demo爬虫

叁歲伎倆 2024-04-18 18:06 56阅读 0赞

\#!/usr/bin/python  
\#指明编码  
\# -\*- coding: UTF-8 -\*-

\#导入python库  
import urllib  
import urllib2  
import re  
import MySQLdb  
import json

\#定义爬虫类  
class crawl1:  
def getHtml(self,url=None):  
\#代理  
user\_agent="Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.0"  
header=\{"User-Agent":user\_agent\}  
request=urllib2.Request(url,headers=header)  
response=urllib2.urlopen(request)  
html=response.read()  
return html

def getContent(self,html,reg):  
content=re.findall(html, reg, re.S)  
return content

\#连接数据库 mysql  
def connectDB(self):  
host="192.168.85.21"  
dbName="test1"  
user="root"  
password="123456"  
\#此处添加charset='utf8'是为了在数据库中显示中文，此编码必须与数据库的编码一致  
db=MySQLdb.connect(host,user,password,dbName,charset='utf8')  
return db  
cursorDB=db.cursor()  
return cursorDB

\#创建表，SQL语言。CREATE TABLE IF NOT EXISTS 表示：表createTableName不存在时就创建  
def creatTable(self,createTableName):  
createTableSql="CREATE TABLE IF NOT EXISTS "+ createTableName+"(time VARCHAR(40),title VARCHAR(100),text VARCHAR(40),clicks VARCHAR(10))"  
DB\_create=self.connectDB()  
cursor\_create=DB\_create.cursor()  
cursor\_create.execute(createTableSql)  
DB\_create.close()  
print 'creat table '+createTableName+' successfully'  
return createTableName

\#数据插入表中  
def inserttable(self,insertTable,insertTime,insertTitle,insertText,insertClicks):  
insertContentSql="INSERT INTO "+insertTable+"(time,title,text,clicks)VALUES(%s,%s,%s,%s)"  
\# insertContentSql="INSERT INTO "+insertTable+"(time,title,text,clicks)VALUES("+insertTime+" , "+insertTitle+" , "+insertText+" , "+insertClicks+")"

DB\_insert=self.connectDB()  
cursor\_insert=DB\_insert.cursor()  
cursor\_insert.execute(insertContentSql,(insertTime,insertTitle,insertText,insertClicks))  
DB\_insert.commit()  
DB\_insert.close()  
print 'inert contents to '+insertTable+' successfully'

url="http://baoliao.hb.qq.com/api/report/NewIndexReportsList/cityid/18/num/20/pageno/1?callback=jQuery183019859437816181613\_1440723895018&\_=1440723895472"

\#正则表达式，获取js，时间，标题，文本内容，点击量（浏览次数）  
reg\_jason=r'.\*?jQuery.\*?\\((.\*)\\)'  
reg\_time=r'.\*?"create\_time":"(.\*?)"'  
reg\_title=r'.\*?"title":"(.\*?)".\*?'  
reg\_text=r'.\*?"content":"(.\*?)".\*?'  
reg\_clicks=r'.\*?"counter\_clicks":"(.\*?)"'

\#实例化crawl()对象  
crawl=crawl1()  
html=crawl.getHtml(url)  
html\_jason=re.findall(reg\_jason, html, re.S)

html\_need=json.loads(html\_jason\[0\])

print len(html\_need)  
print len(html\_need\['data'\]\['list'\])

table=crawl.creatTable('yh1')  
for i in range(len(html\_need\['data'\]\['list'\])):  
creatTime=html\_need\['data'\]\['list'\]\[i\]\['create\_time'\]  
title=html\_need\['data'\]\['list'\]\[i\]\['title'\]  
content=html\_need\['data'\]\['list'\]\[i\]\['content'\]  
clicks=html\_need\['data'\]\['list'\]\[i\]\['counter\_clicks'\]  
crawl.inserttable(table,creatTime,title,content,clicks)