发布时间提取正则汇总

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

# 部分特别规范的新闻网站,可以直接从 HTML 的 meta 数据中获得发布时间
PUBLISH_TIME_META = [
    '//meta[starts-with(@property, "rnews:datePublished")]/@content',
    '//meta[starts-with(@property, "article:published_time")]/@content',
    '//meta[starts-with(@property, "og:published_time")]/@content',
    '//meta[starts-with(@property, "og:release_date")]/@content',
    '//meta[starts-with(@itemprop, "datePublished")]/@content',
    '//meta[starts-with(@itemprop, "dateUpdate")]/@content',
    '//meta[starts-with(@name, "OriginalPublicationDate")]/@content',
    '//meta[starts-with(@name, "article_date_original")]/@content',
    '//meta[starts-with(@name, "og:time")]/@content',
    '//meta[starts-with(@name, "apub:time")]/@content',
    '//meta[starts-with(@name, "publication_date")]/@content',
    '//meta[starts-with(@name, "sailthru.date")]/@content',
    '//meta[starts-with(@name, "PublishDate")]/@content',
    '//meta[starts-with(@name, "publishdate")]/@content',
    '//meta[starts-with(@name, "PubDate")]/@content',
    '//meta[starts-with(@name, "pubtime")]/@content',
    '//meta[starts-with(@name, "_pubtime")]/@content',
    '//meta[starts-with(@name, "weibo: article:create_at")]/@content',
    '//meta[starts-with(@pubdate, "pubdate")]/@content',
]

 

posted @ 2020-11-18 15:16  淋哥  阅读(285)  评论(0编辑  收藏  举报