import requests
import re
import time
from redis import Redis
import threading
REDIS_HOST, REDIS_PORT, PASSWORD = '192.168.2.51', '6379', 'mypwd'
rds = Redis(host=REDIS_HOST, port=REDIS_PORT, password=PASSWORD)
f, url_l, filter_replace_l = 'kwaddress_address_20180227.json', [], ['
', ' ', ' ']
with open(f,'r',encoding='utf-8') as fr:
for i in fr:
try:
ii =i.split('address":"')[-1].split('"}')[0]
#url_l.append(ii)
rds.sadd('chk_url_all', ii)
except Exception as e:
print(e)
去内存,持久化
import pymysql
from redis import Redis
import time
h, pt, u, p, db = '192.168.2.210', 3306, 'root', 'nfwt&2016', 'xl_product_DONOT_REMOVE'
def mysql_fetch(sql, res_type='tuple'):
global h, pt, u, p, db
try:
conn = pymysql.connect(host=h, port=pt, user=u, passwd=p, db=db, charset='utf8')
except Exception as e:
print(e)
return ()
if res_type == 'dic':
cursor = conn.cursor(pymysql.cursors.DictCursor)
else:
cursor = conn.cursor()
cursor.execute(sql)
conn.commit()
cursor.close()
conn.close()
return cursor.fetchall()
def mysql_write(sql):
global h, pt, u, p, db
try:
conn = pymysql.connect(host=h, port=pt, user=u, passwd=p, db=db, charset='utf8')
except Exception as e:
print(e)
return 1
cursor = conn.cursor()
cursor.execute(sql)
conn.commit()
cursor.close()
conn.close()
return 0
REDIS_HOST, REDIS_PORT, PASSWORD = '192.168.2.51', '6379', 'mypwd'
rds = Redis(host=REDIS_HOST, port=REDIS_PORT, password=PASSWORD)
while True:
s_404 = [i.decode('utf-8') for i in rds.smembers('chk_url_404')]
for i in s_404:
sql = 'SELECT id FROM chk_url_404 WHERE url="{}" '.format(i)
try:
r = mysql_fetch(sql)
print(sql)
except Exception as e:
print(e)
continue
if len(r) == 0:
sql = 'INSERT INTO chk_url_404 (url,indb_time) VALUES ("{}","{}")'.format(i, int(time.time()))
try:
mysql_write(sql)
print(sql)
except Exception as e:
print(e)
continue
time.sleep(60 * 15)
多线程
import requests
import re
import time
from redis import Redis
import threading
REDIS_HOST, REDIS_PORT, PASSWORD = '192.168.2.51', '6379', 'mypwd'
rds = Redis(host=REDIS_HOST, port=REDIS_PORT, password=PASSWORD)
# f, url_l, filter_replace_l = 'DISTINCT_url.txt', [], ['
', ' ', ' ']
# with open(f, 'r', encoding='utf-8') as fr:
# for i in fr:
# try:
# for ii in filter_replace_l:
# i = i.replace(ii, '')
# rds.sadd('chk_url_all', i)
# except Exception as e:
# print(e)
def tf():
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'}
while True:
try:
url_ori = rds.spop('chk_url_all').decode('utf-8')
s = 'http://'
if s not in url_ori:
url = '{}{}'.format(s, url_ori)
print(url)
r = requests.get(url, headers=headers, timeout=50)
print(r.status_code)
sc = r.status_code
if sc == 404:
print(sc)
rds.sadd('chk_url_404', url_ori)
except Exception as e:
print(e)
class MyThread(threading.Thread):
def __init__(self, func, args=None, name=None):
threading.Thread.__init__(self)
self.func, self.args, self.name = func, args, name
def run(self):
if self.args==None:
self.func()
else:
self.func(self.args)
tl = []
for i in range(10):
thread_instance = MyThread(tf)
tl.append(thread_instance)
for t in tl:
t.setDaemon = False
t.start()
for t in tl:
t.join()
发布代码至多台机器
redis 自典型 支持更新
rds = return_redis(redis_key)
rds.hset(my_dict_name, uid, uid_info)