spark读取json文件

 JSON文件

1593136280858|{"cm":{"ln":"-55.0","sv":"V2.9.6","os":"8.0.4","g":"C6816QZ0@gmail.com","mid":"489","nw":"3G","l":"es","vc":"4","hw":"640*960","ar":"MX","uid":"489","t":"1593123253541","la":"5.2","md":"sumsung-18","vn":"1.3.4","ba":"Sumsung","sr":"I"},"ap":"app","et":[{"ett":"1593050051366","en":"loading","kv":{"extend2":"","loading_time":"14","action":"3","extend1":"","type":"2","type1":"201","loading_way":"1"}},{"ett":"1593108791764","en":"ad","kv":{"activityId":"1","displayMills":"78522","entry":"1","action":"1","contentType":"0"}},{"ett":"1593111271266","en":"notification","kv":{"ap_time":"1593097087883","action":"1","type":"1","content":""}},{"ett":"1593066033562","en":"active_background","kv":{"active_source":"3"}},{"ett":"1593135644347","en":"comment","kv":{"p_comment_id":1,"addtime":"1593097573725","praise_count":973,"other_id":5,"comment_id":9,"reply_count":40,"userid":7,"content":"辑赤蹲慰鸽抿肘捎"}}]}
1593136280858|{"cm":{"ln":"-114.9","sv":"V2.7.8","os":"8.0.4","g":"NW0S962J@gmail.com","mid":"490","nw":"3G","l":"pt","vc":"8","hw":"640*1136","ar":"MX","uid":"490","t":"1593121224789","la":"-44.4","md":"Huawei-8","vn":"1.0.1","ba":"Huawei","sr":"O"},"ap":"app","et":[{"ett":"1593063223807","en":"loading","kv":{"extend2":"","loading_time":"0","action":"3","extend1":"","type":"1","type1":"102","loading_way":"1"}},{"ett":"1593095105466","en":"ad","kv":{"activityId":"1","displayMills":"1966","entry":"3","action":"2","contentType":"0"}},{"ett":"1593051718208","en":"notification","kv":{"ap_time":"1593095336265","action":"2","type":"3","content":""}},{"ett":"1593100021275","en":"comment","kv":{"p_comment_id":4,"addtime":"1593098946009","praise_count":220,"other_id":4,"comment_id":9,"reply_count":151,"userid":4,"content":"抄应螟皮釉倔掉汉蛋蕾街羡晶"}},{"ett":"1593105344120","en":"praise","kv":{"target_id":9,"id":7,"type":1,"add_time":"1593098545976","userid":8}}]}

操作步骤

1.val fileRDD=sc.textFile("hdfs://192.168.28.70:9000/kb09file/op.log")

fileRDD.collect.foreach(println)
1593136280858|{"cm":{"ln":"-55.0","sv":"V2.9.6","os":"8.0.4","g":"C6816QZ0@gmail.com","mid":"489","nw":"3G","l":"es","vc":"4","hw":"640*960","ar":"MX","uid":"489","t":"1593123253541","la":"5.2","md":"sumsung-18","vn":"1.3.4","ba":"Sumsung","sr":"I"},"ap":"app","et":[{"ett":"1593050051366","en":"loading","kv":{"extend2":"","loading_time":"14","action":"3","extend1":"","type":"2","type1":"201","loading_way":"1"}},{"ett":"1593108791764","en":"ad","kv":{"activityId":"1","displayMills":"78522","entry":"1","action":"1","contentType":"0"}},{"ett":"1593111271266","en":"notification","kv":{"ap_time":"1593097087883","action":"1","type":"1","content":""}},{"ett":"1593066033562","en":"active_background","kv":{"active_source":"3"}},{"ett":"1593135644347","en":"comment","kv":{"p_comment_id":1,"addtime":"1593097573725","praise_count":973,"other_id":5,"comment_id":9,"reply_count":40,"userid":7,"content":"辑赤蹲慰鸽抿肘捎"}}]}
1593136280858|{"cm":{"ln":"-114.9","sv":"V2.7.8","os":"8.0.4","g":"NW0S962J@gmail.com","mid":"490","nw":"3G","l":"pt","vc":"8","hw":"640*1136","ar":"MX","uid":"490","t":"1593121224789","la":"-44.4","md":"Huawei-8","vn":"1.0.1","ba":"Huawei","sr":"O"},"ap":"app","et":[{"ett":"1593063223807","en":"loading","kv":{"extend2":"","loading_time":"0","action":"3","extend1":"","type":"1","type1":"102","loading_way":"1"}},{"ett":"1593095105466","en":"ad","kv":{"activityId":"1","displayMills":"1966","entry":"3","action":"2","contentType":"0"}},{"ett":"1593051718208","en":"notification","kv":{"ap_time":"1593095336265","action":"2","type":"3","content":""}},{"ett":"1593100021275","en":"comment","kv":{"p_comment_id":4,"addtime":"1593098946009","praise_count":220,"other_id":4,"comment_id":9,"reply_count":151,"userid":4,"content":"抄应螟皮釉倔掉汉蛋蕾街羡晶"}},{"ett":"1593105344120","en":"praise","kv":{"target_id":9,"id":7,"type":1,"add_time":"1593098545976","userid":8}}]}

2. val jsonStrRDD=fileRDD.map(x=>x.split('|')).map(x=>(x(0),x(1)))
val jsonRDD=jsonStrRDD.map(x=>{val jsonStr=x._2;val jsonStr1=jsonStr.substring(0,jsonStr.length-1); jsonStr1+",\"id\":\""+x._1+"\"}"})

 jsonRDD.collect.foreach(println)
{"cm":{"ln":"-55.0","sv":"V2.9.6","os":"8.0.4","g":"C6816QZ0@gmail.com","mid":"489","nw":"3G","l":"es","vc":"4","hw":"640*960","ar":"MX","uid":"489","t":"1593123253541","la":"5.2","md":"sumsung-18","vn":"1.3.4","ba":"Sumsung","sr":"I"},"ap":"app","et":[{"ett":"1593050051366","en":"loading","kv":{"extend2":"","loading_time":"14","action":"3","extend1":"","type":"2","type1":"201","loading_way":"1"}},{"ett":"1593108791764","en":"ad","kv":{"activityId":"1","displayMills":"78522","entry":"1","action":"1","contentType":"0"}},{"ett":"1593111271266","en":"notification","kv":{"ap_time":"1593097087883","action":"1","type":"1","content":""}},{"ett":"1593066033562","en":"active_background","kv":{"active_source":"3"}},{"ett":"1593135644347","en":"comment","kv":{"p_comment_id":1,"addtime":"1593097573725","praise_count":973,"other_id":5,"comment_id":9,"reply_count":40,"userid":7,"content":"辑赤蹲慰鸽抿肘捎"}}],"id":"1593136280858"}
{"cm":{"ln":"-114.9","sv":"V2.7.8","os":"8.0.4","g":"NW0S962J@gmail.com","mid":"490","nw":"3G","l":"pt","vc":"8","hw":"640*1136","ar":"MX","uid":"490","t":"1593121224789","la":"-44.4","md":"Huawei-8","vn":"1.0.1","ba":"Huawei","sr":"O"},"ap":"app","et":[{"ett":"1593063223807","en":"loading","kv":{"extend2":"","loading_time":"0","action":"3","extend1":"","type":"1","type1":"102","loading_way":"1"}},{"ett":"1593095105466","en":"ad","kv":{"activityId":"1","displayMills":"1966","entry":"3","action":"2","contentType":"0"}},{"ett":"1593051718208","en":"notification","kv":{"ap_time":"1593095336265","action":"2","type":"3","content":""}},{"ett":"1593100021275","en":"comment","kv":{"p_comment_id":4,"addtime":"1593098946009","praise_count":220,"other_id":4,"comment_id":9,"reply_count":151,"userid":4,"content":"抄应螟皮釉倔掉汉蛋蕾街羡晶"}},{"ett":"1593105344120","en":"praise","kv":{"target_id":9,"id":7,"type":1,"add_time":"1593098545976","userid":8}}],"id":"1593136280858"}

3.val jsonDF=jsonRDD.toDF
val jsonDF2=jsonDF.select(get_json_object($"value","$.cm").alias("cm")
,get_json_object($"value","$.ap").alias("ap")
,get_json_object($"value","$.et").alias("et")
,get_json_object($"value","$.id").alias("id"))

jsonDF2.show
+--------------------+---+--------------------+-------------+
|                  cm| ap|                  et|           id|
+--------------------+---+--------------------+-------------+
|{"ln":"-55.0","sv...|app|[{"ett":"15930500...|1593136280858|
|{"ln":"-114.9","s...|app|[{"ett":"15930632...|1593136280858|
+--------------------+---+--------------------+-------------+

4.val jsonDF3=jsonDF2.select(get_json_object($"cm","$.ln").alias("ln"),get_json_object($"cm","$.sv").alias("sv")
,get_json_object($"cm","$.os").alias("os"),get_json_object($"cm","$.g").alias("g")
,get_json_object($"cm","$.mid").alias("mid"),get_json_object($"cm","$.nw").alias("nw")
,get_json_object($"cm","$.l").alias("l"),get_json_object($"cm","$.vc").alias("vc")
,get_json_object($"cm","$.hw").alias("hw"),get_json_object($"cm","$.ar").alias("ar")
,get_json_object($"cm","$.uid").alias("uid"),get_json_object($"cm","$.t").alias("t")
,get_json_object($"cm","$.la").alias("la"),get_json_object($"cm","$.md").alias("md")
,get_json_object($"cm","$.vn").alias("vn"),get_json_object($"cm","$.ba").alias("ba")
,get_json_object($"cm","$.sr").alias("sr"),$"et",$"id",$"ap"
)

 jsonDF3.show
+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+-------------+---+
|    ln|    sv|   os|                 g|mid| nw|  l| vc|      hw| ar|uid|            t|   la|        md|   vn|     ba| sr|                  et|           id| ap|
+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+-------------+---+
| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[{"ett":"15930500...|1593136280858|app|
|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[{"ett":"15930632...|1593136280858|app|
+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+-------------+---+

5.val jsonDF4 = jsonDF3.select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",from_json($"et",ArrayType(StructType(StructField("ett",StringType)::StructField("en",StringType)::StructField("kv",StringType)::Nil))).alias("event"))
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+
|           id| ap|    ln|    sv|   os|                 g|mid| nw|  l| vc|      hw| ar|uid|            t|   la|        md|   vn|     ba| sr|               event|
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[[1593050051366, ...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[[1593063223807, ...|
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+

6.val josnDF5 = jsonDF4.select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",explode($"event").alias("event"))
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+
|           id| ap|    ln|    sv|   os|                 g|mid| nw|  l| vc|      hw| ar|uid|            t|   la|        md|   vn|     ba| sr|               event|
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[1593050051366, l...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[1593108791764, a...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[1593111271266, n...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[1593066033562, a...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|[1593135644347, c...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[1593063223807, l...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[1593095105466, a...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[1593051718208, n...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[1593100021275, c...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|[1593105344120, p...|
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+--------------------+


7.val jsonDF6 = josnDF5.select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"event.ett",$"event.en",$"event.kv")
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+-------------+-----------------+--------------------+
|           id| ap|    ln|    sv|   os|                 g|mid| nw|  l| vc|      hw| ar|uid|            t|   la|        md|   vn|     ba| sr|          ett|               en|                  kv|
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+-------------+-----------------+--------------------+
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|1593050051366|          loading|{"extend2":"","lo...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|1593108791764|               ad|{"activityId":"1"...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|1593111271266|     notification|{"ap_time":"15930...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|1593066033562|active_background|{"active_source":...|
|1593136280858|app| -55.0|V2.9.6|8.0.4|C6816QZ0@gmail.com|489| 3G| es|  4| 640*960| MX|489|1593123253541|  5.2|sumsung-18|1.3.4|Sumsung|  I|1593135644347|          comment|{"p_comment_id":1...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|1593063223807|          loading|{"extend2":"","lo...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|1593095105466|               ad|{"activityId":"1"...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|1593051718208|     notification|{"ap_time":"15930...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|1593100021275|          comment|{"p_comment_id":4...|
|1593136280858|app|-114.9|V2.7.8|8.0.4|NW0S962J@gmail.com|490| 3G| pt|  8|640*1136| MX|490|1593121224789|-44.4|  Huawei-8|1.0.1| Huawei|  O|1593105344120|           praise|{"target_id":9,"i...|
+-------------+---+------+------+-----+------------------+---+---+---+---+--------+---+---+-------------+-----+----------+-----+-------+---+-------------+-----------------+--------------------+

8.val loadingDF=jsonDF6.filter(jsonDF6("en")==="loading").select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"ett",$"en",get_json_object($"kv","$.extend2").alias("extend2"),get_json_object($"kv","$.loading_time").alias("loading_time"),get_json_object($"kv","$.action").alias("action"),get_json_object($"kv","$.extend1").alias("extend1"),get_json_object($"kv","$.type").alias("type"),get_json_object($"kv","$.type1").alias("type1"),get_json_object($"kv","$.loading_way").alias("loading_way"))

9.val adDF=jsonDF6.filter(jsonDF6("en")==="ad").select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"ett",$"en",get_json_object($"kv","$.activityId").alias("activityId"),get_json_object($"kv","$.displayMills").alias("displayMills"),get_json_object($"kv","$.entry").alias("entry"),get_json_object($"kv","$.action").alias("action"),get_json_object($"kv","$.contentType").alias("contentType"))

10.val notificationDF=jsonDF6.filter(jsonDF6("en")==="notification").select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"ett",$"en",get_json_object($"kv","$.ap_time").alias("ap_time"),get_json_object($"kv","$.action").alias("action"),get_json_object($"kv","$.type").alias("type"),get_json_object($"kv","$.content").alias("content"))

11.val active_backgroundDF=jsonDF6.filter(jsonDF6("en")==="active_background").select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"ett",$"en",get_json_object($"kv","$.active_source").alias("active_source"))

12.val commentDF=jsonDF6.filter(jsonDF6("en")==="comment").select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"ett",$"en",get_json_object($"kv","$.p_comment_id").alias("p_comment_id"),get_json_object($"kv","$.addtime").alias("addtime"),get_json_object($"kv","$.praise_count").alias("praise_count"),get_json_object($"kv","$.other_id").alias("other_id"),get_json_object($"kv","$.comment_id").alias("comment_id"),get_json_object($"kv","$.reply_count").alias("reply_count"),get_json_object($"kv","$.userid").alias("userid"),get_json_object($"kv","$.content").alias("content"))

13.val praiseDF=jsonDF6.filter(jsonDF6("en")==="praise").select($"id",$"ap",$"ln",$"sv",$"os",$"g",$"mid",$"nw",$"l",$"vc",$"hw",$"ar",$"uid",$"t",$"la",$"md",$"vn",$"ba",$"sr",$"ett",$"en",get_json_object($"kv","$.target_id").alias("target_id"),get_json_object($"kv","$.id").alias("id"),get_json_object($"kv","$.type").alias("type"),get_json_object($"kv","$.add_time").alias("add_time"),get_json_object($"kv","$.userid").alias("userid"))

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值