|
|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
from bs4 import BeautifulSoup
import requests,os
def get_img(path,url,name):
h = requests.get(url)
name = '{0}.jpg'.format(name)
img = os.path.join(path,name)
f = open(img,'wb')
f.write(h.content)
f.close()
for key in range(1,14):
url = 'http://www.1ppt.com/xiazai/ppt_xiazai_{0}.html'.format(key)
html = requests.get(url)
html.encoding = 'gbk'
soup = BeautifulSoup(html.text)
for i in soup.body.find('ul',class_="tplist").findAll('li'):
name = i.find('img')['alt']
listR = []
for j in i.span.strings:
listR.append(j)
types = listR[0]
num=listR[-1]
print([key,name,types,int(num.strip(':').strip('次'))])
print([key,name,types,int(num.strip(':').strip('次'))])
这里最后两行,为什么第一个print会报错,第二个不会? |
|