用python下载诗集并存入docx文件

用到的第三方库

re-用于正则表达式匹配

requests-用于获取网页内容

docx-用于存储docx格式文件

源代码

import re
import requests
from docx import Document

def str2doc(doc_title='', file_name='demo', text=''):
    '''将字符串存入docx'''
    document = Document()

    # 标题
    document.add_heading(doc_title, 0)
    # 添加文本
    p = document.add_paragraph(text,style='List Number')

    #保存文件
    document.save('%s'%file_name)

def get_poem(url_poem,down2where):
    '''获取网页上的诗集文本存入docx格式文件
    url_poem-诗集网页对应url
    down2where-文件路径及文件名称
    '''
    # 获取html文本
    resp = requests.get(url_poem)
    # 使用utf-8以防乱码
    resp.encoding = 'utf-8'
    text = resp.text
    poem = re.findall(r'<strong>现代诗精选</strong></p><p>(.*?)<li><a href="https://www.lz13.cn/shiju/51492.html">现代诗歌集</a></li>',text)[0]

    # 数据清洗
    keys_nextline = ['<br />','</p><p>']
    keys_none = re.findall(r'<a href=".*?">',poem)
    keys_none.extend(['《<strong>','</strong>》</p><p>','&mdash;&mdash;','&hellip;&hellip;','</p><ul>','</a>'])



    for key in keys_none:
        poem = poem.replace(key, '')
    for key in keys_nextline:
        poem = poem.replace(key,'\n')

    str2doc('现代诗集',down2where,poem)
    

'''测试代码'''
url_poem = 'https://www.lz13.cn/shiju/67254.html'
filename = '现代诗集.docx'
get_poem(url_poem,filename)