|
|
@@ -1960,7 +1960,7 @@ def del_tabel_achievement(soup):
|
|
|
if re.search('中标|成交|入围|结果|评标|开标|候选人', soup.text[:800]) == None or re.search('业绩', soup.text)==None:
|
|
|
return None
|
|
|
p1 = '中标(单位|候选人)的?(企业|项目|项目负责人|\w{,5})?业绩|类似(项目)?业绩|\w{,10}业绩$|业绩(公示|情况|荣誉)'
|
|
|
-
|
|
|
+ '''删除前面标签 命中业绩规则；当前标签为表格且公布业绩相关信息的去除'''
|
|
|
for tag in soup.find_all('table'):
|
|
|
pre_text = tag.findPreviousSibling().text.strip() if tag.findPreviousSibling() != None else ""
|
|
|
tr_text = tag.find('tr').text.strip() if tag.find('tr') != None else ""
|
|
|
@@ -1977,10 +1977,12 @@ def del_tabel_achievement(soup):
|
|
|
pre_tag = tag.findPreviousSibling().extract()
|
|
|
del_tag = tag.extract()
|
|
|
# print('删除表格业绩内容', pre_tag.text + del_tag.text)
|
|
|
+ break
|
|
|
elif re.search('业绩名称', tr_text) and re.search('建设单位|采购单位|业主', tr_text) and len(tr_text)<100:
|
|
|
del_tag = tag.extract()
|
|
|
# print('删除表格业绩内容', del_tag.text)
|
|
|
del_trs = []
|
|
|
+ '''删除表格某些行公布的业绩信息'''
|
|
|
for tag in soup.find_all('table'):
|
|
|
text = tag.text
|
|
|
if re.search('业绩', text) == None:
|
luojiehua