爬取简书图片(使用BeautifulSoup)

import requests

from bs4 import BeautifulSoup

url_list = []

kv = {'User-Agent':'Mozilla/5.0'}

r = requests.get('https://www.jianshu.com/p/42df25cfc1ec',timeout=30,headers = kv)

# print(r.request.headers)

dome = r.text

soup = BeautifulSoup(dome,'html.parser')

# print(soup.prettify())

img_ = soup.find_all('img')

for i in img_:

    # print(i.get('src'))

    if i.get('data-original-src') != '//cdn2.jianshu.io/assets/web/nav-logo-4c7bbafe27adc892f3046e6978459bac.png' and i.get('data-original-src') != None:

        url_list.append(i.get('data-original-src'))

for i in url_list:

    image_name = i.split('/')[-1]

    response = requests.get(f'https:{i}')

    image_data = response.content

    with open(f"./image/{image_name}",'wb') as fw:

        fw.write(image_data)

巴特西

爬取简书图片(使用BeautifulSoup)

最新文章

热门文章