本週須要將爬蟲爬下來的數據入庫,由於以前已經寫好PHP的接口的,能夠直接經過python調用PHP接口來實現,因此把方法總結一下。python
//python編碼問題,由於很久用,因此很容易出現laravel
# -*- coding: utf8 -*-
#!/usr/bin/pythonsql
import sys
reload(sys)
sys.setdefaultencoding('utf8') 數據庫
//python 鏈接數據庫json
import MySQLdbide
conn = MySQLdb.connect(
host = "localhost",
port = 22,
user = "root",
passwd = "root",
db = "test",
charset = "utf8")函數
cur = conn.cursor()
sql = 'select title,url,publish_time from mp_articles'
cur.execute(sql)
info = cur.fetchall()fetch
cur.close()
conn.commit()
conn.close()編碼
//python 調用RESTFul 接口url
test_data = {'title':title,'srcUrl':srcUrl,'composeTime':composeTime} #參數,以此種字典形式呈現
test_data_urlencode = urllib.urlencode(test_data) #須要注意的是編碼問題,經過urllib.urlencode()對將要傳入的函數進行編碼
requrl = 'http://47.90.20.84/addArticleFromSpider' #這是傳入的URL,相似laravel5中的route,須要在laravel 的controller中設置route
req = urllib2.Request(url = requrl,data =test_data_urlencode) 經過Request的方式入數據,好像是默認根據PHP中採用的POST/GET 等方式傳入數據
res_data = urllib2.urlopen(req) #對返回的數據進行解析
res = res_data.read() #讀取返回的數據
//try...except 當返回的參數有異常是,爲了避免中斷程序的運行,須要用此方式來保證程序運行
try:
test_data = {'title':title,'srcUrl':srcUrl,'composeTime':composeTime}
test_data_urlencode = urllib.urlencode(test_data)
requrl = 'http://47.90.20.84/addArticleFromSpider'
req = urllib2.Request(url = requrl,data =test_data_urlencode)
res_data = urllib2.urlopen(req)
res = res_data.read()
print "addArticleFromSpider():" + res
except urllib2.HTTPError:
print "there is an error"
pass #跳過錯誤,不進行處理,直接繼續執行
完整代碼以下:
# -*- coding: <utf8> -*- #!/usr/bin/python import MySQLdb import datetime import time import urllib import urllib2 import json import sys reload(sys) sys.setdefaultencoding('utf8') conn = MySQLdb.connect( host = "localhost", port = 22, user = "", passwd = "", db = "", charset = "utf8") cur = conn.cursor() sql = 'select title,url,publish_time from mp_articles' cur.execute(sql) info = cur.fetchall() #print len(info) for row in info: #print len(row) title = row[0] srcUrl = row[1] publish_Time = row[2] composeTime = time.mktime(publish_Time.timetuple()) composeTime = str(composeTime) try: test_data = {'title':title,'srcUrl':srcUrl,'composeTime':composeTime} test_data_urlencode = urllib.urlencode(test_data) requrl = 'http://47.90.20.84/addArticleFromSpider' req = urllib2.Request(url = requrl,data =test_data_urlencode) res_data = urllib2.urlopen(req) res = res_data.read() print "addArticleFromSpider():" + res except urllib2.HTTPError: print "there is an error" pass cur.close() conn.commit() conn.close()