lines, table_line, table):
    res = {}
    # txts = ['项目名称', '工程名称', '标段名称']
    # res['xmmc'] = get_value_by_next_td2(html, txts)
    res['xmbh'] = get_value_by_next_td(html, '标段编号')
    res['type'] = get_value_by_next_td(html, '工程类别')
    res['zbdl'] = get_value_by_next_td(html, '代理机构')
    res['zbr'] = get_value_by_next_td(html, '建设单位')
    kbsj = get_value_by_next_td(html, '开标日期')
    res['kbsj'] = deal_date_str(kbsj)
    # res['jhgq'] = get_value_by_next_td(html, '有效工期')
    res['gsmc'] = get_value_by_next_td(html, '中标单位')
    res['xmyz'] = get_value_by_next_td(html, '建设单位')
    res['htjg'] = get_value_by_next_td(html, '中标价')
    res['name'] = get_value_by_next_td(html, '项目负责人姓名')
    res['jb'] = get_value_by_next_td(html, '中标负责人级别')
    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('&nbsp;', '', result1).replace('为', ' ').replace(':', ' ').strip()
            result.append(result1)
    except:
        pass
    res = get_finally_result(result)
    return res
def bt_jyw_zbjggg(province, html, text, lines, table_line, table):
    res = {}
    res['xmbh'] = bt_get_value_by_next_td(html, '项目编号')
    res['type'] = bt_get_value_by_next_td(html, '项目类别')
    res['zbr'] = bt_get_value_by_next_td(html, '招标人')
    # res['xmmc'] = bt_get_value_by_next_td(html, '项目名称')
    company = get_data_from_table(table, '中标单位')
    if len(company) == 1:
        company = company[0]
    res['company'] = company
    res['gsmc'] = company

    # jhgq = get_data_from_table(table, '工期')
    # res['jhgq'] = jhgq if jhgq else None
    res['name'] = get_data_from_table(table, '项目经理')
    gsq_start = get_value_by_next_td(html, '公示开始时间')
    gsq_end = get_value_by_next_td(html, '公示结束时间')
    res['gsq'] = gsq_start + '-' + gsq_end if gsq_start else None

    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
Beispiel #8
0
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('&nbsp;', '', 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_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 ln_jyw_zbhxr(province, html, text, lines, table_line, table):
    res = {}
    # res['xmmc'] = get_value_by_next_td(html, '工程名称')
    res['type'] = get_value_by_next_td(html, '工程类别')
    res['xmbh'] = get_value_by_next_td(html, '编号')
    res['zbr'] = get_value_by_next_td(html, '建设单位')
    res['gsmc'] = get_data_from_table(table, '单位名称')
    # jhgq = get_data_from_table(table, '工期')
    # if not jhgq:
    #     jhgq = None
    # res['jhgq'] = jhgq
    res['tbbj'] = get_data_from_table(table, '报价')
    res['name'] = get_data_from_table(table, '项目负责人')
    text_list = ['注册资格', '证书']
    res['zsmc'] = get_data_from_table2(table, text_list)
    res['zsbh'] = get_data_from_table(table, '证书编号')
    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')
    res['gsq'] = gsq_start + '-' + gsq_end
    return res
Beispiel #11
0
def extract_ssd(province, html, text, lines, table_line, table):
    texts = ['招标项目所在地区', '建设地点']
    res = get_value_by_split_maohao2(lines, texts)
    if not res:
        res = get_value_by_next_td(html, '建设地点')
    return res
Beispiel #12
0
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_type(province, html, text, lines, table_line, table):
    res = get_value_by_next_td(html, '工程类型')
    if not res:
        res = bt_get_value_by_next_td(html, '项目类别')
    return res