Autorefresh of live.html, changed file name in server to solve caching issues

Author: luisbelloch

spark/_template_rdd

@@ -7,5 +7,5 @@ no_header = txt.filter(lambda s: not s.startswith(item_fields[0]))
 parsed = no_header.map(lambda s: parse_item(s)).cache()
 
 print(parsed.take(1))
-print(parsed.toDebugString())
+print(parsed.toDebugString().decode('utf-8'))
 

spark/hello1.py

@@ -6,5 +6,5 @@
 print(rdd.count())
 
 # Also spark-submit hello1.py --conf spark.logLineage=true
-print(rdd.toDebugString())
+print(rdd.toDebugString().decode('utf-8'))
 

spark/hello2.py

@@ -5,7 +5,7 @@
 
 solo_en_euros = rdd.filter(lambda fila: 'EUR' in fila)
 
-print(solo_en_euros.toDebugString())
+print(solo_en_euros.toDebugString().decode('utf-8'))
 print(solo_en_euros.count())
 print(solo_en_euros.take(10))
 

spark/live/live.sh

@@ -5,7 +5,8 @@ fswatch ../live.py | while read -r fpath; do \
     echo -e "\033[0;36mRELOAD\033[0m $fpath $(date +"%H%M%S")"
     echo -e "# $(date +"%H:%M:%S")\n" | cat - ../live.py > live_mod.py
     sed -e '/-python">/r./live_mod.py' live_template.html > live.html
-    gsutil cp live.html gs://bigdata.luisbelloch.es/live.html
+    gsutil -h "Cache-Control:no-cache,max-age=0" \
+        cp live.html gs://bigdata.luisbelloch.es/en_directo.html
 
     # echo -e "# $(date +"%H:%M:%S")\n" | cat - live.py | pygmentize -f html -O full,linenos=1 -o live.html
     # scp live.html [email protected]:/var/www/html/index.html

spark/live/live_template.html

@@ -4,6 +4,7 @@
     <meta charset="UTF-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <meta http-equiv="X-UA-Compatible" content="ie=edge" />
+    <meta http-equiv="Refresh" content="5">
     <title>#bidataupv - live</title>
     <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Fira+Mono:400,500,700|Roboto:300,400,500,700,900" />
     <link rel="stylesheet" href="http://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.14.2/styles/dracula.min.css" />