|
|
@@ -0,0 +1,1176 @@
|
|
|
+#coding:utf8
|
|
|
+from bs4 import BeautifulSoup
|
|
|
+import json
|
|
|
+import re
|
|
|
+import traceback
|
|
|
+
|
|
|
+import logging
|
|
|
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
|
|
+
|
|
|
+logger = logging.getLogger(__name__)
|
|
|
+logger.setLevel(logging.INFO)
|
|
|
+
|
|
|
+def log(msg):
|
|
|
+ '''
|
|
|
+ @summary:打印信息
|
|
|
+ '''
|
|
|
+ logger.info(msg)
|
|
|
+
|
|
|
+class DotDict(dict):
|
|
|
+
|
|
|
+ def __getattr__(self,name):
|
|
|
+ try:
|
|
|
+ return self[name]
|
|
|
+ except KeyError:
|
|
|
+ raise AttributeError("No attribute '%s'" % name)
|
|
|
+
|
|
|
+ def __setattr__(self,name,value):
|
|
|
+ self[name] = value
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+# 递归地将 DOM 转换为 JSON
|
|
|
+# 递归地将 DOM 转换为 JSON
|
|
|
+def dom_to_tree(node):
|
|
|
+ if node.name: # 如果是标签节点
|
|
|
+ json_obj = DotDict({"tag": node.name})
|
|
|
+ if node.attrs:
|
|
|
+ json_obj["attributes"] = node.attrs
|
|
|
+ children = []
|
|
|
+ for child in node.contents:
|
|
|
+ _child = dom_to_tree(child)
|
|
|
+ if _child is not None:
|
|
|
+ _child["parent"] = json_obj
|
|
|
+ children.append(_child)
|
|
|
+ if children:
|
|
|
+ json_obj["children"] = children
|
|
|
+ return json_obj
|
|
|
+ elif node.string and node.string.strip(): # 如果是纯文本节点
|
|
|
+ return DotDict({"tag":"text","text": node.string.strip()})
|
|
|
+ return None # 忽略空白字符
|
|
|
+
|
|
|
+def tree_pop_parent(tree):
|
|
|
+
|
|
|
+ if isinstance(tree,list):
|
|
|
+ for child in tree:
|
|
|
+ tree_pop_parent(child)
|
|
|
+ if isinstance(tree,dict):
|
|
|
+ if "parent" in tree:
|
|
|
+ del tree["parent"]
|
|
|
+ for child in tree.get("children",[]):
|
|
|
+ tree_pop_parent(child)
|
|
|
+
|
|
|
+
|
|
|
+def html_to_tree(html_content):
|
|
|
+ # 使用 BeautifulSoup 解析 HTML
|
|
|
+ soup = BeautifulSoup(html_content, "lxml")
|
|
|
+ dom_tree = dom_to_tree(soup)
|
|
|
+ return dom_tree
|
|
|
+
|
|
|
+def print_tree(dom_tree):
|
|
|
+ # 转换为 JSON 格式
|
|
|
+ tree_pop_parent(dom_tree)
|
|
|
+ json_output = json.dumps(dom_tree,ensure_ascii=False, indent=2)
|
|
|
+ print(json_output)
|
|
|
+
|
|
|
+# kv_pattern = "\s*(?P<key>.{,10})[:：]\s*(?P<value>[^:：。，()]+?)(\s+|$|;|；)(?![\u4e00-\u9fa5]+：)"
|
|
|
+kv_pattern = r"(?P<key>[\u4e00-\u9fa5]+)：\s*(?P<value>[^\s，。();；]+)"
|
|
|
+
|
|
|
+def get_kv_pattern():
|
|
|
+ import re
|
|
|
+
|
|
|
+ text = """
|
|
|
+ name: John age: 30 note: invalid;
|
|
|
+ """
|
|
|
+
|
|
|
+ # 正则模式
|
|
|
+ kv_pattern = r"(?P<key>[a-zA-Z]+)[:：](?P<value>.+(?!.*[:：]))"
|
|
|
+
|
|
|
+ # 提取匹配
|
|
|
+ matches = re.findall(kv_pattern, text)
|
|
|
+
|
|
|
+ # 打印结果
|
|
|
+ for match in matches:
|
|
|
+ key, value = match
|
|
|
+ print("{%s}: {%s}"%(key,value))
|
|
|
+def extract_kv_from_sentence(sentence):
|
|
|
+ list_kv = []
|
|
|
+ _iter = re.finditer("[:：]", sentence)
|
|
|
+ if _iter:
|
|
|
+ list_span = []
|
|
|
+ for iter in _iter:
|
|
|
+ list_span.append(iter.span())
|
|
|
+ if len(list_span)==1:
|
|
|
+ _begin,_end = list_span[0]
|
|
|
+ if _begin<20 and _end<len(sentence)-1:
|
|
|
+ _d = DotDict({"key":sentence[0:_begin],"value":sentence[_end:],"key_span":[0,_begin],"value_span":[_end,len(sentence)]})
|
|
|
+ list_kv.append(_d)
|
|
|
+ else:
|
|
|
+ _begin = 0
|
|
|
+ _end = len(sentence)-1
|
|
|
+ iter = re.search(kv_pattern,sentence[_begin:_end])
|
|
|
+ if iter is not None:
|
|
|
+ _d = DotDict({})
|
|
|
+ _d["key"] = iter.group("key")
|
|
|
+ _d["value"] = iter.group("value")
|
|
|
+ _d["key_span"] = iter.span("key")
|
|
|
+ _d["value_span"] = iter.span("value")
|
|
|
+ list_kv.append(_d)
|
|
|
+
|
|
|
+ elif len(list_span)>1:
|
|
|
+ _begin = 0
|
|
|
+
|
|
|
+ for _i in range(len(list_span)-1):
|
|
|
+ _end = list_span[_i+1][0]
|
|
|
+ iter = re.search(kv_pattern,sentence[_begin:_end])
|
|
|
+ _begin = list_span[_i][1]
|
|
|
+ if iter is not None:
|
|
|
+ _d = DotDict({})
|
|
|
+ _d["key"] = iter.group("key")
|
|
|
+ _d["value"] = iter.group("value")
|
|
|
+ _d["key_span"] = iter.span("key")
|
|
|
+ _d["value_span"] = iter.span("value")
|
|
|
+ list_kv.append(_d)
|
|
|
+
|
|
|
+ _begin = list_span[-2][1]
|
|
|
+ _end = len(sentence)
|
|
|
+ iter = re.search(kv_pattern,sentence[_begin:_end])
|
|
|
+ if iter is not None:
|
|
|
+ _d = DotDict({})
|
|
|
+ _d["key"] = iter.group("key")
|
|
|
+ _d["value"] = iter.group("value")
|
|
|
+ _d["key_span"] = iter.span("key")
|
|
|
+ _d["value_span"] = iter.span("value")
|
|
|
+ list_kv.append(_d)
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+ # for iter in _iter:
|
|
|
+ # _d = DotDict({})
|
|
|
+ # _d["key"] = iter.group("key")
|
|
|
+ # _d["value"] = iter.group("value")
|
|
|
+ # _d["key_span"] = iter.span("key")
|
|
|
+ # _d["value_span"] = iter.span("value")
|
|
|
+ # list_kv.append(_d)
|
|
|
+ return list_kv
|
|
|
+
|
|
|
+
|
|
|
+def extract_kv_from_node(node):
|
|
|
+ list_kv = []
|
|
|
+ _text = node.get("text")
|
|
|
+ if _text:
|
|
|
+ list_kv = extract_kv_from_sentence(_text)
|
|
|
+ node["kv"] = list_kv
|
|
|
+ return list_kv
|
|
|
+
|
|
|
+
|
|
|
+def get_child_text(node):
|
|
|
+ _text = node.get("text","")
|
|
|
+ for child in node.get("children",[]):
|
|
|
+ _text += get_child_text(child)
|
|
|
+ return _text
|
|
|
+def extract_kv_from_tree(tree):
|
|
|
+ if isinstance(tree,list):
|
|
|
+ _count = 0
|
|
|
+ for child in tree:
|
|
|
+ _count += extract_kv_from_tree(child)
|
|
|
+ return _count
|
|
|
+ if isinstance(tree,dict):
|
|
|
+ childs = tree.get("children",[])
|
|
|
+ if len(childs)>0:
|
|
|
+ _count = 0
|
|
|
+ for child in childs:
|
|
|
+ _count += extract_kv_from_tree(child)
|
|
|
+ if _count==0:
|
|
|
+ _text = get_child_text(tree)
|
|
|
+ if "children" in tree:
|
|
|
+ del tree["children"]
|
|
|
+ tree["text"] = _text
|
|
|
+ list_kv = extract_kv_from_node(tree)
|
|
|
+ _count = len(list_kv)
|
|
|
+ return _count
|
|
|
+ if tree.get("tag","")=="p":
|
|
|
+ _text = get_child_text(tree)
|
|
|
+ tree["text"] = _text
|
|
|
+ p_list_kv = extract_kv_from_node(tree)
|
|
|
+ if len(p_list_kv)>=_count:
|
|
|
+ if "children" in tree:
|
|
|
+ del tree["children"]
|
|
|
+ else:
|
|
|
+ tree["text"] = ""
|
|
|
+ return len(p_list_kv)
|
|
|
+
|
|
|
+ return _count
|
|
|
+ else:
|
|
|
+ list_kv = extract_kv_from_node(tree)
|
|
|
+ return len(list_kv)
|
|
|
+
|
|
|
+
|
|
|
+def update_kv_span(list_kv,append_length):
|
|
|
+ for _d in list_kv:
|
|
|
+ _d["key_span"][0] += append_length
|
|
|
+ _d["key_span"][1] += append_length
|
|
|
+ _d["value_span"][0] += append_length
|
|
|
+ _d["value_span"][1] += append_length
|
|
|
+
|
|
|
+def get_sentence_from_tree(tree,list_sentences=None):
|
|
|
+
|
|
|
+ is_first = False
|
|
|
+ if list_sentences is None:
|
|
|
+ list_sentences = []
|
|
|
+ is_first = True
|
|
|
+ if isinstance(tree,list):
|
|
|
+ for child in tree:
|
|
|
+ get_sentence_from_tree(child,list_sentences)
|
|
|
+ if isinstance(tree,dict):
|
|
|
+ childs = tree.get("children",[])
|
|
|
+ _text = tree.get("text","")
|
|
|
+ if _text!="":
|
|
|
+ tree.name = tree.tag
|
|
|
+ list_sentences.append(tree)
|
|
|
+ for child in childs:
|
|
|
+ get_sentence_from_tree(child,list_sentences)
|
|
|
+ if is_first:
|
|
|
+ wordOffset_begin = 0
|
|
|
+ wordOffset_end = 0
|
|
|
+ for _i in range(len(list_sentences)):
|
|
|
+ list_sentences[_i].sentence_index = _i
|
|
|
+ list_sentences[_i].wordOffset_begin = wordOffset_begin
|
|
|
+ wordOffset_end = wordOffset_begin+len(list_sentences[_i].text)
|
|
|
+ list_sentences[_i].wordOffset_end = wordOffset_end
|
|
|
+ wordOffset_begin = wordOffset_end
|
|
|
+
|
|
|
+ return list_sentences
|
|
|
+
|
|
|
+
|
|
|
+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("）",")")
|
|
|
+
|
|
|
+
|
|
|
+import Levenshtein
|
|
|
+import copy
|
|
|
+def jaccard_score(source,target):
|
|
|
+ source_set = set([s for s in source])
|
|
|
+ target_set = set([s for s in target])
|
|
|
+ if len(source_set)==0 or len(target_set)==0:
|
|
|
+ return 0
|
|
|
+ return max(len(source_set&target_set)/len(source_set),len(source_set&target_set)/len(target_set))
|
|
|
+
|
|
|
+
|
|
|
+def judge_pur_chinese(keyword):
|
|
|
+ """
|
|
|
+ 中文字符的编码范围为： u'\u4e00' -- u'\u9fff：只要在此范围内就可以判断为中文字符串
|
|
|
+ @param keyword:
|
|
|
+ @return:
|
|
|
+ """
|
|
|
+ # 定义一个需要删除的标点符号字符串列表
|
|
|
+ remove_chars = '[·’!"\#$%&\'()＃！（）*+,-./:;<=>?\@，：?￥★、…．＞【】［］《》？“”‘’\[\\]^_`{|}~]+'
|
|
|
+ # 利用re.sub来删除中文字符串中的标点符号
|
|
|
+ strings = re.sub(remove_chars, "", keyword) # 将keyword中文字符串中remove_chars中包含的标点符号替换为空字符串
|
|
|
+ for ch in strings:
|
|
|
+ if u'\u4e00' <= ch <= u'\u9fff':
|
|
|
+ pass
|
|
|
+ else:
|
|
|
+ return False
|
|
|
+ return True
|
|
|
+def is_similar(source,target,_radio=None):
|
|
|
+ source = str(source).lower()
|
|
|
+ target = str(target).lower()
|
|
|
+ max_len = max(len(source),len(target))
|
|
|
+ min_len = min(len(source),len(target))
|
|
|
+
|
|
|
+ min_ratio = 90
|
|
|
+ if min_len>=3:
|
|
|
+ min_ratio = 87
|
|
|
+ if min_len>=5:
|
|
|
+ min_ratio = 85
|
|
|
+ if _radio is not None:
|
|
|
+ min_ratio = _radio
|
|
|
+ # dis_len = abs(len(source)-len(target))
|
|
|
+ # min_dis = min(max_len*0.2,4)
|
|
|
+ if min_len==0 and max_len>0:
|
|
|
+ return False
|
|
|
+ if max_len<=2:
|
|
|
+ if source==target:
|
|
|
+ return True
|
|
|
+ if min_len<2:
|
|
|
+ return False
|
|
|
+ #判断相似度
|
|
|
+ similar = Levenshtein.ratio(source,target)*100
|
|
|
+ if similar>=min_ratio:
|
|
|
+ log("%s and %s similar_jaro %d"%(source,target,similar))
|
|
|
+ return True
|
|
|
+ similar_jaro = Levenshtein.jaro(source,target)
|
|
|
+ if similar_jaro*100>=min_ratio:
|
|
|
+ log("%s and %s similar_jaro %d"%(source,target,similar_jaro*100))
|
|
|
+ return True
|
|
|
+ similar_jarow = Levenshtein.jaro_winkler(source,target)
|
|
|
+ if similar_jarow*100>=min_ratio:
|
|
|
+ log("%s and %s similar_jaro %d"%(source,target,similar_jarow*100))
|
|
|
+ return True
|
|
|
+
|
|
|
+ if min_len>=5:
|
|
|
+ if len(source)==max_len and str(source).find(target)>=0:
|
|
|
+ return True
|
|
|
+ elif len(target)==max_len and target.find(source)>=0:
|
|
|
+ return True
|
|
|
+ elif jaccard_score(source, target)==1 and judge_pur_chinese(source) and judge_pur_chinese(target):
|
|
|
+ return True
|
|
|
+ return False
|
|
|
+
|
|
|
+
|
|
|
+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
|
|
|
+
|
|
|
+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, max_depth=None):
|
|
|
+ list_data = []
|
|
|
+ for _child in childs:
|
|
|
+ list_data.append(_child)
|
|
|
+ childs2 = _child.get("child_title",[])
|
|
|
+
|
|
|
+ if len(childs2)>0 and (max_depth==None or max_depth>0):
|
|
|
+ for _child2 in childs2:
|
|
|
+ if max_depth != None:
|
|
|
+ list_data.extend(get_childs([_child2], max_depth-1))
|
|
|
+ else:
|
|
|
+ list_data.extend(get_childs([_child2], None))
|
|
|
+ return list_data
|
|
|
+
|
|
|
+class Html2KVTree():
|
|
|
+
|
|
|
+ def __init__(self,_html,auto_merge_table=True,list_obj = []):
|
|
|
+ if _html is None:
|
|
|
+ _html = ""
|
|
|
+ self.html = _html
|
|
|
+ self.auto_merge_table = auto_merge_table
|
|
|
+
|
|
|
+ if list_obj:
|
|
|
+ self.list_obj = list_obj
|
|
|
+ else:
|
|
|
+
|
|
|
+ _tree = html_to_tree(html_content)
|
|
|
+ extract_kv_from_tree(_tree)
|
|
|
+ self.list_obj = get_sentence_from_tree(_tree)
|
|
|
+
|
|
|
+ print(len(self.list_obj))
|
|
|
+
|
|
|
+
|
|
|
+ # 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
|
|
|
+ # 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)
|
|
|
+ elif _obj.name=="p":
|
|
|
+ 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="",set_tree_id=None):
|
|
|
+ if set_tree_id is None:
|
|
|
+ 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 set_tree_id:
|
|
|
+ continue
|
|
|
+ set_tree_id.add(_id)
|
|
|
+ logger.info("%s text:%s title:%s title_text:%s before:%s after%s product:%s kv:%s"%(append,t["text"][:50],t["sentence_title"],t["sentence_title_text"],t["title_before"],t["title_after"],t["has_product"],str(t["kv"])))
|
|
|
+ childs = t["child_title"]
|
|
|
+ self.print_tree(childs,append=append+"-|",set_tree_id=set_tree_id)
|
|
|
+
|
|
|
+ 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:
|
|
|
+ e = _se.end()
|
|
|
+ if re.search('(时间|日期|编号|账号|号码|手机|价格|\w价|人民币|金额|得分|分值|总分|满分|最高得|扣|减|数量|评委)[:：]?\d', _se.group(0)) or (re.search('\d[.:：]?$', _se.group(0)) and re.search('^[\d年月日万元天个分秒台条A-Za-z]|^(小时)', _text[e:])):
|
|
|
+ return None
|
|
|
+ elif re.match('[二三四五六七八九十]\w{1,2}[市区县]|五金|四川|八疆|九龙|[一二三四五六七八九十][层天标包]', _text) and re.match('[一二三四五六七八九十]', _se.group(0)): # 289765335 排除三明市等开头作为大纲
|
|
|
+ return None
|
|
|
+ elif re.search('^[\u4e00-\u9fa5]+[:：]', _text[:e]):
|
|
|
+ return None
|
|
|
+ _gd = _se.groupdict()
|
|
|
+ for k,v in _gd.items():
|
|
|
+ if v is not None:
|
|
|
+ groups.append((k,v))
|
|
|
+ if len(groups):
|
|
|
+ groups.sort(key=lambda x:x[0])
|
|
|
+ return groups
|
|
|
+ return None
|
|
|
+
|
|
|
+ def make_increase(self,_sort,_title,_add=1):
|
|
|
+ if len(_title)==0 and _add==0:
|
|
|
+ return ""
|
|
|
+ if len(_title)==0 and _add==1:
|
|
|
+ return _sort[0]
|
|
|
+ _index = _sort.index(_title[-1])
|
|
|
+ next_index = (_index+_add)%len(_sort)
|
|
|
+ next_chr = _sort[next_index]
|
|
|
+ if _index==len(_sort)-1:
|
|
|
+ _add = 1
|
|
|
+ else:
|
|
|
+ _add = 0
|
|
|
+ return next_chr+self.make_increase(_sort,_title[:-1],_add)
|
|
|
+
|
|
|
+
|
|
|
+ def get_next_title(self,_title):
|
|
|
+ if re.search("^\d+$",_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,auto_append=False):
|
|
|
+
|
|
|
+ self.parseTree = None
|
|
|
+ trees = []
|
|
|
+ list_length = []
|
|
|
+ for obj in list_obj[:200]:
|
|
|
+ if obj.name!="table":
|
|
|
+ list_length.append(len(obj.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 = []
|
|
|
+ # new
|
|
|
+ sentence_index = obj.sentence_index
|
|
|
+ wordOffset_begin = obj.wordOffset_begin
|
|
|
+ wordOffset_end = obj.wordOffset_end
|
|
|
+
|
|
|
+ list_kv = obj.get("kv",[])
|
|
|
+
|
|
|
+ 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
|
|
|
+
|
|
|
+ # 合并两个非标题句子 20241106 注销，由于 485441521 招标内容结束位置不对
|
|
|
+ if auto_append:
|
|
|
+ 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)
|
|
|
+ update_kv_span(list_kv,len(_text))
|
|
|
+ list_data[-1]["kv"].extend(list_kv)
|
|
|
+ _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)
|
|
|
+ update_kv_span(list_kv,len(_text))
|
|
|
+ list_data[-1]["kv"].extend(list_kv)
|
|
|
+ _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,
|
|
|
+ "sentence_index":sentence_index,"wordOffset_begin":wordOffset_begin,"wordOffset_end":wordOffset_end,
|
|
|
+ "kv":list_kv
|
|
|
+ }
|
|
|
+
|
|
|
+ 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 get_sentence_tree(self):
|
|
|
+ return self.tree
|
|
|
+
|
|
|
+ def extract_kv(self,k_pattern,from_kv=True,from_outline=True):
|
|
|
+ result_kv = []
|
|
|
+ try:
|
|
|
+ re.compile(k_pattern)
|
|
|
+ except Exception as e:
|
|
|
+ log("k_pattern error: "+str(e))
|
|
|
+ traceback.print_exc()
|
|
|
+ return result_kv
|
|
|
+ for sentence in self.tree:
|
|
|
+ _text = sentence["text"]
|
|
|
+ list_kv = sentence.get("kv",[])
|
|
|
+ sentence_index_from = sentence["sentence_index"]
|
|
|
+ sentence_index_to = sentence_index_from
|
|
|
+ if from_kv:
|
|
|
+ for _d in list_kv:
|
|
|
+ _k = _d.get("key","")
|
|
|
+ _v = _d.get("value","")
|
|
|
+ _k_span = _d.get("key_span",[])
|
|
|
+ _v_span = _d.get("value_span",[])
|
|
|
+ if re.search(k_pattern,_k) is not None:
|
|
|
+ result_kv.append({"key":_k,"value":_v,"from_kv":True,"key_sentence_index_from":sentence_index_from,
|
|
|
+ "key_sentence_index_to":sentence_index_to,"value_sentence_index_from":sentence_index_from,
|
|
|
+ "value_sentence_index_to":sentence_index_to,
|
|
|
+ "key_span":_k_span,
|
|
|
+ "value_span":_v_span})
|
|
|
+ if from_outline:
|
|
|
+ if re.search(k_pattern,_text) is not None and sentence.get("sentence_title") is not None:
|
|
|
+
|
|
|
+ childs = get_childs([sentence])
|
|
|
+ _child_text = ""
|
|
|
+ for _child in childs:
|
|
|
+ sentence_index_to = _child["sentence_index"]
|
|
|
+ _child_text+=_child["text"]
|
|
|
+ result_kv.append({"key":_text,"value":_child_text,"from_outline":True,"key_sentence_index_from":sentence_index_from,
|
|
|
+ "key_sentence_index_to":sentence_index_from,"value_sentence_index_from":sentence_index_from,
|
|
|
+ "value_sentence_index_to":sentence_index_to,})
|
|
|
+ return result_kv
|
|
|
+
|
|
|
+ # def extract_kvs_from_table(self,list_pattern):
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+if __name__ == '__main__':
|
|
|
+ # HTML 文本
|
|
|
+ html_content = """
|
|
|
+<div>
|
|
|
+ <div>
|
|
|
+ 中介服务交易|中介服务交易；中选公示；广东省中介超市交易系统
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 采购项目编码： 4451024573035462411180923
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 采购项目名称： 意溪中学办公楼一楼卫生间、保密室、运动场围墙及零碎修缮工程（结算审核）
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 项目业主名称： <a target="_blank" class="markBlue" href="/bdqyhx/212724763956953088.html" style="color: #3083EB !important;text-decoration: underline;">潮州市湘桥区意溪中学</a>
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 中介服务事项： 无（属于非行政管理的中介服务项目采购）
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 投资审批项目编码：
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 服务金额： 暂不做评估与测算
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 金额说明： 按粤价函【2011】742号文及潮财建【2019】19号文的收费标准执行 （行业收费标准）计算。
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 选取中介机构方式： 直接选取
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 业务单位咨询电话： 13715781262
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 监督举报：
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 中选中介机构名称： <a target="_blank" class="markBlue" href="/bdqyhx/216479817075470337.html" style="color: #3083EB !important;text-decoration: underline;">中庭国际设计有限公司</a>
|
|
|
+ </div>
|
|
|
+ <div>
|
|
|
+ 中介机构联系地址： 广州市天河区大观南路26号C203A
|
|
|
+ </div>
|
|
|
+</div>
|
|
|
+ """
|
|
|
+ _tree = html_to_tree(html_content)
|
|
|
+ extract_kv_from_tree(_tree)
|
|
|
+
|
|
|
+ list_sentences = get_sentence_from_tree(_tree)
|
|
|
+ _pd = Html2KVTree(html_content)
|
|
|
+ _pd.print_tree(_pd.tree,"-|")
|
|
|
+
|
|
|
+
|
|
|
+ list_kv = _pd.extract_kv("交货地点")
|
|
|
+ print(list_kv)
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+
|
luojiehua