作业1_4

importurllib.request

frombs4importBeautifulSoup

importrequests

data=[]

url=['http://www.tara-china.cn/TARA_Gallery/TARA_Picture/2015/11/07/1947562240_{}.html'.format(str(i))foriinrange(2,19)]

url2=['http://www.tara-china.cn/TARA_Gallery/TARA_Wallpaper/2015/11/07/1902192236_{}.html'.format(str(i))foriinrange(2,8)]

url_base='http://www.tara-china.cn'

defdownload_t_ara(url):

wb_data=requests.get(url)

soup=BeautifulSoup(wb_data.text,'lxml')

images=soup.select(' p > img')

forimageinimages:

data.append(url_base+image.get('src'))

# count=0

forurl1inurl2:

download_t_ara(url1)

# count=count+1

# if count==3:

#    break

file_path='C:/Users/xilixjd/Desktop/Important file/python/爬虫/1/1_4/T-ara/'

file_path1='C:/Users/xilixjd/Desktop/Important file/python/爬虫/1/1_4/T-ara1/'

deffile_download(file_path,data):

count1=0

forimage_urlindata:

count1=count1+1

urllib.request.urlretrieve(image_url,file_path+str(count1)+'.jpg')

file_download(file_path1,data)

'''

image_url='http://www.tara-china.cn/UploadFiles/TARA_Gallery/2015/11/201511071943301109.jpg'

urllib.request.urlretrieve(image_url,'C:/Users/xilixjd/Desktop/Important file/python/爬虫/1/1_4/T-ara/1.jpg')

'''