python表情包斗图_Python爬取 斗图表情，让你成为斗图大佬

话不多说，上结果(只爬了10页内容)

上代码：(可直接运行)   用到Xpath

#encoding:utf-8

# __author__ = 'donghao'

# __time__ = 2018/12/24 15:20

import requests

import urllib.request

import urllib3

import os

import re

import time

from lxml import etree

def parse_page(url):

headers = {

'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:57.0) Gecko/20100101 Firefox/57.0'

}

resp = requests.get(url=url,headers=headers)

text = resp.text

html = etree.HTML(text)

imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']")

for img in imgs:

#获取图片url

img_url = img.get('data-original')

#获取图片Url的后缀名

end = os.path.splitext(img_url)[1]

#替换掉url中特殊字符

end = re.sub(r'[，。?？,/\\·]','',end)

# 获取图片描述,并加上后缀

name = img.get('alt')+end

#文件名为

#下载到本地文件夹

urllib.request.urlretrieve(img_url,'images/'+name)

def main():

#爬取10页

for x in range(1,10):

url = 'http://www.doutula.com/photo/list/?page=%d'%x

parse_page(url)

if __name__ == '__main__':

start = time.time()

main()

end = time.time()

print('耗时：%0.002fs' % (end - start))