BaseDataMaintenance/BaseDataMaintenance/maintenance/product/htmlparser.py

#coding:utf8

import re

from BaseDataMaintenance.maintenance.product.productUtils import is_similar
import logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')

logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)


from bs4 import BeautifulSoup
import copy

end_pattern = "商务要求|评分标准|商务条件|商务条件"
_param_pattern = "(产品|技术|清单|配置|参数|具体|明细|项目|招标|货物|服务|规格|工作|具体)[及和与]?(指标|配置|条件|要求|参数|需求|规格|条款|名称及要求)|配置清单|(质量|技术).{,10}要求|验收标准|^(参数|功能)$"
meter_pattern = "[><≤≥±]\d+|\d+(?:[μucmkK微毫千]?[米升LlgGmMΩ]|摄氏度|英寸|度|天|VA|dB|bpm|rpm|kPa|mol|cmH20|%|°|Mpa|Hz|K?HZ|℃|W|min|[*×xX])|[*×xX]\d+|/min|\ds[^a-zA-Z]|GB.{,20}标准|PVC|PP|角度|容积|色彩|自动|流量|外径|轴位|折射率|帧率|柱镜|振幅|磁场|镜片|防漏|强度|允差|心率|倍数|瞳距|底座|色泽|噪音|间距|材质|材料|表面|频率|阻抗|浓度|兼容|防尘|防水|内径|实时|一次性|误差|性能|距离|精确|温度|超温|范围|跟踪|对比度|亮度|[横纵]向|均压|负压|正压|可调|设定值|功能|检测|高度|厚度|宽度|深度|[单双多]通道|效果|指数|模式|尺寸|重量|峰值|谷值|容量|寿命|稳定性|高温|信号|电源|电流|转换率|效率|释放量|转速|离心力|向心力|弯曲|电压|功率|气量|国标|标准协议|灵敏度|最大值|最小值|耐磨|波形|高压|性强|工艺|光源|低压|压力|压强|速度|湿度|重量|毛重|[MLX大中小]+码|净重|颜色|[红橙黄绿青蓝紫]色|不锈钢|输入|输出|噪声|认证|配置"
not_meter_pattern = "投标报价|中标金额|商务部分|公章|分值构成|业绩|详见|联系人|联系电话|合同价|金额|采购预算|资金来源|费用|质疑|评审因素|评审标准|商务资信|商务评分|专家论证意见|评标方法|代理服务费|售后服务|评分类型|评分项目|预算金额|得\d+分|项目金额|详见招标文件|乙方"


def getTrs(tbody):
    #获取所有的tr
    trs = []
    if tbody.name=="table":
        body = tbody.find("tbody",recursive=False)
        if body is not None:
            tbody = body
    objs = tbody.find_all(recursive=False)
    for obj in objs:
        if obj.name=="tr":
            trs.append(obj)
        if obj.name=="tbody" or obj.name=="table":
            for tr in obj.find_all("tr",recursive=False):
                trs.append(tr)
    return trs

def fixSpan(tbody):
    # 处理colspan, rowspan信息补全问题
    #trs = tbody.findChildren('tr', recursive=False)

    trs = getTrs(tbody)
    ths_len = 0
    ths = list()
    trs_set = set()
    #修改为先进行列补全再进行行补全，否则可能会出现表格解析混乱
    # 遍历每一个tr

    for indtr, tr in enumerate(trs):
        ths_tmp = tr.findChildren('th', recursive=False)
        #不补全含有表格的tr
        if len(tr.findChildren('table'))>0:
            continue
        if len(ths_tmp) > 0:
            ths_len = ths_len + len(ths_tmp)
            for th in ths_tmp:
                ths.append(th)
            trs_set.add(tr)
        # 遍历每行中的element
        tds = tr.findChildren(recursive=False)
        for indtd, td in enumerate(tds):
            # 若有colspan 则补全同一行下一个位置
            if 'colspan' in td.attrs:
                if str(re.sub("[^0-9]","",str(td['colspan'])))!="":
                    col = int(re.sub("[^0-9]","",str(td['colspan'])))
                    if col<100 and len(td.get_text())<1000:
                        td['colspan'] = 1
                        for i in range(1, col, 1):
                            td.insert_after(copy.copy(td))

    for indtr, tr in enumerate(trs):
        ths_tmp = tr.findChildren('th', recursive=False)
        #不补全含有表格的tr
        if len(tr.findChildren('table'))>0:
            continue
        if len(ths_tmp) > 0:
            ths_len = ths_len + len(ths_tmp)
            for th in ths_tmp:
                ths.append(th)
            trs_set.add(tr)
        # 遍历每行中的element
        tds = tr.findChildren(recursive=False)
        for indtd, td in enumerate(tds):
            # 若有rowspan 则补全下一行同样位置
            if 'rowspan' in td.attrs:
                if str(re.sub("[^0-9]","",str(td['rowspan'])))!="":
                    row = int(re.sub("[^0-9]","",str(td['rowspan'])))
                    td['rowspan'] = 1
                    for i in range(1, row, 1):
                        # 获取下一行的所有td， 在对应的位置插入
                        if indtr+i<len(trs):
                            tds1 = trs[indtr + i].findChildren(['td','th'], recursive=False)
                            if len(tds1) >= (indtd) and len(tds1)>0:
                                if indtd > 0:
                                    tds1[indtd - 1].insert_after(copy.copy(td))
                                else:
                                    tds1[0].insert_before(copy.copy(td))
                            elif indtd-2>0 and len(tds1) > 0 and len(tds1) == indtd - 1:  # 修正某些表格最后一列没补全
                                tds1[indtd-2].insert_after(copy.copy(td))
def getTable(tbody):
    #trs = tbody.findChildren('tr', recursive=False)
    fixSpan(tbody)
    trs = getTrs(tbody)
    inner_table = []
    for tr in trs:
        tr_line = []
        tds = tr.findChildren(['td','th'], recursive=False)
        if len(tds)==0:
            tr_line.append([re.sub('\xa0','',tr.get_text()),0]) # 2021/12/21 修复部分表格没有td 造成数据丢失
        for td in tds:
            tr_line.append([re.sub('\xa0','',td.get_text()),0])
            #tr_line.append([td.get_text(),0])
        inner_table.append(tr_line)
    return inner_table

class ParseDocument():

    def __init__(self,_html,auto_merge_table=True):
        if _html is None:
            _html = ""
        self.html = _html

        # self.soup = BeautifulSoup(self.html,"lxml")
        # self.soup = BeautifulSoup(self.html,"html.parser")
        self.auto_merge_table = auto_merge_table

        self.soup = BeautifulSoup(self.html,"html5lib")
        _body = self.soup.find("body")
        if _body is not None:
            self.soup = _body
        self.list_obj = self.get_soup_objs(self.soup)

        # for obj in self.list_obj:
        #     print("obj",obj.get_text()[:20])

        self.tree = self.buildParsetree(self.list_obj,[],auto_merge_table)


        # #识别目录树
        # if self.parseTree:
        #     self.parseTree.printParseTree()
        # self.print_tree(self.tree,"-|")

    def get_soup_objs(self,soup,list_obj=None):
        if list_obj is None:
            list_obj = []
        childs = soup.find_all(recursive=False)
        for _obj in childs:
            childs1 = _obj.find_all(recursive=False)
            if len(childs1)==0 or len(_obj.get_text())<40 or _obj.name=="table":
                list_obj.append(_obj)
            else:
                self.get_soup_objs(_obj,list_obj)
        return list_obj

    def fix_tree(self,_product):
        products = extract_products(self.tree,_product)
        if len(products)>0:
            self.tree = self.buildParsetree(self.list_obj,products,self.auto_merge_table)

    def print_tree(self,tree,append=""):
        self.set_tree_id = set()
        if append=="":
            for t in tree:
                logger.debug("%s text:%s title:%s title_text:%s before:%s after%s product:%s"%("==>",t["text"][:50],t["sentence_title"],t["sentence_title_text"],t["title_before"],t["title_after"],t["has_product"]))

        for t in tree:
            _id = id(t)
            if _id in self.set_tree_id:
                continue
            self.set_tree_id.add(_id)
            logger.info("%s text:%s title:%s title_text:%s before:%s after%s product:%s"%(append,t["text"][:50],t["sentence_title"],t["sentence_title_text"],t["title_before"],t["title_after"],t["has_product"]))
            childs = t["child_title"]
            self.print_tree(childs,append=append+"-|")

    def is_title_first(self,title):
        if title in ("一","1","Ⅰ","a","A"):
            return True
        return False

    def find_title_by_pattern(self,_text,_pattern="(^|★|▲|:|：|\s+)(?P<title_1>(?P<title_1_index_0_0>第?)(?P<title_1_index_1_1>[一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]+)(?P<title_1_index_2_0>[、章册包标部.:：、、]+))|" \
                                             "([\s★▲\*]*)(?P<title_3>(?P<title_3_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?)(?P<title_3_index_0_1>[ⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]+)(?P<title_3_index_0_2>[、章册包标部.:：、、]+))|" \
                                             "([\s★▲\*]*)(?P<title_4>(?P<title_4_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?第?)(?P<title_4_index_1_1>[一二三四五六七八九十]+)(?P<title_4_index_2_0>[节章册部\.:：、、]+))|" \
                                             "([\s★▲\*]*)(?P<title_5>(?P<title_5_index_0_0>^)(?P<title_5_index_1_1>[一二三四五六七八九十]+)(?P<title_5_index_2_0>)[^一二三四五六七八九十节章册部\.:：、、])|" \
                                             "([\s★▲\*]*)(?P<title_12>(?P<title_12_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?\d{1,2}[\.．、\s\-]\d{1,2}[\.．、\s\-]\d{1,2}[\.．、\s\-]\d{1,2}[\.．、\s\-])(?P<title_12_index_1_1>\d{1,2})(?P<title_12_index_2_0>[\.．、\s\-]?))|"\
                                             "([\s★▲\*]*)(?P<title_11>(?P<title_11_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?\d{1,2}[\.．、\s\-]\d{1,2}[\.．、\s\-]\d{1,2}[\.．、\s\-])(?P<title_11_index_1_1>\d{1,2})(?P<title_11_index_2_0>[\.．、\s\-]?))|" \
                                             "([\s★▲\*]*)(?P<title_10>(?P<title_10_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?\d{1,2}[\.．、\s\-]\d{1,2}[\.．、\s\-])(?P<title_10_index_1_1>\d{1,2})(?P<title_10_index_2_0>[\.．、\s\-]?))|" \
                                             "([\s★▲\*]*)(?P<title_7>(?P<title_7_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?\d{1,2}[\.．\s\-])(?P<title_7_index_1_1>\d{1,2})(?P<title_7_index_2_0>[\.．包标:：、\s\-]*))|" \
                                             "(^[\s★▲\*]*)(?P<title_6>(?P<title_6_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?包?)(?P<title_6_index_0_1>\d{1,2})(?P<title_6_index_2_0>[\.．、\s\-包标]*))|" \
                                             "([\s★▲\*]*)(?P<title_15>(?P<title_15_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?[(（]?)(?P<title_15_index_1_1>\d{1,2})(?P<title_15_index_2_0>[)）包标\.．:：、]+))|" \
                                             "([\s★▲\*]*)(?P<title_17>(?P<title_17_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?[(（]?)(?P<title_17_index_1_1>[a-zA-Z]+)(?P<title_17_index_2_0>[)）包标\.．:：、]+))|" \
                                             "([\s★▲\*]*)(?P<title_19>(?P<title_19_index_0_0>[^一二三四五六七八九十\dⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]{,3}?[(（]?)(?P<title_19_index_1_1>[一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]+)(?P<title_19_index_2_0>[)）]))"
                              ):
        _se = re.search(_pattern,_text)
        groups = []
        if _se is not None:
            _gd = _se.groupdict()
            for k,v in _gd.items():
                if v is not None:
                    groups.append((k,v))
        if len(groups):
            # groups.sort(key=lambda x:x[0])
            return groups
        return None

    def make_increase(self,_sort,_title,_add=1):
        if len(_title)==0 and _add==0:
            return ""
        if len(_title)==0 and _add==1:
            return _sort[0]
        _index = _sort.index(_title[-1])
        next_index = (_index+_add)%len(_sort)
        next_chr = _sort[next_index]
        if _index==len(_sort)-1:
            _add = 1
        else:
            _add = 0
        return next_chr+self.make_increase(_sort,_title[:-1],_add)


    def get_next_title(self,_title):
        if re.search("^\d+$",_title) is not None:
            return str(int(_title)+1)
        if re.search("^[一二三四五六七八九十百]+$",_title) is not None:
            if _title[-1]=="十":
                return _title+"一"
            if _title[-1]=="百":
                return _title+"零一"

            if _title[-1]=="九":
                if len(_title)==1:
                    return "十"
                if len(_title)==2:
                    if _title[0]=="十":
                        return "二十"
                if len(_title)==3:
                    if _title[0]=="九":
                        return "一百"
                    else:
                        _next_title = self.make_increase(['一','二','三','四','五','六','七','八','九','十'],re.sub("[十百]",'',_title[0]))
                        return _next_title+"十"

            _next_title = self.make_increase(['一','二','三','四','五','六','七','八','九','十'],re.sub("[十百]",'',_title))
            _next_title = list(_next_title)
            _next_title.reverse()
            if _next_title[-1]!="十":
                if len(_next_title)>=2:
                    _next_title.insert(-1,'十')
            if len(_next_title)>=4:
                _next_title.insert(-3,'百')
            if _title[0]=="十":
                if _next_title=="十":
                    _next_title = ["二","十"]
                _next_title.insert(0,"十")
            _next_title = "".join(_next_title)
            return _next_title
        if re.search("^[a-z]+$",_title) is not None:
            _next_title = self.make_increase([chr(i+ord('a')) for i in range(26)],_title)
            _next_title = list(_next_title)
            _next_title.reverse()
            return "".join(_next_title)
        if re.search("^[A-Z]+$",_title) is not None:
            _next_title = self.make_increase([chr(i+ord('A')) for i in range(26)],_title)
            _next_title = list(_next_title)
            _next_title.reverse()
            return "".join(_next_title)
        if re.search("^[ⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫ]$",_title) is not None:
            _sort = ["Ⅰ","Ⅱ","Ⅲ","Ⅳ","Ⅴ","Ⅵ","Ⅶ","Ⅷ","Ⅸ","Ⅹ","Ⅺ","Ⅻ"]
            _index = _sort.index(_title)
            if _index<len(_sort)-1:
                return _sort[_index+1]
            return None

    def count_title_before(self,list_obj):
        dict_before = {}
        dict_sentence_count = {}
        illegal_sentence = set()
        for obj_i in range(len(list_obj)):
            obj = list_obj[obj_i]
            _type = "sentence"
            _text = obj.text.strip()
            if obj.name=="table":
                _type = "table"
                _text = str(obj)
            _append = False


            if _type=="sentence":
                if len(_text)>10 and len(_text)<100:
                    if _text not in dict_sentence_count:
                        dict_sentence_count[_text] = 0
                    dict_sentence_count[_text] += 1
                    if re.search("\d+页",_text) is not None:
                        illegal_sentence.add(_text)
                elif len(_text)<10:
                    if re.search("第\d+页",_text) is not None:
                        illegal_sentence.add(_text)

                sentence_groups = self.find_title_by_pattern(_text[:10])
                if sentence_groups:
                    # c062f53cf83401e671822003d63c1828print("sentence_groups",sentence_groups)
                    sentence_title = sentence_groups[0][0]
                    sentence_title_text = sentence_groups[0][1]
                    title_index = sentence_groups[-2][1]
                    title_before = sentence_groups[1][1].replace("（","(").replace("：",":").replace("：",";").replace("，",".").replace(",",".").replace("、",".")
                    title_after = sentence_groups[-1][1].replace("）",")").replace("：",":").replace("：",";").replace("，",".").replace(",",".").replace("、",".")
                    next_index = self.get_next_title(title_index)
                    if title_before not in dict_before:
                        dict_before[title_before] = 0
                    dict_before[title_before] += 1

        for k,v in dict_sentence_count.items():
            if v>10:
                illegal_sentence.add(k)
        return dict_before,illegal_sentence

    def is_page_no(self,sentence):
        if len(sentence)<10:
            if re.search("\d+页|^\-\d+\-$",sentence) is not None:
                return True

    def block_tree(self,childs):
        for child in childs:

            if not child["block"]:
                child["block"] = True
                childs2 = child["child_title"]
                self.block_tree(childs2)


    def buildParsetree(self,list_obj,products=[],auto_merge_table=True):

        self.parseTree = None
        trees = []
        list_length = []
        for obj in list_obj[:200]:
            if obj.name!="table":
                list_length.append(len(obj.get_text()))
        if len(list_length)>0:
            max_length = max(list_length)
        else:
            max_length = 40
        max_length = min(max_length,40)

        logger.debug("%s:%d"%("max_length",max_length))


        list_data = []
        last_table_index = None
        last_table_columns = None
        last_table = None
        dict_before,illegal_sentence = self.count_title_before(list_obj)
        for obj_i in range(len(list_obj)):
            obj = list_obj[obj_i]

            # logger.debug("==obj %s"%obj.text[:20])

            _type = "sentence"
            _text = standard_product(obj.text)
            if obj.name=="table":
                _type = "table"
                _text = standard_product(str(obj))
            _append = False
            sentence_title = None
            sentence_title_text = None
            sentence_groups = None
            title_index = None
            next_index = None
            parent_title = None
            title_before = None
            title_after = None
            title_next = None
            childs = []

            list_table = None
            block = False

            has_product = False

            if _type=="sentence":
                if _text in illegal_sentence:
                    continue


                sentence_groups = self.find_title_by_pattern(_text[:10])
                if sentence_groups:
                    title_before = standard_title_context(sentence_groups[1][1])
                    title_after = sentence_groups[-1][1]
                    sentence_title_text = sentence_groups[0][1]
                    other_text = _text.replace(sentence_title_text,"")
                    if (title_before in dict_before and dict_before[title_before]>1) or title_after!="":
                        sentence_title = sentence_groups[0][0]

                        title_index = sentence_groups[-2][1]
                        next_index = self.get_next_title(title_index)

                        other_text = _text.replace(sentence_title_text,"")

                        for p in products:
                            if other_text.strip()==p.strip():
                                has_product = True

                    else:
                        _fix = False

                        for p in products:
                            if other_text.strip()==p.strip():
                                title_before = "=产品"
                                sentence_title = "title_0"
                                sentence_title_text = p
                                title_index = "0"
                                title_after = "产品="
                                next_index = "0"
                                _fix = True
                                has_product = True
                                break
                        if not _fix:
                            title_before = None
                            title_after = None
                            sentence_title_text = None
                else:
                    if len(_text)<40 and re.search(_param_pattern,_text) is not None:
                        for p in products:
                            if _text.find(p)>=0:
                                title_before = "=产品"
                                sentence_title = "title_0"
                                sentence_title_text = p
                                title_index = "0"
                                title_after = "产品="
                                next_index = "0"
                                _fix = True
                                has_product = True
                                break

            if _type=="sentence":
                if sentence_title is None and len(list_data)>0 and list_data[-1]["sentence_title"] is not None and list_data[-1]["line_width"]>=max_length*0.6:
                    list_data[-1]["text"] += _text
                    list_data[-1]["line_width"] = len(_text)
                    _append = True
                elif sentence_title is None and len(list_data)>0 and _type==list_data[-1]["type"]:
                    if list_data[-1]["line_width"]>=max_length*0.7:
                        list_data[-1]["text"] += _text
                        list_data[-1]["line_width"] = len(_text)
                        _append = True

            if _type=="table":
                _soup = BeautifulSoup(_text,"lxml")
                _table = _soup.find("table")
                if _table is not None:
                    list_table = getTable(_table)
                    if len(list_table)==0:
                        continue
                    table_columns = len(list_table[0])

                    if auto_merge_table:
                        if last_table_index is not None and abs(obj_i-last_table_index)<=2 and last_table_columns is not None and last_table_columns==table_columns:
                            if last_table is not None:
                                trs = getTrs(_table)
                                last_tbody = BeautifulSoup(last_table["text"],"lxml")
                                _table = last_tbody.find("table")
                                last_trs = getTrs(_table)
                                _append = True

                                for _line in list_table:
                                    last_table["list_table"].append(_line)
                                if len(last_trs)>0:
                                    for _tr in trs:
                                        last_trs[-1].insert_after(copy.copy(_tr))
                                    last_table["text"] = re.sub("</?html>|</?body>","",str(last_tbody))

                                last_table_index = obj_i
                                last_table_columns = len(list_table[-1])


            if not _append:
                _data = {"type":_type, "text":_text,"list_table":list_table,"line_width":len(_text),"sentence_title":sentence_title,"title_index":title_index,
                         "sentence_title_text":sentence_title_text,"sentence_groups":sentence_groups,"parent_title":parent_title,
                         "child_title":childs,"title_before":title_before,"title_after":title_after,"title_next":title_next,"next_index":next_index,
                         "block":block,"has_product":has_product}

                if _type=="table":
                    last_table = _data
                    last_table_index = obj_i
                    if list_table:
                        last_table_columns = last_table_columns = len(list_table[-1])

                if sentence_title is not None:
                    if len(list_data)>0:
                        if self.is_title_first(title_index):
                            for i in range(1,len(list_data)+1):
                                _d = list_data[-i]
                                if _d["sentence_title"] is not None:
                                    _data["parent_title"] = _d
                                    _d["child_title"].append(_data)
                                    break
                        else:
                            _find = False
                            for i in range(1,len(list_data)+1):
                                if _find:
                                    break
                                _d = list_data[-i]
                                if _d.get("sentence_title")==sentence_title and title_before==_d["title_before"] and title_after==_d["title_after"]:
                                    if _d["next_index"]==title_index and _d["title_next"] is None and not _d["block"]:
                                        _data["parent_title"] = _d["parent_title"]
                                        _d["title_next"] = _data
                                        if len(_d["child_title"])>0:
                                            _d["child_title"][-1]["title_next"] = ""
                                            self.block_tree(_d["child_title"])
                                        if _d["parent_title"] is not None:
                                            _d["parent_title"]["child_title"].append(_data)
                                        _find = True
                                        break
                            for i in range(1,len(list_data)+1):
                                if _find:
                                    break
                                _d = list_data[-i]
                                if i==1 and not _d["block"] and _d.get("sentence_title")==sentence_title and title_before==_d["title_before"] and title_after==_d["title_after"]:
                                    _data["parent_title"] = _d["parent_title"]
                                    _d["title_next"] = _data
                                    if len(_d["child_title"])>0:
                                        _d["child_title"][-1]["title_next"] = ""
                                        self.block_tree(_d["child_title"])
                                    if _d["parent_title"] is not None:
                                        _d["parent_title"]["child_title"].append(_data)
                                    _find = True
                                    break
                            title_before = standard_title_context(title_before)
                            title_after = standard_title_context(title_after)
                            for i in range(1,len(list_data)+1):
                                if _find:
                                    break
                                _d = list_data[-i]
                                if _d.get("sentence_title")==sentence_title and title_before==standard_title_context(_d["title_before"]) and title_after==standard_title_context(_d["title_after"]):
                                    if _d["next_index"]==title_index and _d["title_next"] is None and not _d["block"]:
                                        _data["parent_title"] = _d["parent_title"]
                                        _d["title_next"] = _data
                                        if len(_d["child_title"])>0:
                                            _d["child_title"][-1]["title_next"] = ""
                                            self.block_tree(_d["child_title"])
                                        if _d["parent_title"] is not None:
                                            _d["parent_title"]["child_title"].append(_data)
                                        _find = True
                                        break
                            for i in range(1,len(list_data)+1):
                                if _find:
                                    break
                                _d = list_data[-i]
                                if not _d["block"] and _d.get("sentence_title")==sentence_title and title_before==standard_title_context(_d["title_before"]) and title_after==standard_title_context(_d["title_after"]):
                                    _data["parent_title"] = _d["parent_title"]
                                    _d["title_next"] = _data
                                    if len(_d["child_title"])>0:
                                        _d["child_title"][-1]["title_next"] = ""
                                        # self.block_tree(_d["child_title"])
                                    if _d["parent_title"] is not None:
                                        _d["parent_title"]["child_title"].append(_data)
                                    _find = True
                                    break
                            for i in range(1,min(len(list_data)+1,20)):
                                if _find:
                                    break
                                _d = list_data[-i]
                                if not _d["block"] and _d.get("sentence_title")==sentence_title and title_before==standard_title_context(_d["title_before"]):
                                    _data["parent_title"] = _d["parent_title"]
                                    _d["title_next"] = _data
                                    if len(_d["child_title"])>0:
                                        _d["child_title"][-1]["title_next"] = ""
                                        # self.block_tree(_d["child_title"])
                                    if _d["parent_title"] is not None:
                                        _d["parent_title"]["child_title"].append(_data)
                                    _find = True
                                    break

                            if not _find:
                                if len(list_data)>0:
                                    for i in range(1,len(list_data)+1):
                                        _d = list_data[-i]
                                        if _d.get("sentence_title") is not None:
                                            _data["parent_title"] = _d
                                            _d["child_title"].append(_data)
                                            break


                else:
                    if len(list_data)>0:
                        for i in range(1,len(list_data)+1):
                            _d = list_data[-i]
                            if _d.get("sentence_title") is not None:
                                _data["parent_title"] = _d
                                _d["child_title"].append(_data)
                                break

                list_data.append(_data)

        for _data in list_data:

            childs = _data["child_title"]

            for c_i in range(len(childs)):
                cdata = childs[c_i]
                if cdata["has_product"]:
                    continue
                else:
                    if c_i>0:
                        last_cdata = childs[c_i-1]
                        if cdata["sentence_title"] is not None and last_cdata["sentence_title"] is not None and last_cdata["title_before"]==cdata["title_before"] and last_cdata["title_after"]==cdata["title_after"] and last_cdata["has_product"]:
                            cdata["has_product"] = True
                    if c_i<len(childs)-1:
                        last_cdata = childs[c_i+1]
                        if cdata["sentence_title"] is not None and last_cdata["sentence_title"] is not None and last_cdata["title_before"]==cdata["title_before"] and last_cdata["title_after"]==cdata["title_after"] and last_cdata["has_product"]:
                            cdata["has_product"] = True
            for c_i in range(len(childs)):
                cdata = childs[len(childs)-1-c_i]
                if cdata["has_product"]:
                    continue
                else:
                    if c_i>0:
                        last_cdata = childs[c_i-1]
                        if cdata["sentence_title"] is not None and last_cdata["sentence_title"] is not None and last_cdata["title_before"]==cdata["title_before"] and last_cdata["title_after"]==cdata["title_after"] and last_cdata["has_product"]:
                            cdata["has_product"] = True
                    if c_i<len(childs)-1:
                        last_cdata = childs[c_i+1]
                        if cdata["sentence_title"] is not None and last_cdata["sentence_title"] is not None and last_cdata["title_before"]==cdata["title_before"] and last_cdata["title_after"]==cdata["title_after"] and last_cdata["has_product"]:
                            cdata["has_product"] = True


        return list_data


def standard_title_context(_title_context):
    return _title_context.replace("（","(").replace("）",")").replace("：",":").replace("：",";").replace("，",".").replace(",",".").replace("、",".").replace("．",".")

def standard_product(sentence):
    return sentence.replace("（","(").replace("）",")")

def extract_products(list_data,_product,_param_pattern = "产品名称|设备材料|采购内存|标的名称|采购内容|(标的|维修|系统|报价构成|商品|产品|物料|物资|货物|设备|采购品|采购条目|物品|材料|印刷品?|采购|物装|配件|资产|耗材|清单|器材|仪器|器械|备件|拍卖物|标的物|物件|药品|药材|药械|货品|食品|食材|品目|^品名|气体|标项|分项|项目|计划|包组|标段|[分子]?包|子目|服务|招标|中标|成交|工程|招标内容)[\)）的]?([、\w]{,4}名称|内容|描述)|标的|标项|项目$|商品|产品|物料|物资|货物|设备|采购品|采购条目|物品|材料|印刷品|物装|配件|资产|招标内容|耗材|清单|器材|仪器|器械|备件|拍卖物|标的物|物件|药品|药材|药械|货品|食品|食材|菜名|^品目$|^品名$|^名称|^内容$"):
    _product = standard_product(_product)
    list_result = []
    list_table_products = []
    for _data_i in range(len(list_data)):
        _data = list_data[_data_i]
        _type = _data["type"]
        _text = _data["text"]

        if _type=="table":
            list_table = _data["list_table"]
            if list_table is None:
                continue
            _check = True
            max_length = max([len(a) for a in list_table])
            min_length = min([len(a) for a in list_table])
            if min_length<max_length/2:
                continue
            list_head_index = []
            _begin_index = 0
            head_cell_text = ""
            for line_i in range(len(list_table[:2])):
                line = list_table[line_i]
                line_text = ",".join([cell[0] for cell in line])
                for cell_i in range(len(line)):
                    cell = line[cell_i]
                    cell_text = cell[0]
                    if len(cell_text)<10 and re.search(_param_pattern,cell_text) is not None and re.search("单价|数量|预算|限价|总价|品牌|规格|型号|用途|要求|采购量",line_text) is not None:
                        _begin_index = line_i+1
                        list_head_index.append(cell_i)

            for line_i in range(len(list_table)):
                line = list_table[line_i]
                for cell_i in list_head_index:
                    if cell_i>=len(line):
                        continue
                    cell = line[cell_i]
                    cell_text = cell[0]
                    head_cell_text += cell_text

            # print("===head_cell_text",head_cell_text)
            if re.search("招标人|采购人|项目编号|项目名称|金额|^\d+$",head_cell_text) is not None:
                list_head_index = []

            for line in list_table:
                line_text = ",".join([cell[0] for cell in line])
                for cell_i in range(len(line)):
                    cell = line[cell_i]
                    cell_text = cell[0]
                    if cell_text is not None and _product is not None and len(cell_text)<len(_product)*10 and cell_text.find(_product)>=0 and re.search("单价|数量|总价|规格|品牌|型号|用途|要求|采购量",line_text) is not None:
                        list_head_index.append(cell_i)

            list_head_index = list(set(list_head_index))
            if len(list_head_index)>0:
                has_number = False
                for cell_i in list_head_index:
                    table_products = []

                    for line_i in range(_begin_index,len(list_table)):
                        line = list_table[line_i]

                        for _i in range(len(line)):
                            cell = line[_i]
                            cell_text = cell[0]
                            if re.search("^\d+$",cell_text) is not None:
                                has_number = True

                        if cell_i>=len(line):
                            continue
                        cell = line[cell_i]
                        cell_text = cell[0]
                        if re.search(_param_pattern,cell_text) is None or has_number:
                            if re.search("^[\da-zA-Z]+$",cell_text) is None:
                                table_products.append(cell_text)

                    if len(table_products)>0:
                        logger.debug("table products %s"%(str(table_products)))
                        if min([len(x) for x in table_products])>0 and max([len(x) for x in table_products])<=30:
                            if re.search("招标人|代理人|预算|数量|交货期|品牌|产地","".join(table_products)) is None:
                                list_table_products.append(table_products)
    _find = False
    for table_products in list_table_products:
        for _p in table_products:
            if is_similar(_product,_p,90):
                _find = True
                logger.debug("similar table_products %s"%(str(table_products)))
                list_result = list(set([a for a in table_products if len(a)>1 and len(a)<20 and re.search("费用|预算|合计|金额|万元|运费|^其他$",a) is None]))
                break
    if not _find:
        for table_products in list_table_products:
            list_result.extend(table_products)
        list_result = list(set([a for a in list_result if len(a)>1 and len(a)<30 and re.search("费用|预算|合计|金额|万元|运费",a) is None]))
    return list_result


def get_childs(childs):
    list_data = []
    for _child in childs:
        list_data.append(_child)
        childs2 = _child.get("child_title",[])

        if len(childs2)>0:
            for _child2 in childs2:
                list_data.extend(get_childs([_child2]))
    return list_data

def get_range_data_by_childs(list_data,childs):
    range_data = []
    list_child = get_childs(childs)
    list_index = []
    set_child = set([id(x) for x in list_child])
    for _data_i in range(len(list_data)):
        _data = list_data[_data_i]
        _id = id(_data)
        if _id in set_child:
            list_index.append(_data_i)
    if len(list_index)>0:
        range_data = list_data[min(list_index):max(list_index)+1]
    return range_data

def get_correct_product(product,products):
    list_data = []
    for p in products:
        is_sim = is_similar(product,p)
        _d = {"product":p,"distance":abs(len(product)-len(p)),"is_sim":is_sim}
        list_data.append(_d)
    list_data.sort(key=lambda x:x["distance"])
    for _d in list_data:
        is_sim = _d["is_sim"]
        if is_sim:
            if len(_d["product"])>len(product) and _d["product"].find(product)>=0:
                return product
            return _d["product"]
    return product

def get_childs_text(childs,_product,products,is_begin=False,is_end=False):
    _text = ""

    end_next = False
    for _child in childs:

        child_text = _child.get("text")


        if child_text.find(_product)>=0:
            if not is_begin:
                is_begin = True
                if not end_next:
                    if _child["sentence_title"] is not None and isinstance(_child["title_next"],dict) and _child["title_next"]["sentence_title"] is not None:
                        end_next = True
                        end_title = _child["title_next"]
                        logger.debug("end_title %s "%end_title["text"])

        logger.debug("%s-%s-%s"%("get_childs_text",child_text[:10],str(is_begin)))

        for p in products:
            if child_text.find(p)>=0 and is_similar(_product,p,90):
                is_begin = True

            if child_text.find(_product)<0  and not is_similar(_product,p,80) and  (child_text.find(p)>=0 or _child["has_product"]):
                if is_begin:
                    is_end = True
                    logger.debug("%s-%s-%s"%("get_childs_text end",child_text[:10],p))
                break
        if re.search(end_pattern,child_text) is not None:
            if is_begin:
                is_end = True
                logger.debug("%s-%s-%s"%("get_childs_text end",child_text[:10],str(is_end)))

        if is_begin and is_end:
            break

        if is_begin:
            _text += _child.get("text")+"\r\n"
        childs2 = _child.get("child_title",[])


        if len(childs2)>0:
            for _child2 in childs2:
                child_text,is_begin,is_end = get_childs_text([_child2],_product,products,is_begin)
                if is_begin:
                    _text += child_text
                    if is_end:
                        break

        if end_next:
            is_end = True

    #     logger.debug("%s-%s-%s"%("get_childs_text1",_text,str(is_begin)))
    # logger.debug("%s-%s-%s"%("get_childs_text2",_text,str(is_begin)))
    return _text,is_begin,is_end

def extract_parameters_by_tree(_product,products,list_data,_data_i,parent_title,list_result,):
    _data = list_data[_data_i]
    childs = _data.get("child_title",[])
    if len(childs)>0:
        child_text,_,_ = get_childs_text([_data],_product,products)
        if len(child_text)>0:
            logger.info("extract_type by_tree child_text:%s"%child_text)
            list_result.append(child_text)
    if parent_title is not None:
        child_text,_,_ = get_childs_text([parent_title],_product,products)
        if len(child_text)>0:
            logger.info("extract_type by_tree child_text:%s"%child_text)
            list_result.append(child_text)

        childs = parent_title.get("child_title",[])
        if len(childs)>0:

            range_data = get_range_data_by_childs(list_data[_data_i:],childs)
            p_text = ""
            _find = False
            end_id = id(_data["title_next"]) if isinstance(_data["sentence_title"],dict) and _data["title_next"] is not None and _data["title_next"]["sentence_title"] is not None else None
            for pdata in range_data:
                ptext = pdata["text"]
                for p in products:
                    if ptext.find(_product)<0 and  (ptext.find(p)>=0 or pdata["has_product"]):
                        _find = True
                        break
                if re.search(end_pattern,ptext) is not None:
                    _find = True
                if _find:
                    break
                if id(pdata)==end_id:
                    break
                p_text += ptext+"\r\n"
            if len(p_text)>0:
                logger.debug("extract_type by parent range_text:%s"%p_text)
                list_result.append(p_text)
                return True
    return False


def get_table_pieces(_text,_product,products,list_result,_find):
    _soup = BeautifulSoup(_text,"html5lib")
    _table = _soup.find("table")
    if _table is not None:
        trs = getTrs(_table)
        list_trs = []
        for tr in trs:
            tr_text = tr.get_text()
            if tr_text.find(_product)>=0:
                _find = True

            logger.debug("%s-%s"%("table_html_tr",tr_text))
            for p in products:
                if _find and p!=_product and tr_text.find(p)>=0:
                    _find = False
                    break
            if re.search(end_pattern,tr_text) is not None:
                _find = False
                break
            if _find:
                list_trs.append(tr)
        if len(list_trs)>0:
            table_html = "<table>%s</table>"%("\r\n".join([str(a) for a in list_trs]))
            logger.debug("extract_type table slices %s"%(table_html))
            list_result.append(table_html)

def extract_parameters_by_table(_product,products,_param_pattern,list_data,_data_i,list_result):
    _data = list_data[_data_i]
    _text = _data["text"]
    list_table = _data["list_table"]
    parent_title = _data["parent_title"]
    if list_table is not None:
        _check = True
        max_length = max([len(a) for a in list_table])
        min_length = min([len(a) for a in list_table])
        text_line_first = ",".join(a[0] for a in list_table[0])
        if max_length>10:
            if min_length<max_length/2:
                return
        last_data = list_data[_data_i-1]
        _flag = False
        if last_data["type"]=="sentence" and last_data["text"].find(_product)>=0:
            logger.debug("last sentence find product %s-%s"%(_product,last_data["text"]))
            _flag = True
        # print(text_line_first,"text_line_first",re.search(_param_pattern,text_line_first) is not None and text_line_first.find(_product)>=0)
        if re.search(_param_pattern,text_line_first) is not None and text_line_first.find(_product)>=0:
            _flag = True
        if _flag:
            if len(products)==0:
                logger.debug("extract_type whole table by param and product %s"%(_text))
                list_result.append(_text)
            else:
                for p in products:
                    if p!=_product and _text.find(p)>=0:
                        logger.debug("extract_type add all table failed %s-%s"%(_product,p))
                        _flag = False
                        break
                if _flag:
                    logger.debug("extract_type add all table succeed")
                    get_table_pieces(_text,_product,products,list_result,True)
        else:
            list_head_index = []
            for line in list_table[:2]:
                for cell_i in range(len(line)):
                    cell = line[cell_i]
                    cell_text = cell[0]
                    if len(cell_text)<20 and re.search(_param_pattern,cell_text) is not None:
                        list_head_index.append(cell_i)
            list_head_index = list(set(list_head_index))
            for line in list_table:
                for cell in line:
                    cell_text = cell[0]
                    if len(cell_text)>50 and len(re.findall(meter_pattern,cell_text))>5 and cell_text.find(_product)>=0:
                        _f = True
                        for cell in line:
                            if not _f:
                                break
                            cell_text = cell[0]
                            for p in products:
                                if cell_text.find(p)>=0 and p!=_product:
                                    _f = False
                                    break
                        if _f:
                            logger.debug("extract_type param column %s"%(cell_text))
                            list_result.append(cell_text)
                    if len(cell_text)<len(_product)*10 and str(cell_text).find(_product)>=0:
                        for _index in list_head_index:
                            if _index>=len(line):
                                continue
                            _cell = line[_index]
                            if len(cell[0])>0:
                                logger.info("%s-%s"%("extract_type add on table text:",_cell[0]))
                                list_result.append(_cell[0])
        if not _flag and (re.search(_param_pattern,_text) is not None or (parent_title is not None and re.search(_param_pattern,parent_title["text"]) is not None)) and _text.find(_product)>=0:
            get_table_pieces(_text,_product,products,list_result,False)


def extract_parameters_by_sentence(list_data,_data,_data_i,_product,products,list_result,is_project):
    _text = _data["text"]
    if _text.find(_product)>=0:
        parent_title = _data.get("parent_title")
        parent_text = ""
        parent_parent_title = None
        parent_parent_text = ""
        parent_title_index = None
        parent_parent_title_index = None
        childs = get_childs([_data])

        child_find = False
        for c in childs:
            if re.search(_param_pattern,c["text"]) is not None and len(c["text"])<30:
                logger.debug("child text %s"%(c["text"]))
                child_find = True
                break

        extract_text,_,_ = get_childs_text([_data],_product,products)
        logger.debug("childs found extract_text %s %s"%(str(child_find),extract_text))
        if child_find:
            if len(extract_text)>0:
                list_result.append(extract_text)
        else:
            limit_nums = len(_product)*2+5
            if len(_product)<=3:
                limit_nums += 6
            if _text.find("数量")>=0:
                limit_nums += 6
            if len(_text)<=limit_nums and _data["sentence_title"] is not None:
                if re.search(meter_pattern,extract_text) is not None:
                    list_result.append(extract_text)
            elif len(re.findall(meter_pattern,extract_text))>2:
                list_result.append(extract_text)

        if parent_title is not None:
            parent_text = parent_title.get("text","")
            parent_parent_title = parent_title.get("parent_title")
            parent_title_index = parent_title["title_index"]
            if parent_parent_title is not None:
                parent_parent_text = parent_parent_title.get("text","")
                parent_parent_title_index = parent_parent_title["title_index"]

        _suit = False
        if re.search(_param_pattern,_text) is not None and len(_text)<50:
            _suit = True
        if re.search(_param_pattern,parent_text) is not None and len(parent_text)<50:
            _suit = True
        if re.search(_param_pattern,parent_parent_text) is not None and len(parent_parent_text)<50:
            _suit = True
        if _suit:
            logger.debug("extract_type sentence %s"%("extract_parameters_by_tree"))
            if not extract_parameters_by_tree(_product,products,list_data,_data_i,parent_title,list_result):
                logger.debug("extract_type sentence %s"%("extract_parameters_by_tree"))
                extract_parameters_by_tree(_product,products,list_data,_data_i,parent_parent_title,list_result)

    if re.search(_param_pattern,_text) is not None and len(_text)<50:
        childs = _data["child_title"]
        if len(childs)>0:
            extract_text,_,_ = get_childs_text([_data],_product,products)
            if len(extract_text)>0:
                logger.debug("extract_type param-product %s"%(extract_text))
                list_result.append(extract_text)
            elif is_project:
                extract_text,_,_ = get_childs_text([_data],_product,products,is_begin=True)
                if len(extract_text)>0 and re.search(meter_pattern,extract_text) is not None:
                    logger.debug("extract_type sentence is_project param-product is product %s"%(extract_text))
                    list_result.append(extract_text)

def getBestProductText(list_result,_product,products):
    list_result.sort(key=lambda x:len(re.findall(meter_pattern+"|"+'[:：;；]|\d+[%A-Za-z]+',BeautifulSoup(x,"html5lib").get_text())), reverse=True)

    logger.debug("+++++++++++++++++++++")
    for i in range(len(list_result)):
        logger.debug("result%d %s"%(i,list_result[i]))
    logger.debug("+++++++++++++++++++++")

    for i in range(len(list_result)):
        _result = list_result[i]
        _check = True
        _result_text = BeautifulSoup(_result,"html5lib").get_text()
        _search = re.search("项目编号[:：]|项目名称[:：]|联合体投标|开户银行",_result)
        if _search is not None:
            logger.debug("result%d error illegal text %s"%(i,str(_search)))
            _check = False
        if not (len(_result_text)<1000 and _result[:6]!="<table"):
            for p in products:
                if _result_text.find(p)>0 and not (is_similar(_product,p,80) or p.find(_product)>=0 or _product.find(p)>=0):
                    logger.debug("result%d error product scoss %s"%(i,p))
                    _check = False
        if len(_result_text)<100:
            if re.search(meter_pattern,_result_text) is None:
                logger.debug("result%d error text min count"%(i))
                _check = False
        if len(_result_text)>5000:
            if len(_result_text)>10000:
                logger.debug("result%d error text max count"%(i))
                _check = False
            elif len(re.findall(meter_pattern,_result_text))<10:
                logger.debug("result%d error text max count less meter"%(i))
                _check = False

        list_find = list(set(re.findall(meter_pattern,_result_text)))

        not_list_find = list(set(re.findall(not_meter_pattern,_result_text)))
        _count = len(list_find)-len(not_list_find)
        has_num = False
        for _find in list_find:
            if re.search('[0-9a-zA-Z]',_find) is not None:
                has_num = True
                break
        if not(_count>=2 and has_num or _count>=5):
            logger.debug("result%d error match not enough"%(i))
            _check = False

        if _check:
            return _result

def format_text(_result):
    list_result = re.split("\r|\n",_result)
    _result = ""
    for _r in list_result:
        if len(_r)>0:
            _result+="%s\n"%(_r)
    _result = '<div style="white-space:pre">%s</div>'%(_result)
    return _result

def extract_product_parameters(list_data,_product):

    list_result = []
    _product = standard_product(_product.strip())
    products = extract_products(list_data,_product)

    _product = get_correct_product(_product,products)
    logger.debug("all products %s-%s"%(_product,str(products)))
    is_project = False
    if re.search("项目名称|采购项目",_product) is not None:
        is_project = True
        
    if len(products)==1 and is_similar(products[0],_product,90):
        is_project = True
    _find_count = 0
    for _data_i in range(len(list_data)):
        _data = list_data[_data_i]
        _type = _data["type"]
        _text = _data["text"]
        if _type=="sentence":
            if _text.find(_product)>=0:
                _find_count += 1
                if re.search("项目名称|采购项目",_text) is not None and re.search("等",_text) is not None:
                    is_project = True
            extract_parameters_by_sentence(list_data,_data,_data_i,_product,products,list_result,is_project)

        elif _type=="table":
            if _text.find(_product)>=0:
                _find_count += 1
            extract_parameters_by_table(_product,products,_param_pattern,list_data,_data_i,list_result)

    _text = getBestProductText(list_result,_product,products)
    return _text,_find_count


if __name__ == '__main__':

    filepath = "download/4597dcc128bfabc7584d10590ae50656.html"
    _product = "彩色多普勒超声诊断仪"

    _html = open(filepath, "r", encoding="utf8").read()

    pd = ParseDocument(_html,False)

    pd.fix_tree(_product)
    list_data = pd.tree
    pd.print_tree(list_data)

    _text,_count = extract_product_parameters(list_data,_product)
    logger.info("find count:%d"%(_count))
    logger.info("extract_parameter_text::%s"%(_text))