简单几行代码轻松爬取表情包

对于喜欢斗图的小伙伴来说，通过幽默搞笑的图片压制对方就显得非常有成就感，幽默搞笑趣玩这也是表情包深受广大网友喜欢的主要原因，那么如何才能海量收集各种表情包，下面的几行代码拿走不谢。

# coding=utf-8

import requests
import re

def download_photo(name, url):
    res = requests.get(url)
    print(res.status_code)
    suffix = url.split('.')[-1]
    with open('photo/' + name + '.' + suffix, 'wb') as f:
        f.write(res.content)


"""
​​http://tva1.sinaimg.cn/large/6a2a7a61ly1gy5fd1pb7ij20iz0iz41l.jpg
​​
​​http://tva1.sinaimg.cn/large/6a2a7a61ly1gy5fd3od4lg208w08wdvb.gif
​​
​​https://www.fabiaoqing.com/bqb/lists/page/3.html
​​
"""


def download_page(url):
    # url = 'https://www.fabiaoqing.com/biaoqing/lists/page/3.html'
    res1 = requests.get(url)
    temp = '<img class="ui image lazy" data-original="(.*?)" src="/Public/lazyload/img/transparent.gif" title="(.*?)" alt="(.*?)" style="max-height:188;margin: 0 auto"/>'
    result1 = re.findall(temp, res1.text)
    print(result1)
    for img in result1:
        print(img)
        # name = img[0]
        # new_name = re.sub(r'[\/:*?;"<>|\n]', '_', name)
        # download_photo(img[1], new_name)
        download_photo(img[1], img[0])

# download_page('https://www.fabiaoqing.com/biaoqing/lists/page/3.html')


def download_all_page():
    for page in range(1, 50):
        pages = 'https://www.fabiaoqing.com/biaoqing/lists/page/' + str(page) + '.html'
        download_page(pages)

download_all_page()

上面的代码只要学会，轻松下载海量表情包，需要的小伙伴可以试试。