今天没事用BeautifulSoup写了一个爬取淘宝页面的部分图片的代码,之前用正则也写了一个,感觉用BeautifulSoup 更简单了
import urllib
import urllib.request as request
from bs4 import BeautifulSoup
def taobao(url):
response = request.urlopen(url)
html = response.read()
#我是win7系统,默认是gdk要先解码,再用utf8编码就可以显示汉字了
data = html.decode('gbk').encode('utf-8')
soup = BeautifulSoup(data)
path = 'f:/image/'
count = 1
for list in soup.find_all('img'):
#拆分属性
dict = list.attrs
if "data-lazy" in dict:
image = dict['data-lazy']
img = image[image.rfind('.')::]
filepath = path + str(count)+img
with open(filepath, 'wb') as file:
image_data = request.urlopen(dict['data-lazy']).read()
print(dict['data-lazy'])
file.write(image_data)
count += 1
file.close()
if __name__ == '__main__':
print("""
+++++++++++++++++++++++
学校:超神学院
专业:德玛班
姓名:德玛之力
version: python3.2
+++++++++++++++++=++++
""")
url = 'http://www.taobao.com/?spm=a310q.2219005.1581860521.1.b9kUd4'
taobao(url)
+++++++++++++++++++++++
学校:超神学院
专业:德玛班
姓名:德玛之力
version: python3.2
+++++++++++++++++=++++
http://gtms01.alicdn.com/tps/i1/T1RC0qFF4bXXcMypPC-260-125.png
http://gtms02.alicdn.com/tps/i2/T1HZFrFGVbXXcMypPC-260-125.png
http://gtms04.alicdn.com/tps/i4/T1WZNrFPVbXXanhZrl-250-125.jpg
http://gtms03.alicdn.com/tps/i3/T1p10nFUFdXXc2jIrl-250-125.png
http://gtms04.alicdn.com/tps/i4/T1GczVFwpXXXc2jIrl-250-125.png
http://gtms04.alicdn.com/tps/i4/T1w.RnFMtbXXc2jIrl-250-125.png
http://gtms03.alicdn.com/tps/i3/T1KN8oFJVdXXc2jIrl-250-125.png
http://gtms01.alicdn.com/tps/i1/T1oyxnFMFdXXc2jIrl-250-125.png
http://gtms03.alicdn.com/tps/i3/T1g2toFG0dXXc2jIrl-250-125.png
http://gtms04.alicdn.com/tps/i4/T1DNlrFMXaXXc2jIrl-250-125.png
http://gtms02.alicdn.com/tps/i2/T1vBFrFGxaXXanhZrl-250-125.jpg
http://gtms02.alicdn.com/tps/i2/T1.gBoFLxdXXanhZrl-250-125.jpg
http://gtms03.alicdn.com/tps/i3/T1Q9NqFNlaXXc2jIrl-250-125.png
http://gtms04.alicdn.com/tps/i4/T1HblpFStcXXc2jIrl-250-125.png
http://gtms01.alicdn.com/tps/i1/T1wbxoFN8dXXc2jIrl-250-125.png
http://gtms01.alicdn.com/tps/i1/T1OXFnFQ8cXXc2jIrl-250-125.png
http://img.taobaocdn.com/bao/uploaded/T1eYDyFfdbXXb1upjX.jpg
http://img.taobaocdn.com/bao/uploaded/T1q0eDFd4eXXb1upjX.jpg
http://img04.taobaocdn.com/bao/uploaded/i4/T1oa.kXa8hXXXQXDnq-90-45.png
http://img02.taobaocdn.com/bao/uploaded/i2/T1ouQYXltbXXXQXDnq-90-45.png
http://img.taobaocdn.com/bao/uploaded/T1o2aWFc4dXXb1upjX.jpg
http://img02.taobaocdn.com/bao/uploaded/i2/T1deC.XhhvXXXQXDnq-90-45.png
http://img04.taobaocdn.com/bao/uploaded/i4/T1vtUYXbxbXXXQXDnq-90-45.png
http://img02.taobaocdn.com/bao/uploaded/i2/T1KsYVXndXXXXQXDnq-90-45.png
http://img03.taobaocdn.com/bao/uploaded/i3/T1utqAXdBUXXXXXXXX-90-45.jpg
http://img01.taobaocdn.com/bao/uploaded/i1/T1VezWXaBeXXXQXDnq-90-45.png
http://img01.taobaocdn.com/bao/uploaded/i1/T19KfUXkheXXXQXDnq-90-45.png
http://img02.taobaocdn.com/bao/uploaded/i2/T1UOmoXd8rXXXXXXXX-90-45.jpg
http://img.taobaocdn.com/bao/uploaded/T1Z86AFXlbXXb1upjX.jpg
http://img01.taobaocdn.com/bao/uploaded/i1/T1_5.YXa0bXXXQXDnq-90-45.png
http://img04.taobaocdn.com/bao/uploaded/i4/T1PgeoXmJOXXXXXXXX-90-45.jpg
测试通过