jd.py

#!/usr/bin/env python
#coding:utf-8
import urllib2,re,sys,os,types
#from bs4 import BeautifulSoup                 

reload(sys);
sys.setdefaultencoding('gbk');              

province="上海"
city="上海"
fileHeader='\xEF\xBB\xBF'
colums='省直辖市^城市^行政区^商圈^名称^地址^联系人^联系电话^URL^公司介绍^'

def getCompany():
    for page in range(1,5+1):
        url1="http://book.jd.com/booktop-4-6929-%s.html"%(page)
        print "\n##################:",url1
        httpCrawler(url1,page) 

def httpCrawler(url,page):
    content = httpRequest(url)
    #<tr logr='j_2_27359935228167_20019655228034_3'>
    List=re.findall(r'<dt class=\'p-name\'>(.*?)<a href=\'(.*?)\' title="(.*?)" target=\'_blank\'',content,re.S)
    no=len(List)
    print no
    for i in range(0,no):#0 ~ no-1
    url=List[i][1]
    name=List[i][2]
    print "\ndownload one page:",List[i][1],"\n",List[i][2]
    if not os.path.exists('./jd'):
        os.mkdir(r'./jd')
    content = httpRequest(url)
#    if (page-1)*20+i+1 != 82:
        open(u'jd/%s.%s'%((page-1)*20+i+1,List[i][2].replace("/",""))+'.html','w+').write(content)
    print "ok"

def httpRequest(url):
    #try:
    html = None
    req_header = {
        'User-Agent':'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Firefox/38.0',
        'Accept':'text/html;q=0.9,*/*;q=0.8',
        #'Accept-Language':'en-US,en;q=0.5',
        #'Accept-Encoding':'gzip',
        #'Host':'j3.s2.dpfile.com',
        #'Connection':'keep-alive'
        #'Referer':'http://www.baidu.com'
    }
    req_timeout = 15
    req = urllib2.Request(url,None,req_header)
    resp = urllib2.urlopen(req,None,req_timeout)
    html = resp.read()#.decode('gbk').encode('gbk')
    print "resp:",resp
    #print html
    #finally:
    #    if resp:
    #        resp.close()
    return html

def writeHeader(fileheader,colums):
    if not os.path.exists('./58'):
        os.mkdir(r'./58')
    f = open('./58/daikuan.csv', 'w')
    f.write(fileheader)
    f.write(colums)
    #f.write('\r\n')
    f.close()

if __name__ == '__main__':
    #writeHeader(fileHeader,colums)
    getCompany()