china-pub

#!/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(method):
    for page in range(1,5+1):  
        url1="http://product.china-pub.com/cache/rank3/newbook/%s_%s.html"%(method,page)
        print "\n##################:",url1
        httpCrawler(url1,page,method)

def httpCrawler(url,page,method):
    content = httpRequest(url)
    #<tr logr='j_2_27359935228167_20019655228034_3'>
    List=re.findall(r'<td height="17" style="overflow: hidden;" colspan="5">(.*?)<a href="(.*?)" target="_blank">(.*?)</a>',content,re.S)
    no=len(List)
    print no
    method1=method.replace("\/","")
    for i in range(0,no):#0 ~ no-1
    url=List[i][1]
    name=List[i][2]
    name1=name.replace("/","").replace(u"+微信营销与运营：策略、方法、技巧与实践+微信营销解密:移动互联网时代的营销革命","")
    print "\ndownload one page:",List[i][1],"\n",List[i][2]
    if not os.path.exists('./%s'%method1):
        os.mkdir(r'./%s'%method1)
    content = httpRequest(url)
#    if (page-1)*20+i+1 != 82:
        open(u'%s/%s.%s'%(method1,(page-1)*20+i+1,name1+'.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()

array=(
'day\/rank_day_7_51',
'day\/rank_day_30_51',
'day\/rank_day_90_51',
'month\/rank_month_7_51',
'month\/rank_month_6_51',
'month\/rank_month_5_51',
'month\/rank_month_4_51',
'month\/rank_month_3_51',
'month\/rank_month_2_51',
'month\/rank_month_1_51',
'day\/rank_day_7_02',
'day\/rank_day_30_02',
'day\/rank_day_90_02',
'month\/rank_month_7_02',
'month\/rank_month_6_02',
'month\/rank_month_5_02',
'month\/rank_month_4_02',
'month\/rank_month_3_02',
'month\/rank_month_2_02',
'month\/rank_month_1_02',
'day\/rank_day_7_31',
'day\/rank_day_30_31',
'day\/rank_day_90_31',
'month\/rank_month_7_31',
'month\/rank_month_6_31',
'month\/rank_month_5_31',
'month\/rank_month_4_31',
'month\/rank_month_3_31',
'month\/rank_month_2_31',
'month\/rank_month_1_31',
'day\/rank_day_7_57',
'day\/rank_day_30_57',
'day\/rank_day_90_57',
'month\/rank_month_7_57',
'month\/rank_month_6_57',
'month\/rank_month_5_57',
'month\/rank_month_4_57',
'month\/rank_month_3_57',
'month\/rank_month_2_57',
'month\/rank_month_1_57',
'day\/rank_day_7_47',
'day\/rank_day_30_47',
'day\/rank_day_90_47',
'month\/rank_month_7_47',
'month\/rank_month_6_47',
'month\/rank_month_5_47',
'month\/rank_month_4_47',
'month\/rank_month_3_47',
'month\/rank_month_2_47',
'month\/rank_month_1_47',
'day\/rank_day_7_46',
'day\/rank_day_30_46',
'day\/rank_day_90_46',
'month\/rank_month_7_46',
'month\/rank_month_6_46',
'month\/rank_month_5_46',
'month\/rank_month_4_46',
'month\/rank_month_3_46',
'month\/rank_month_2_46',
'month\/rank_month_1_46',
'day\/rank_day_7_60',
'day\/rank_day_30_60',
'day\/rank_day_90_60',
'month\/rank_month_7_60',
'month\/rank_month_6_60',
'month\/rank_month_5_60',
'month\/rank_month_4_60',
'month\/rank_month_3_60',
'month\/rank_month_2_60',
'month\/rank_month_1_60',
'day\/rank_day_7_52',
'day\/rank_day_30_52',
'day\/rank_day_90_52',
'month\/rank_month_7_52',
'month\/rank_month_6_52',
'month\/rank_month_5_52',
'month\/rank_month_4_52',
'month\/rank_month_3_52',
'month\/rank_month_2_52',
'month\/rank_month_1_52',
'day\/rank_day_7_59',
'day\/rank_day_30_59',
'day\/rank_day_90_59',
'month\/rank_month_7_59',
'month\/rank_month_6_59',
'month\/rank_month_5_59',
'month\/rank_month_4_59',
'month\/rank_month_3_59',
'month\/rank_month_2_59',
'month\/rank_month_1_59'
'day\/rank_day_7_28',
'day\/rank_day_30_28',
'day\/rank_day_90_28',
'month\/rank_month_7_28',
'month\/rank_month_6_28',
'month\/rank_month_5_28',
'month\/rank_month_4_28',
'month\/rank_month_3_28',
'month\/rank_month_2_28',
'month\/rank_month_1_28',
)

if __name__ == '__main__':
    #writeHeader(fileHeader,colums)
    print len(array)
    for i in range(0,len(array)):
        getCompany(array[i])