写一个函数解析公众号文章的 URL,变为一个三元组。用到 base64 解密。
private def parseUrlToTriTuple(url:String): Option[String] = {
var id_tuple = url.split("&")
if (id_tuple.length < 3) {
return None
}
var tupleItemIndexs = Array(-1, -1, -1)
for (idx <- 0 until id_tuple.length) {
var pattern_bizuin = "__biz=".r
var pattern_msgid = "mid=".r
var pattern_msgidx = "idx=".r
if (pattern_bizuin.findFirstIn(id_tuple(idx)) != None) {
tupleItemIndexs(0) = idx
}
else if (pattern_msgid.findFirstIn(id_tuple(idx)) != None) {
tupleItemIndexs(1) = idx
}
else if (pattern_msgidx.findFirstIn(id_tuple(idx)) != None) {
tupleItemIndexs(2) = idx
}
}
// 是否包含三元组的名字
for (item <- tupleItemIndexs) {
if (item == -1)
return None
}
var uin_pos = id_tuple(tupleItemIndexs(0)).indexOf("__biz=")
var encode_uin = id_tuple(tupleItemIndexs(0)).substring(uin_pos+6)
var decode_uin = new String(Base64.decodeBase64(encode_uin))
var mid_pos = id_tuple(tupleItemIndexs(1)).indexOf("=")
var msg_id = id_tuple(tupleItemIndexs(1)).substring(mid_pos+1)
var idx_pos = id_tuple(tupleItemIndexs(2)).indexOf("=")
var msg_idx = id_tuple(tupleItemIndexs(2)).substring(idx_pos+1)
return Some(decode_uin + "_" + msg_id + "_" + msg_idx)
}