爬取文章写入doc文件中

最新推荐文章于 2024-06-28 10:52:10 发布

libinbin_1014

最新推荐文章于 2024-06-28 10:52:10 发布

阅读量409

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/libinbin_1014/article/details/107934257

版权

#-*-coding:utf-8-*-
import requests

import os
import time

from docx.shared import Inches
import docx
from bs4 import BeautifulSoup

headers = {
   
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:72.0) Gecko/20100101 Firefox/72.0"
}


def get_html(url):
	request = requests.get(url, headers=headers)
	return request.text

baseUrl = "https://www.jianshu.com"
url = "https://www.jianshu.com/c/1111111"

def download_img(href):
	url = "https:" + href
	name = url.split("/")[::-1][0]

	if os.path.exists("./pic/"+name):
		return "./pic/"+name

	rep = requests.get(url, headers=headers)
	f = open("./pic/"+name, "wb+")
	f.write