crawlab_feader/FworkSpider/untils/check_data.py

import re


class CheckData:
    """检查数据文本内容"""
    __bidding_title_set = {'招标', '流标', '评标', '询价', '中标候选人', '抽签',
                           '谈判', '中选', '意见征询', '更正公告', '废标',
                           '补遗', '议价', '邀请', '资格预审', '竞标', '变更',
                           '遴选', '磋商', '项目', '评审', '询比', '开标',
                           '澄清', '比选', '中止', '采购', '竟价', '招投标',
                           '拟建', '成交', '中标', '竞争性谈判', '工程',
                           '验收公告', '更正', '单一来源', '变更公告', '合同',
                           '违规', '评判', '监理', '竞价', '答疑', '终止',
                           '系统'}

    __bidding_channel_set = {"通知公告", "公告公示", "公示公告"}

    __plan_to_build_title_set = {'项目', '工程', '验收', '评价', '设计', '调查',
                                 '审核', '审批', '批复', '批后', '批前', '核准',
                                 '备案', '立项', '规划设计', '环评', }

    __plan_to_build_channel_set = {"通知", "部门文件", "公告", "公示",
                                    "办件" ,"公司", "新闻", "最新资讯"}

    @classmethod
    def title(cls, name: str, group=None):
        check_texts = cls.__bidding_title_set
        if group and group.lower() in ["njpc", "plan_to_build"]:
            check_texts = cls.__plan_to_build_title_set

        for text in check_texts:
            valid_text = re.search(text, name)
            if valid_text is not None:
                break
        else:
            return 10106, '标题未检索到采集关键词'
        return 200, 'ok'

    @classmethod
    def channel(cls, name: str, group=None):
        check_texts = cls.__bidding_channel_set
        if group and group.lower() in ["njpc", "plan_to_build"]:
            check_texts = cls.__plan_to_build_channel_set

        for text in check_texts:
            valid_text = re.search(text, name)
            if valid_text is not None:
                break
        else:
            return False
        return True