批量下载免费PPT模板【另一种智能翻页】

最新推荐文章于 2021-08-05 23:41:31 发布

JW☞♡Lee

最新推荐文章于 2021-08-05 23:41:31 发布

阅读量427

点赞数

分类专栏： python 爬虫文章标签： python

本文链接：https://blog.csdn.net/weixin_43422435/article/details/108202378

版权

python 爬虫专栏收录该内容

15 篇文章 0 订阅

订阅专栏

1.导入模块并判断所下载类型PPT是否存在文件夹，若无，新建

import requests
import os
from lxml import etree
path = "e:/中秋节ppt模板"
if not os.path.exists(path):
    os.mkdir(path)

2.访问基础页面，并且拿到总页数列表，确定该类型文件共有几页

b_url ="http://www.1ppt.com/moban/zhongqiujie/"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36'
}
response = requests.get(url= b_url, headers=headers)
response.encoding = 'gbk'    #更改解码方式
html = etree.HTML(response.text)
num = html.xpath('//ul[@class="pages"]//a/text()')[-3]

3.循环依次访问每页数据，并获取每个PPT的名称及下载链接

for i in range(1,int(num)+1):
    url = b_url + f"ppt_zhongqiujie_{i}.html"    
    response = requests.get(url= url, headers=headers)
    response.encoding = 'gbk'    #更改解码方式
    html = etree.HTML(response.text)
    ppt_name = html.xpath('//ul[@class="tplist"]//img/@alt')
    ppt_url = html.xpath('//ul[@class="tplist"]//h2/a/@href')
    ppt_url = ["http://www.1ppt.com"+i for i in ppt_url]
    dt = dict(zip(ppt_name, ppt_url))    
    for k, v in dt.items():
        res = requests.get(url =v,headers =headers)
        res.encoding = "gbk"
        html = etree.HTML(res.text)
        down_url = html.xpath('//ul[@class="downurllist"]//a/@href')[0]
        print(down_url)
        resp = requests.get(down_url).content

4.数据存储

 #数据存储
        houzhui = v.split(".")[-1]
        path = path + k + '.' + houzhui
        print(path)
        with open(path, "wb") as f:
            f.write(resp)
            print(k,"下载完成")

完整代码展示

import requests
import os
from lxml import etree
path = "e:/中秋节ppt模板"
if not os.path.exists(path):
    os.mkdir(path)
b_url ="http://www.1ppt.com/moban/zhongqiujie/"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36'
}
response = requests.get(url= b_url, headers=headers)
response.encoding = 'gbk'    #更改解码方式
html = etree.HTML(response.text)
num = html.xpath('//ul[@class="pages"]//a/text()')[-3]
for i in range(1,int(num)+1):
    url = b_url + f"ppt_zhongqiujie_{i}.html"    
    response = requests.get(url= url, headers=headers)
    response.encoding = 'gbk'    #更改解码方式
    html = etree.HTML(response.text)
    ppt_name = html.xpath('//ul[@class="tplist"]//img/@alt')
    ppt_url = html.xpath('//ul[@class="tplist"]//h2/a/@href')
    ppt_url = ["http://www.1ppt.com"+i for i in ppt_url]
    dt = dict(zip(ppt_name, ppt_url))    
    for k, v in dt.items():
        res = requests.get(url =v,headers =headers)
        res.encoding = "gbk"
        html = etree.HTML(res.text)
        down_url = html.xpath('//ul[@class="downurllist"]//a/@href')[0]
        print(down_url)
        resp = requests.get(down_url).content
        #数据存储
        houzhui = v.split(".")[-1]
        path = path + k + '.' + houzhui
        print(path)
        with open(path, "wb") as f:
            f.write(resp)
            print(k,"下载完成")