topic_spider/find_source/crawler/analysis/TimeExtractor.py

import re

from lxml.html import HtmlElement

DATETIME_PATTERN = [
    "(\d{4}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[0-1]?[0-9]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{4}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[2][0-3]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{4}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[0-1]?[0-9]:[0-5]?[0-9])",
    "(\d{4}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[2][0-3]:[0-5]?[0-9])",
    "(\d{4}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[1-24]\d时[0-60]\d分)([1-24]\d时)",
    "(\d{2}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[0-1]?[0-9]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{2}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[2][0-3]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{2}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[0-1]?[0-9]:[0-5]?[0-9])",
    "(\d{2}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[2][0-3]:[0-5]?[0-9])",
    "(\d{2}[-|/|.]\d{1,2}[-|/|.]\d{1,2}\s*?[1-24]\d时[0-60]\d分)([1-24]\d时)",
    "(\d{1,2}[-|/|.]\d{1,2})",
    "(\d{4}年\d{1,2}月\d{1,2}日\s*?[0-1]?[0-9]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{4}年\d{1,2}月\d{1,2}日\s*?[2][0-3]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{4}年\d{1,2}月\d{1,2}日\s*?[0-1]?[0-9]:[0-5]?[0-9])",
    "(\d{4}年\d{1,2}月\d{1,2}日\s*?[2][0-3]:[0-5]?[0-9])",
    "(\d{4}年\d{1,2}月\d{1,2}日\s*?[1-24]\d时[0-60]\d分)([1-24]\d时)",
    "(\d{2}年\d{1,2}月\d{1,2}日\s*?[0-1]?[0-9]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{2}年\d{1,2}月\d{1,2}日\s*?[2][0-3]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{2}年\d{1,2}月\d{1,2}日\s*?[0-1]?[0-9]:[0-5]?[0-9])",
    "(\d{2}年\d{1,2}月\d{1,2}日\s*?[2][0-3]:[0-5]?[0-9])",
    "(\d{2}年\d{1,2}月\d{1,2}日\s*?[1-24]\d时[0-60]\d分)([1-24]\d时)",
    "(\d{1,2}月\d{1,2}日\s*?[0-1]?[0-9]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{1,2}月\d{1,2}日\s*?[2][0-3]:[0-5]?[0-9]:[0-5]?[0-9])",
    "(\d{1,2}月\d{1,2}日\s*?[0-1]?[0-9]:[0-5]?[0-9])",
    "(\d{1,2}月\d{1,2}日\s*?[2][0-3]:[0-5]?[0-9])",
    "(\d{1,2}月\d{1,2}日\s*?[1-24]\d时[0-60]\d分)([1-24]\d时)",
    "(\d{4}[-|/|.]\d{1,2}[-|/|.]\d{1,2})",
    "(\d{2}[-|/|.]\d{1,2}[-|/|.]\d{1,2})",
    "(\d{4}年\d{1,2}月\d{1,2}日)",
    "(\d{2}年\d{1,2}月\d{1,2}日)",
    "(\d{1,2}月\d{1,2}日)"
]


class TimeExtractor:
    def __init__(self):
        self.time_pattern = DATETIME_PATTERN

    def extractor(self, element: HtmlElement) -> str:
        # text = ''.join(element.xpath('.//text()'))
        text = ''.join(element.xpath('string(.)'))
        for dt in self.time_pattern:
            dt_obj = re.search(dt, text)
            if dt_obj:
                return dt_obj.group(1)
        else:
            return ''