p15679402
/
bigdata
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

.

This commit is contained in:
guange 2019-01-18 10:24:34 +08:00
parent 411e14684f
commit ed358a8a59
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
chapter3/spark.py
View File

@ -53,7 +53,7 @@ def collect_crawl_info(spark):
def collect_news(spark): def collect_news(spark):
df = spark.sql("select * from jd_comment order by created_at desc limit 20") df = spark.sql("select * from jd_comment order by created_at desc limit 20")
for row in df.rdd.collect(): for row in df.rdd.collect():
mysql_execute("insert into news (comment_time, content, comment_id) values ('{}', '{}', '{}'')".format( mysql_execute("insert into news (comment_time, content, comment_id) values ('{}', '{}', '{}')".format(
row["comment_time"], row["content"], row["id"])) row["comment_time"], row["content"], row["id"]))