[python] 使用urllib从页面上采集信息示例

#!/usr/bin/env python
# -*- coding:utf-8 -*-
'''
从URL中采集所需信息，这边是用于采集hbase集群管理页面每秒请求数和region数量
'''
import re
import urllib.request
pagehandler = urllib.request.urlopen("http://127.0.0.1:60010/master-status?filter=general#baseStats")
content = pagehandler.read().decode()
result=re.findall('.*Total(.*?)Used Heap.*',content,re.S) ####(.*?)表示除换行外的所有字符，非贪婪模式，re.S使 . 匹配包括换行在内的所有字符
msg = re.findall(r'<td>(\d+)</td>',result[0])    ####取出数值，HBASE集群每秒请求数和region数量。注意，这边取出后为字符串
print(msg)

#!/usr/bin/env python
# -*- coding:utf-8 -*-
'''
kafka管理页面上，lag列为消息堵塞数量，无法直接从URL返回的信息中采集该值，需要由logSize-offset计算得出
'''
import json
import urllib.request
pagehandler = urllib.request.urlopen("http://127.0.0.1:8086/group/test_group")
content = pagehandler.read().decode()
m = json.loads(content)
topic_dict = {}
for i in m['offsets']:
blocking_num = 0
#print(i['topic'],i['offset'],i['logSize'])
blocking_num +=  (i['logSize'] - i['offset'])	   ####计算队列堵塞量
if i['topic'] in topic_dict:			   ####将结果按topic_name:blocking_num存放在字典里
topic_dict[i['topic']] += blocking_num
else:
topic_dict[i['topic']] = blocking_num

#print(topic_dict)
for key in topic_dict:
if topic_dict[key] > 3000:
print("topic:",key,",blocking msg num:",topic_dict[key])