代碼如下:

#-*-coding:UTF-8-*-

”’

Createdon2021-12-5

@author:good-temper

”’

importurllib2

importbs4

importtime

defgetPage(urlStr):

”’

獲取頁面內容

”’

content=urllib2.urlopen(urlStr).read()

returncontent

defgetNextPageUrl(currPageNum):

#頁碼-1-1-72-4137-33.html

url=u’‘+str(currPageNum+1)+’-1-1-72-4137-33.html’

#是否有下一頁

content=getPage(url);

soup=bs4.BeautifulSoup(content)

list=soup.findAll(‘span’,{‘class’:’next-disabled’});

if(len(list)==0):

returnurl

return”

defanalyzeList():

pageNum=0

list=[]

url=getNextPageUrl(pageNum)

whileurl!=”:

soup=bs4.BeautifulSoup(getPage(url))

pagelist=soup.findAll(‘div’,{‘class’:’p-name’})

foreleminpagelist:

soup1=bs4.BeautifulSoup(str(elem))

list.append(soup1.find(‘a’)[‘href’])

pageNum=pageNum+1

printpageNum

url=getNextPageUrl(pageNum)

returnlist

defanalyzeContent(url):

return”

defwriteToFile(list,path):

f=open(path,‘a’)

foreleminlist:

f.write(elem+’

’)

f.close()

if__name__==‘__main__’:

list=analyzeList()

print‘共抓取’+str(len(list))+’條

’

writeToFile(list,u’E:\\jd_phone_list.dat’);

轉載請注明：seo-網站優化-網站建設?python抓取京東商城手機列表url實例代碼