百度文库爬取及PPT制作

最新推荐文章于 2021-06-29 20:38:07 发布

原创最新推荐文章于 2021-06-29 20:38:07 发布 · 1.7k 阅读

17 ·

CC 4.0 BY-SA版权

文章标签：

#爬取 #百度文库 #PPT #宏 #开发者模式

MakeStart 专栏收录该内容

3 篇文章

订阅专栏

本文介绍了一种使用Python爬虫从百度文库下载PPT的方法，通过解析网页获取图片链接并保存到本地文件夹，同时利用VB宏脚本批量创建PPT页面并导入图片。

今天帮媳妇儿做一个PPT，无奈百度文库没有积分。偶然用一次，如今互联网上哪哪都要充值还得是包月，很烦。
分两步：

爬取文库的PPT，输出图片，放到一个文件夹中
PPT开发者模式，写一个宏文件，批量创建PPT页并按顺序导入图片

下面是代码：
Python版爬虫脚本，输入参数是URL。PPT版的已经经过测试验证，其他的应该原理都一样，需要的自行验证。
VB版PPT宏脚本，文件夹路径需要自己指定。

import requests
import re
import argparse
import json
import os

# 根据文件决定函数
y = 0
def DOC(url):
    doc_id = re.findall('view/(.*).html', url)[0]
    html = requests.get(url).text
    lists = re.findall('(https.*?0.json.*?)\\\\x22}', html)
    lenth = (len(lists) // 2)
    NewLists = lists[:lenth]
    for i in range(len(NewLists)):
        NewLists[i] = NewLists[i].replace('\\', '')
        txts = requests.get(NewLists[i]).text
        txtlists = re.findall('"c":"(.*?)".*?"y":(.*?),', txts)
        for i in range(0, len(txtlists)):
            global y
            print(txtlists[i][0].encode('utf-8').decode('unicode_escape', 'ignore'))
            if y != txtlists[i][1]:
                y = txtlists[i][1]
                n = '\n'
            else:
                n = ''
            filename = doc_id + '.txt'
            with open(filename, 'a', encoding='utf-8') as f:
                f.write(n + txtlists[i][0].encode('utf-8').decode('unicode_escape', 'ignore').replace('\\', ''))
        print("文档保存在" + filename)


def PPT(url):
    doc_id = re.findall('view/(.*).html', url)[0]
    url = "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + doc_id + "&pn=1&rn=99999&type=ppt"
    html = requests.get(url).text
    lists = re.findall('{"zoom":"(.*?)","page"', html)
    for i in range(0, len(lists)):
        lists[i] = lists[i].replace("\\", '')
    try:
        os.mkdir(doc_id)
    except:
        pass
    for i in range(0, len(lists)):
        img = requests.get(lists[i]).content
        with open(doc_id + '\img' + str(i) + '.jpg', 'wb') as m:
            m.write(img)
    print("PPT图片保存在" + doc_id + "文件夹")


def TXT(url):
    doc_id = re.findall('view/(.*).html', url)[0]
    url = "https://wenku.baidu.com/api/doc/getdocinfo?callback=cb&doc_id=" + doc_id
    html = requests.get(url).text
    md5 = re.findall('"md5sum":"(.*?)"', html)[0]
    pn = re.findall('"totalPageNum":"(.*?)"', html)[0]
    rsign = re.findall('"rsign":"(.*?)"', html)[0]
    NewUrl = 'https://wkretype.bdimg.com/retype/text/' + doc_id + '?rn=' + pn + '&type=txt' + md5 + '&rsign=' + rsign
    txt = requests.get(NewUrl).text
    jsons = json.loads(txt)
    texts = re.findall("'c': '(.*?)',", str(jsons))
    print(texts)
    filename = doc_id + '.txt'
    with open(filename, 'a', encoding='utf-8') as f:
        for i in range(0, len(texts)):
            texts[i] = texts[i].replace('\\r', '\r')
            texts[i] = texts[i].replace('\\n', '\n')

            f.write(texts[i])
    print("文档保存在" + filename)


def FPD(url):
    doc_id = re.findall('view/(.*).html', url)[0]
    url = "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + doc_id + "&pn=1&rn=99999&type=ppt"
    html = requests.get(url).text
    lists = re.findall('{"zoom":"(.*?)","page"', html)
    for i in range(0, len(lists)):
        lists[i] = lists[i].replace("\\", '')
    try:
        os.mkdir(doc_id)
    except:
        pass
    for i in range(0, len(lists)):
        img = requests.get(lists[i]).content
        with open(doc_id + '\img' + str(i) + '.jpg', 'wb') as m:
            m.write(img)
    print("FPD图片保存在" + doc_id + "文件夹")


if __name__ == "__main__":
    PPT("https://wenku.baidu.com/view/361cbd5c7f21af45b307e87101f69e314332fac1.html")

Sub photos()
Dim i As Integer
For i = 1 To 59
    ActiveWindow.View.GotoSlide Index:=ActivePresentation.Slides.Add(Index:=i, Layout:=ppLayoutBlank).SlideIndex
    ActivePresentation.Slides(i).Select
    With ActiveWindow.Selection.SlideRange
        .FollowMasterBackground = msoFalse
        .Background.Fill.UserPicture "D:\img\img" & CStr(i - 1) & ".jpg"
    End With
Next
End Sub