批量下载PPT模板
我自己写的代码，还可以精简很多代码，目前还没有翻页的效果import os
from lxml import etree
import requests
if not os.path.exists('d:/ppt1'):
os.mkdir('d:/ppt1')
url = 'http://www.1ppt.com/moban/jianjie/'
ua = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36'}
respon = requests.get(url= url,headers= ua)
respon.encoding = 'gb2312'
jiexi = etree.HTML(respon.text)
lianjie = jiexi.xpath('//ul[@class="tplist"]/li/a/@href')
listlianjie = []
for i in lianjie:
lianjie = 'http://www.1ppt.com' + i
listlianjie.append(lianjie)
name = jiexi.xpath('//ul[@class="tplist"]/li/a/img/@alt')
#print(name)
dwonlist = []
for url in listlianjie:
respon = requests.get(url=url,headers=ua).text
jiexi = etree.HTML(respon)
downurl = jiexi.xpath('//ul[@class="downurllist"]/li/a/@href')
downurl = ['http://www.1ppt.com' + downurl for downurl in downurl]
#print(downurl)
respon = requests.get(url=downurl,headers=ua).text
jiexi = etree.HTML(respon)
downurl1 = jiexi.xpath('//li[@class="c1"]/a/@href')
for i in downurl1:
dwonlist.append(i)
#print(dwonlist)
zidian = dict(zip(name,dwonlist))
for name,dwonlist in zidian.items():
houzhui = dwonlist.split('.')[-1]
add = 'd:/ppt1/' + name +'.'+houzhui
respon = requests.get(url=dwonlist,headers = ua).content
with open(add,'wb') as a:
a.write(respon)
print(name,'下载完成')
页:
[1]