Commit 45f8df90 authored by huangiyu's avatar huangiyu

1

parent 4a77589c
......@@ -42,7 +42,7 @@ def remove_html_tags(text):
url_data = mysql_zdzs_proxy(
"SELECT id,url,mallId FROM DMP_SEARCH_SPIDER WHERE ID NOT IN (SELECT ID FROM DMP_SEARCH_DATA) and mallId = 'DS-JD' and project_id = '110' and (id like '%0' or id like '%1' or id like '%2' or id like '%3' ) limit 10000"))
"SELECT id,url,mallId FROM DMP_SEARCH_SPIDER WHERE ID NOT IN (SELECT ID FROM DMP_SEARCH_DATA) and mallId = 'DS-JD' and project_id = '110' and (id like '%0' or id like '%1' or id like '%2' or id like '%3' ) limit 10000")
for row in url_data:
url = row['url']
keyword = url.replace('https://search.jd.com/search?keyword=', "").replace('&enc=utf-8', "")
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment