本文實例講述了Python3實現的爬蟲爬取數據并存入mysql數據庫操作。分享給大家供大家參考，具體如下：

爬一個電腦客戶端的訂單。羅總推薦，抓包工具用的是HttpAnalyzerStdV7，與chrome自帶的F12類似。客戶端有接單大廳，羅列所有訂單的簡要信息。當單子被接了，就不存在了。我要做的是新出訂單就爬取記錄到我的數據庫zyc里。

設置每10s爬一次。

抓包工具頁面如圖：

首先是爬蟲，先找到數據存儲的頁面，再用正則爬出。

# -*- coding:utf-8 -*-

import re

import requests

import pymysql #Python3的mysql模塊，Python2 是mysqldb

import datetime

import time

def GetResults():

requests.adapters.DEFAULT_RETRIES = 5 #有時候報錯，我在網上找的不知道啥意思，好像也沒用。

reg = [r'"id":(.*?),',

r'"order_no":"(.*?)",',

r'"order_title":"(.*?)",',

r'"publish_desc":"(.*?)",',

r'"game_area":"(.*?)\\/(.*?)\\/(.*?)",',

r'"order_current":"(.*?)",',

r'"order_content":"(.*?)",',

r'"order_hours":(.*?),',

r'"order_price":"(.*?)",',

r'"add_price":"(.*?)",',

r'"safe_money":"(.*?)",',

r'"speed_money":"(.*?)",',

r'"order_status_desc":"(.*?)",',

r'"order_lock_desc":"(.*?)",',

r'"cancel_type_desc":"(.*?)",',

r'"kf_status_desc":"(.*?)",',

r'"is_show_pwd":(.*?),',

r'"game_pwd":"(.*?)",',

r'"game_account":"(.*?)",',

r'"game_actor":"(.*?)",',

r'"left_hours":"(.*?)",',

r'"created_at":"(.*?)",',

r'"account_id":"(.*?)",',

r'"mobile":"(.*?)",',

r'"contact":"(.*?)",',

r'"qq":"(.*?)"},']

results=[]

try:

for l in range(1,2): #頁碼

proxy = {'HTTP':'61.135.155.82:443'} #代理ip

html = requests.get('https://www.dianjingbaozi.com/api/dailian/soldier/hall?access_token=3ef3abbea1f6cf16b2420eb962cf1c9a&dan_end=&dan_start=&game_id=2&kw=&order=price_desc&page=%d'%l+'&pagesize=30&price_end=0&price_start=0&server_code=000200000000&sign=ca19072ea0acb55a2ed2486d6ff6c5256c7a0773&timestamp=1511235791&type=public&type_id=%20HTTP/1.1',proxies=proxy) # 用get的方式訪問。網頁解碼成中文。接單大廳頁。

#

html=html.content.decode('utf-8')

outcome_reg_order_no = re.findall(r'"order_no":"(.*?)","game_area"', html) #獲取訂單編號，因為訂單詳情頁url與訂單編號有關。

for j in range(len(outcome_reg_order_no)):

html_order = requests.get('http://www.lpergame.com/api/dailian/order/detail?access_token=eb547a14bad97e1ee5d835b32cb83ff1&order_no=' +outcome_reg_order_no[j] + '&sign=c9b503c0e4e8786c2945dc0dca0fabfa1ca4a870&timestamp=1511146154 HTTP/1.1',proxies=proxy) #訂單詳細頁

html_order=html_order.content.decode('utf-8')

# print(html_order)

outcome_reg = []

for i in range(len(reg)):#每條訂單

outcome = re.findall(reg[i], html_order)

if i == 4:

for k in range(len(outcome)):

outcome_reg.extend(outcome[k])

else:

outcome_reg.extend(outcome)

results.append(outcome_reg) #結果集

return results

except:

time.sleep(5) #有時太頻繁會報錯。

print("失敗")

pass

根據爬蟲結果建表，這里變量名要準確。并且要設置唯一索引，使每次爬的只有新訂單入庫。

def mysql_create():

mysql_host = ''

mysql_db = 'zyc'

mysql_user = 'zyc'

mysql_password = ''

mysql_port = 3306

db = pymysql.connect(host=mysql_host, port=mysql_port, user=mysql_user, password=mysql_password, db=mysql_db,charset='utf8') # 連接數據庫編碼注意是utf8，不然中文結果輸出會亂碼

sql_create = "CREATE TABLE DUMPLINGS (id CHAR(10),order_no CHAR(50),order_title VARCHAR(265),publish_desc VARCHAR(265),game_name VARCHAR(265),"\

"game_area VARCHAR(265),game_area_distinct VARCHAR(265),order_current VARCHAR(3908),order_content VARCHAR(3908),order_hours CHAR(10)," \

"order_price FLOAT(10),add_price FLOAT(10),safe_money FLOAT(10),speed_money FLOAT(10),order_status_desc VARCHAR(265),"\

"order_lock_desc VARCHAR(265),cancel_type_desc VARCHAR(265),kf_status_desc VARCHAR(265),is_show_pwd TINYINT,game_pwd CHAR(50),"\

"game_account VARCHAR(265),game_actor VARCHAR(265),left_hours VARCHAR(265),created_at VARCHAR(265),account_id CHAR(50),"\

"mobile VARCHAR(265),mobile2 VARCHAR(265),contact VARCHAR(265),contact2 VARCHAR(265),qq VARCHAR(265),"\

"PRIMARY KEY (`id`),UNIQUE KEY `no`(`order_no`))ENGINE=InnoDB AUTO_INCREMENT=12 DEFAULT CHARSET=utf8"

sql_key="CREATE UNIQUE INDEX id ON DUMPLINGS(id)"

cursor = db.cursor()

cursor.execute("DROP TABLE IF EXISTS DUMPLINGS")

cursor.execute(sql_create)# 執行SQL語句

cursor.execute(sql_key)

db.close() # 關閉數據庫連

把數據導入Mysql，注意編碼和字段之間的匹配。

def IntoMysql(results):

mysql_host = ''

mysql_db = 'zyc'

mysql_user = 'zyc'

mysql_password = ''

mysql_port = 3306

db = pymysql.connect(host=mysql_host, port=mysql_port, user=mysql_user, password=mysql_password, db=mysql_db,charset='utf8') # 連接數據庫編碼注意是utf8，不然中文結果輸出會亂碼

cursor = db.cursor()

for j in range(len(results)):

try:

sql = "INSERT INTO DUMPLINGS(id,order_no,order_title,publish_desc ,game_name," \

"game_area,game_area_distinct,order_current,order_content,order_hours," \

"order_price,add_price,safe_money,speed_money,order_status_desc," \

"order_lock_desc,cancel_type_desc,kf_status_desc,is_show_pwd,game_pwd," \

"game_account,game_actor,left_hours,created_at,account_id," \

"mobile,mobile2,contact,contact2,qq) VALUES ("

for i in range(len(results[j])):

sql = sql + "'" + results[j][i] + "',"

sql = sql[:-1] + ")"

sql = sql.encode('utf-8')

cursor.execute(sql)

db.commit()

except:pass

db.close()

每十秒運行一次。

mysql_create()

i=0

while True:

results = GetResults()

IntoMysql(results)

i=i+1

print("爬蟲次數:",i)

time.sleep(10)

結果如圖：

希望本文所述對大家Python程序設計有所幫助。