**度文库提取（仅作学习交流）

import requests,re

from lxml import etree

from docx import Document

def get_detail(url):

    header = {'User-agent': 'Googlebot'}

    response = requests.get(url , headers = header).content.decode('gbk')

    #print(response)

    title_ze=r'<title>(.+?)_百度文库</title>'

    div_ze=r'<div class="bd doc-reader">(.+?)<div class="aside">'

    title=re.findall(title_ze,response,re.S)[0]

    div=re.findall(div_ze,response,re.S)[0]

    div=etree.HTML(div)

    details=div.xpath('//div//text()')

    j=0

    for i in range(len(details)):

        if details[j] in [' ']:

            details.pop(j)

        else:

            j+=1

    data=title,details

    print(data)

    return data

def get_word(data):

    document = Document()

    document.add_heading(data[0])

    

    for detail in data[1]:

        document.add_paragraph(detail) #添加段落  

        document.save(f'C:/Users/Desktop/******.docx')

if __name__=='__main__':

    url="https://wenku.baidu.com/view/779f8c48cd22bcd126fff705cc17552706225e6d.html"

    text=get_detail(url)

    get_word(text)