mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-12-12 09:22:05 +00:00
1.2 KiB
1.2 KiB
维基访问数据
参考: http://dumps.wikimedia.org/other/pagecounts-raw/
创建表结构:
CREATE TABLE wikistat
(
date Date,
time DateTime,
project String,
subproject String,
path String,
hits UInt64,
size UInt64
) ENGINE = MergeTree(date, (path, time), 8192);
加载数据:
for i in {2007..2016}; do for j in {01..12}; do echo $i-$j >&2; curl -sSL "http://dumps.wikimedia.org/other/pagecounts-raw/$i/$i-$j/" | grep -oE 'pagecounts-[0-9]+-[0-9]+\.gz'; done; done | sort | uniq | tee links.txt
cat links.txt | while read link; do wget http://dumps.wikimedia.org/other/pagecounts-raw/$(echo $link | sed -r 's/pagecounts-([0-9]{4})([0-9]{2})[0-9]{2}-[0-9]+\.gz/\1/')/$(echo $link | sed -r 's/pagecounts-([0-9]{4})([0-9]{2})[0-9]{2}-[0-9]+\.gz/\1-\2/')/$link; done
ls -1 /opt/wikistat/ | grep gz | while read i; do echo $i; gzip -cd /opt/wikistat/$i | ./wikistat-loader --time="$(echo -n $i | sed -r 's/pagecounts-([0-9]{4})([0-9]{2})([0-9]{2})-([0-9]{2})([0-9]{2})([0-9]{2})\.gz/\1-\2-\3 \4-00-00/')" | clickhouse-client --query="INSERT INTO wikistat FORMAT TabSeparated"; done