用python爬虫爬取图虫网站图片

用python爬虫爬取图虫网站上的付费图片话不多说，直接上代码！import requestsimport reimport osimagIds = re.compile('"imageId":"(.*?)"')headers = {"User_Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,

前端技术

1550人浏览 · 2020-08-22 08:16:27

前端技术 · 2020-08-22 08:16:27 发布

用python爬虫爬取图虫网站上的付费图片

话不多说，直接上代码！

import requests
import re
import os

imagIds = re.compile('"imageId":"(.*?)"')

headers = {"User_Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36 Edg/84.0.522.59",
           "Accept-Encoding":""}

def get_page():
    url = "https://stock.tuchong.com/topic?topicId=49795"
    html = requests.get(url,headers=headers)
    results = imagIds.finditer(html.text)
    for r in results:
        imgurl = 'https://weiliicimg1.pstatp.com/weili/l/{}.jpg'.format(r.groups()[0])
        download_img(imgurl,r.groups()[0])

def download_img(url,name):
    if not os.path.exists("C:/Users/86135/Desktop/图虫"):
        os.mkdir("C:/Users/86135/Desktop/图虫")
    print('正在下载图片，ID：'+name)
    with open("C:/Users/86135/Desktop/图虫/{}.jpg".format(name),'wb') as f:
        f.write(requests.get(url,headers=headers).content)

if __name__ == '__main__':
    get_page()