Python下载中国数据库大会（DTCC2024）PPT全集

话不多说，上代码

encoding: utf-8

from bs4 import BeautifulSoup

import requests

from urllib.request import urlopen

import re

import json

def visit(url):

headers = {

“User-Agent”: “Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)”,

“accept”: “application/json, text/javascript, /; q=0.01”,

“accept-encoding”: “gzip, deflate, br”,

“accept-language”: “zh-CN,zh;q=0.9”,

“content-type”: “application/x-www-form-urlencoded; charset=UTF-8”,

“cookie”: “”, – 填自己的

“referer”: “”,

“sec-fetch-dest”: “document”,

“sec-fetch-mode”: “navigate”,

“sec-fetch-site”: “same-origin”,

}

res = requests.get(url,headers=headers)

bsObj = BeautifulSoup(res.text, “html.parser”)

return bsObj

def visit_homepage(url):

bsObj = visit(url)

content = bsObj.find(‘div’, class_=“content”)

content_list = content.select(“p”)

category = []

for i in range(4,len(content_list)):

try:

urls = content_list[i].a[‘href’]

name = content_list[i].get_text(“|”).split(“|”)[0].replace(’ ‘,’‘).replace(’\xa0’,‘’)

category.append([name,urls])

except:

pass

print(category)

return category

def download_pdf(conf,path):

category_name = conf[0]

category_url = conf[1]

bsObj = visit(category_url)

res = re.search(r’(.)token:(.?),',str(bsObj) ,re.M|re.I)

token = res.group(2).replace(‘"’,‘’).replace(’ ‘,’')

arts = re.findall(r’(.)li data-docinfo=(.?)}',str(bsObj) ,re.M|re.I)

for art in arts:

art_str = “{”+str(art).split(‘{’)[1].replace(“')”,“}”)

art_dic = json.loads(art_str)

id = art_dic[‘id’]

name = art_dic[‘name’]

download_url = “https://api.z.itpub.net/download/file?st-usertoken=%s&id=%s”%(token,str(id))

print(download_url)

data = urlopen(download_url).read()

with open(path+category_name+‘__’+name, ‘wb’) as f:

f.write(data)

print("finish download ")

if name == ‘main’:

homepage = “https://z.itpub.net/article/detail/5260C494873379BAA63BAB7C5CBD7A95”

path = “/Users/xxx/Downloads/DTCC/”

download

category = visit_homepage(homepage)

for i in category:

download_pdf(i,path)

程序下载

========

1、cookie换成自己的

最后

不知道你们用的什么环境，我一般都是用的Python3.6环境和pycharm解释器，没有软件，或者没有资料，没人解答问题，都可以免费领取（包括今天的代码），过几天我还会做个视频教程出来，有需要也可以领取~

给大家准备的学习资料包括但不限于：

Python 环境、pycharm编辑器/永久激活/翻译插件

python 零基础视频教程

Python 界面开发实战教程

Python 爬虫实战教程

Python 数据分析实战教程

python 游戏开发实战教程

Python 电子书100本

Python 学习路线规划